#!/usr/bin/env bun

/**

* Generate SKILL.md files from .tmpl templates.

*

* Pipeline:

* read .tmpl → find {{PLACEHOLDERS}} → resolve from source → format → write .md

*

* Supports --dry-run: generate to memory, exit 1 if different from committed file.

* Used by skill:check and CI freshness checks.

*/

import { COMMAND_DESCRIPTIONS } from '../browse/src/commands';

import { SNAPSHOT_FLAGS } from '../browse/src/snapshot';

import * as fs from 'fs';

import * as path from 'path';

const ROOT = path.resolve(import.meta.dir, '..');

const DRY_RUN = process.argv.includes('--dry-run');

// ─── Template Context ───────────────────────────────────────

type Host = 'claude' | 'codex';

const HOST_ARG = process.argv.find(a => a.startsWith('--host'));

const HOST: Host = (() => {

if (!HOST_ARG) return 'claude';

const val = HOST_ARG.includes('=') ? HOST_ARG.split('=')[1] : process.argv[process.argv.indexOf(HOST_ARG) + 1];

if (val === 'codex' || val === 'agents') return 'codex';

if (val === 'claude') return 'claude';

throw new Error(`Unknown host: ${val}. Use claude, codex, or agents.`);

})();

interface HostPaths {

skillRoot: string;

localSkillRoot: string;

binDir: string;

browseDir: string;

}

const HOST_PATHS: Record<Host, HostPaths> = {

claude: {

skillRoot: '~/.claude/skills/gstack',

localSkillRoot: '.claude/skills/gstack',

binDir: '~/.claude/skills/gstack/bin',

browseDir: '~/.claude/skills/gstack/browse/dist',

},

codex: {

skillRoot: '~/.codex/skills/gstack',

localSkillRoot: '.agents/skills/gstack',

binDir: '~/.codex/skills/gstack/bin',

browseDir: '~/.codex/skills/gstack/browse/dist',

},

};

interface TemplateContext {

skillName: string;

tmplPath: string;

benefitsFrom?: string[];

host: Host;

paths: HostPaths;

}

// ─── Placeholder Resolvers ──────────────────────────────────

function generateCommandReference(_ctx: TemplateContext): string {

// Group commands by category

const groups = new Map<string, Array<{ command: string; description: string; usage?: string }>>();

for (const [cmd, meta] of Object.entries(COMMAND_DESCRIPTIONS)) {

const list = groups.get(meta.category) || [];

list.push({ command: cmd, description: meta.description, usage: meta.usage });

groups.set(meta.category, list);

}

// Category display order

const categoryOrder = [

'Navigation', 'Reading', 'Interaction', 'Inspection',

'Visual', 'Snapshot', 'Meta', 'Tabs', 'Server',

];

const sections: string[] = [];

for (const category of categoryOrder) {

const commands = groups.get(category);

if (!commands || commands.length === 0) continue;

// Sort alphabetically within category

commands.sort((a, b) => a.command.localeCompare(b.command));

sections.push(`### ${category}`);

sections.push('| Command | Description |');

sections.push('|---------|-------------|');

for (const cmd of commands) {

const display = cmd.usage ? `\`${cmd.usage}\`` : `\`${cmd.command}\``;

sections.push(`| ${display} | ${cmd.description} |`);

}

sections.push('');

}

return sections.join('\n').trimEnd();

}

function generateSnapshotFlags(_ctx: TemplateContext): string {

const lines: string[] = [

'The snapshot is your primary tool for understanding and interacting with pages.',

'',

'```',

];

for (const flag of SNAPSHOT_FLAGS) {

const label = flag.valueHint ? `${flag.short} ${flag.valueHint}` : flag.short;

lines.push(`${label.padEnd(10)}${flag.long.padEnd(24)}${flag.description}`);

}

lines.push('```');

lines.push('');

lines.push('All flags can be combined freely. `-o` only applies when `-a` is also used.');

lines.push('Example: `$B snapshot -i -a -C -o /tmp/annotated.png`');

lines.push('');

lines.push('**Ref numbering:** @e refs are assigned sequentially (@e1, @e2, ...) in tree order.');

lines.push('@c refs from `-C` are numbered separately (@c1, @c2, ...).');

lines.push('');

lines.push('After snapshot, use @refs as selectors in any command:');

lines.push('```bash');

lines.push('$B click @e3 $B fill @e4 "value" $B hover @e1');

lines.push('$B html @e2 $B css @e5 "color" $B attrs @e6');

lines.push('$B click @c1 # cursor-interactive ref (from -C)');

lines.push('```');

lines.push('');

lines.push('**Output format:** indented accessibility tree with @ref IDs, one element per line.');

lines.push('```');

lines.push(' @e1 [heading] "Welcome" [level=1]');

lines.push(' @e2 [textbox] "Email"');

lines.push(' @e3 [button] "Submit"');

lines.push('```');

lines.push('');

lines.push('Refs are invalidated on navigation — run `snapshot` again after `goto`.');

return lines.join('\n');

}

function generatePreambleBash(ctx: TemplateContext): string {

return `## Preamble (run first)

\`\`\`bash

_UPD=$(${ctx.paths.binDir}/gstack-update-check 2>/dev/null || ${ctx.paths.localSkillRoot}/bin/gstack-update-check 2>/dev/null || true)

[ -n "$_UPD" ] && echo "$_UPD" || true

mkdir -p ~/.gstack/sessions

touch ~/.gstack/sessions/"$PPID"

_SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')

find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true

_CONTRIB=$(${ctx.paths.binDir}/gstack-config get gstack_contributor 2>/dev/null || true)

_PROACTIVE=$(${ctx.paths.binDir}/gstack-config get proactive 2>/dev/null || echo "true")

_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")

echo "BRANCH: $_BRANCH"

echo "PROACTIVE: $_PROACTIVE"

_LAKE_SEEN=$([ -f ~/.gstack/.completeness-intro-seen ] && echo "yes" || echo "no")

echo "LAKE_INTRO: $_LAKE_SEEN"

_TEL=$(~/.claude/skills/gstack/bin/gstack-config get telemetry 2>/dev/null || true)

_TEL_PROMPTED=$([ -f ~/.gstack/.telemetry-prompted ] && echo "yes" || echo "no")

_TEL_START=$(date +%s)

_SESSION_ID="$$-$(date +%s)"

echo "TELEMETRY: \${_TEL:-off}"

echo "TEL_PROMPTED: $_TEL_PROMPTED"

mkdir -p ~/.gstack/analytics

echo '{"skill":"${ctx.skillName}","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","repo":"'$(basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown")'"}' >> ~/.gstack/analytics/skill-usage.jsonl 2>/dev/null || true

for _PF in ~/.gstack/analytics/.pending-*; do [ -f "$_PF" ] && ${ctx.paths.binDir}/gstack-telemetry-log --event-type skill_run --skill _pending_finalize --outcome unknown --session-id "$_SESSION_ID" 2>/dev/null || true; break; done

\`\`\``;

}

function generateUpgradeCheck(ctx: TemplateContext): string {

return `If \`PROACTIVE\` is \`"false"\`, do not proactively suggest gstack skills — only invoke

them when the user explicitly asks. The user opted out of proactive suggestions.

If output shows \`UPGRADE_AVAILABLE <old> <new>\`: read \`${ctx.paths.skillRoot}/gstack-upgrade/SKILL.md\` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If \`JUST_UPGRADED <from> <to>\`: tell user "Running gstack v{to} (just updated!)" and continue.`;

}

function generateLakeIntro(): string {

return `If \`LAKE_INTRO\` is \`no\`: Before continuing, introduce the Completeness Principle.

Tell the user: "gstack follows the **Boil the Lake** principle — always do the complete

thing when AI makes the marginal cost near-zero. Read more: https://garryslist.org/posts/boil-the-ocean"

Then offer to open the essay in their default browser:

\`\`\`bash

open https://garryslist.org/posts/boil-the-ocean

touch ~/.gstack/.completeness-intro-seen

\`\`\`

Only run \`open\` if the user says yes. Always run \`touch\` to mark as seen. This only happens once.`;

}

function generateTelemetryPrompt(ctx: TemplateContext): string {

return `If \`TEL_PROMPTED\` is \`no\` AND \`LAKE_INTRO\` is \`yes\`: After the lake intro is handled,

ask the user about telemetry. Use AskUserQuestion:

> Help gstack get better! Community mode shares usage data (which skills you use, how long

> they take, crash info) with a stable device ID so we can track trends and fix bugs faster.

> No code, file paths, or repo names are ever sent.

> Change anytime with \`gstack-config set telemetry off\`.

Options:

- A) Help gstack get better! (recommended)

- B) No thanks

If A: run \`${ctx.paths.binDir}/gstack-config set telemetry community\`

If B: ask a follow-up AskUserQuestion:

> How about anonymous mode? We just learn that *someone* used gstack — no unique ID,

> no way to connect sessions. Just a counter that helps us know if anyone's out there.

Options:

- A) Sure, anonymous is fine

- B) No thanks, fully off

If B→A: run \`${ctx.paths.binDir}/gstack-config set telemetry anonymous\`

If B→B: run \`${ctx.paths.binDir}/gstack-config set telemetry off\`

Always run:

\`\`\`bash

touch ~/.gstack/.telemetry-prompted

\`\`\`

This only happens once. If \`TEL_PROMPTED\` is \`yes\`, skip this entirely.`;

}

function generateAskUserFormat(_ctx: TemplateContext): string {

return `## AskUserQuestion Format

**ALWAYS follow this structure for every AskUserQuestion call:**

1. **Re-ground:** State the project, the current branch (use the \`_BRANCH\` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)

2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.

3. **Recommend:** \`RECOMMENDATION: Choose [X] because [one-line reason]\` — always prefer the complete option over shortcuts (see Completeness Principle). Include \`Completeness: X/10\` for each option. Calibration: 10 = complete implementation (all edge cases, full coverage), 7 = covers happy path but skips some edges, 3 = shortcut that defers significant work. If both options are 8+, pick the higher; if one is ≤5, flag it.

4. **Options:** Lettered options: \`A) ... B) ... C) ...\` — when an option involves effort, show both scales: \`(human: ~X / CC: ~Y)\`

Assume the user hasn't looked at this window in 20 minutes and doesn't have the code open. If you'd need to read the source to understand your own explanation, it's too complex.

Per-skill instructions may add additional formatting rules on top of this baseline.`;

}

function generateCompletenessSection(): string {

return `## Completeness Principle — Boil the Lake

AI-assisted coding makes the marginal cost of completeness near-zero. When you present options:

- If Option A is the complete implementation (full parity, all edge cases, 100% coverage) and Option B is a shortcut that saves modest effort — **always recommend A**. The delta between 80 lines and 150 lines is meaningless with CC+gstack. "Good enough" is the wrong instinct when "complete" costs minutes more.

- **Lake vs. ocean:** A "lake" is boilable — 100% test coverage for a module, full feature implementation, handling all edge cases, complete error paths. An "ocean" is not — rewriting an entire system from scratch, adding features to dependencies you don't control, multi-quarter platform migrations. Recommend boiling lakes. Flag oceans as out of scope.

- **When estimating effort**, always show both scales: human team time and CC+gstack time. The compression ratio varies by task type — use this reference:

| Task type | Human team | CC+gstack | Compression |

|-----------|-----------|-----------|-------------|

| Boilerplate / scaffolding | 2 days | 15 min | ~100x |

| Test writing | 1 day | 15 min | ~50x |

| Feature implementation | 1 week | 30 min | ~30x |

| Bug fix + regression test | 4 hours | 15 min | ~20x |

| Architecture / design | 2 days | 4 hours | ~5x |

| Research / exploration | 1 day | 3 hours | ~3x |

- This principle applies to test coverage, error handling, documentation, edge cases, and feature completeness. Don't skip the last 10% to "save time" — with AI, that 10% costs seconds.

**Anti-patterns — DON'T do this:**

- BAD: "Choose B — it covers 90% of the value with less code." (If A is only 70 lines more, choose A.)

- BAD: "We can skip edge case handling to save time." (Edge case handling costs minutes with CC.)

- BAD: "Let's defer test coverage to a follow-up PR." (Tests are the cheapest lake to boil.)

- BAD: Quoting only human-team effort: "This would take 2 weeks." (Say: "2 weeks human / ~1 hour CC.")`;

}

function generateSearchBeforeBuildingSection(ctx: TemplateContext): string {

return `## Search Before Building

Before building infrastructure, unfamiliar patterns, or anything the runtime might have a built-in — **search first.** Read \`${ctx.paths.skillRoot}/ETHOS.md\` for the full philosophy.

**Three layers of knowledge:**

- **Layer 1** (tried and true — in distribution). Don't reinvent the wheel. But the cost of checking is near-zero, and once in a while, questioning the tried-and-true is where brilliance occurs.

- **Layer 2** (new and popular — search for these). But scrutinize: humans are subject to mania. Search results are inputs to your thinking, not answers.

- **Layer 3** (first principles — prize these above all). Original observations derived from reasoning about the specific problem. The most valuable of all.

**Eureka moment:** When first-principles reasoning reveals conventional wisdom is wrong, name it:

"EUREKA: Everyone does X because [assumption]. But [evidence] shows this is wrong. Y is better because [reasoning]."

Log eureka moments:

\`\`\`bash

jq -n --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" --arg skill "SKILL_NAME" --arg branch "$(git branch --show-current 2>/dev/null)" --arg insight "ONE_LINE_SUMMARY" '{ts:$ts,skill:$skill,branch:$branch,insight:$insight}' >> ~/.gstack/analytics/eureka.jsonl 2>/dev/null || true

\`\`\`

Replace SKILL_NAME and ONE_LINE_SUMMARY. Runs inline — don't stop the workflow.

**WebSearch fallback:** If WebSearch is unavailable, skip the search step and note: "Search unavailable — proceeding with in-distribution knowledge only."`;

}

function generateContributorMode(): string {

return `## Contributor Mode

If \`_CONTRIB\` is \`true\`: you are in **contributor mode**. You're a gstack user who also helps make it better.

**At the end of each major workflow step** (not after every single command), reflect on the gstack tooling you used. Rate your experience 0 to 10. If it wasn't a 10, think about why. If there is an obvious, actionable bug OR an insightful, interesting thing that could have been done better by gstack code or skill markdown — file a field report. Maybe our contributor will help make us better!

**Calibration — this is the bar:** For example, \`$B js "await fetch(...)"\` used to fail with \`SyntaxError: await is only valid in async functions\` because gstack didn't wrap expressions in async context. Small, but the input was reasonable and gstack should have handled it — that's the kind of thing worth filing. Things less consequential than this, ignore.

**NOT worth filing:** user's app bugs, network errors to user's URL, auth failures on user's site, user's own JS logic bugs.

**To file:** write \`~/.gstack/contributor-logs/{slug}.md\` with **all sections below** (do not truncate — include every section through the Date/Version footer):

\`\`\`

# {Title}

Hey gstack team — ran into this while using /{skill-name}:

**What I was trying to do:** {what the user/agent was attempting}

**What happened instead:** {what actually happened}

**My rating:** {0-10} — {one sentence on why it wasn't a 10}

## Steps to reproduce

1. {step}

## Raw output

\`\`\`

{paste the actual error or unexpected output here}

\`\`\`

## What would make this a 10

{one sentence: what gstack should have done differently}

**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}

\`\`\`

Slug: lowercase, hyphens, max 60 chars (e.g. \`browse-js-no-await\`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"`;

}

function generateCompletionStatus(): string {

return `## Completion Status Protocol

When completing a skill workflow, report status using one of:

- **DONE** — All steps completed successfully. Evidence provided for each claim.

- **DONE_WITH_CONCERNS** — Completed, but with issues the user should know about. List each concern.

- **BLOCKED** — Cannot proceed. State what is blocking and what was tried.

- **NEEDS_CONTEXT** — Missing information required to continue. State exactly what you need.

### Escalation

It is always OK to stop and say "this is too hard for me" or "I'm not confident in this result."

Bad work is worse than no work. You will not be penalized for escalating.

- If you have attempted a task 3 times without success, STOP and escalate.

- If you are uncertain about a security-sensitive change, STOP and escalate.

- If the scope of work exceeds what you can verify, STOP and escalate.

Escalation format:

\`\`\`

STATUS: BLOCKED | NEEDS_CONTEXT

REASON: [1-2 sentences]

ATTEMPTED: [what you tried]

RECOMMENDATION: [what the user should do next]

\`\`\`

## Telemetry (run last)

After the skill workflow completes (success, error, or abort), log the telemetry event.

Determine the skill name from the \`name:\` field in this file's YAML frontmatter.

Determine the outcome from the workflow result (success if completed normally, error

if it failed, abort if the user interrupted).

**PLAN MODE EXCEPTION — ALWAYS RUN:** This command writes telemetry to

\`~/.gstack/analytics/\` (user config directory, not project files). The skill

preamble already writes to the same directory — this is the same pattern.

Skipping this command loses session duration and outcome data.

Run this bash:

\`\`\`bash

_TEL_END=$(date +%s)

_TEL_DUR=$(( _TEL_END - _TEL_START ))

rm -f ~/.gstack/analytics/.pending-"$_SESSION_ID" 2>/dev/null || true

~/.claude/skills/gstack/bin/gstack-telemetry-log \\

--skill "SKILL_NAME" --duration "$_TEL_DUR" --outcome "OUTCOME" \\

--used-browse "USED_BROWSE" --session-id "$_SESSION_ID" 2>/dev/null &

\`\`\`

Replace \`SKILL_NAME\` with the actual skill name from frontmatter, \`OUTCOME\` with

success/error/abort, and \`USED_BROWSE\` with true/false based on whether \`$B\` was used.

If you cannot determine the outcome, use "unknown". This runs in the background and

never blocks the user.`;

}

function generatePreamble(ctx: TemplateContext): string {

return [

generatePreambleBash(ctx),

generateUpgradeCheck(ctx),

generateLakeIntro(),

generateTelemetryPrompt(ctx),

generateAskUserFormat(ctx),

generateCompletenessSection(),

generateSearchBeforeBuildingSection(ctx),

generateContributorMode(),

generateCompletionStatus(),

].join('\n\n');

}

function generateBrowseSetup(ctx: TemplateContext): string {

return `## SETUP (run this check BEFORE any browse command)

\`\`\`bash

_ROOT=$(git rev-parse --show-toplevel 2>/dev/null)

B=""

[ -n "$_ROOT" ] && [ -x "$_ROOT/${ctx.paths.localSkillRoot}/browse/dist/browse" ] && B="$_ROOT/${ctx.paths.localSkillRoot}/browse/dist/browse"

[ -z "$B" ] && B=${ctx.paths.browseDir}/browse

if [ -x "$B" ]; then

echo "READY: $B"

else

echo "NEEDS_SETUP"

fi

\`\`\`

If \`NEEDS_SETUP\`:

1. Tell the user: "gstack browse needs a one-time build (~10 seconds). OK to proceed?" Then STOP and wait.

2. Run: \`cd <SKILL_DIR> && ./setup\`

3. If \`bun\` is not installed: \`curl -fsSL https://bun.sh/install | bash\``;

}

function generateBaseBranchDetect(_ctx: TemplateContext): string {

return `## Step 0: Detect base branch

Determine which branch this PR targets. Use the result as "the base branch" in all subsequent steps.

1. Check if a PR already exists for this branch:

\`gh pr view --json baseRefName -q .baseRefName\`

If this succeeds, use the printed branch name as the base branch.

2. If no PR exists (command fails), detect the repo's default branch:

\`gh repo view --json defaultBranchRef -q .defaultBranchRef.name\`

3. If both commands fail, fall back to \`main\`.

Print the detected base branch name. In every subsequent \`git diff\`, \`git log\`,

\`git fetch\`, \`git merge\`, and \`gh pr create\` command, substitute the detected

branch name wherever the instructions say "the base branch."

---`;

}

function generateQAMethodology(_ctx: TemplateContext): string {

return `## Modes

### Diff-aware (automatic when on a feature branch with no URL)

This is the **primary mode** for developers verifying their work. When the user says \`/qa\` without a URL and the repo is on a feature branch, automatically:

1. **Analyze the branch diff** to understand what changed:

\`\`\`bash

git diff main...HEAD --name-only

git log main..HEAD --oneline

\`\`\`

2. **Identify affected pages/routes** from the changed files:

- Controller/route files → which URL paths they serve

- View/template/component files → which pages render them

- Model/service files → which pages use those models (check controllers that reference them)

- CSS/style files → which pages include those stylesheets

- API endpoints → test them directly with \`$B js "await fetch('/api/...')"\`

- Static pages (markdown, HTML) → navigate to them directly

**If no obvious pages/routes are identified from the diff:** Do not skip browser testing. The user invoked /qa because they want browser-based verification. Fall back to Quick mode — navigate to the homepage, follow the top 5 navigation targets, check console for errors, and test any interactive elements found. Backend, config, and infrastructure changes affect app behavior — always verify the app still works.

3. **Detect the running app** — check common local dev ports:

\`\`\`bash

$B goto http://localhost:3000 2>/dev/null && echo "Found app on :3000" || \\

$B goto http://localhost:4000 2>/dev/null && echo "Found app on :4000" || \\

$B goto http://localhost:8080 2>/dev/null && echo "Found app on :8080"

\`\`\`

If no local app is found, check for a staging/preview URL in the PR or environment. If nothing works, ask the user for the URL.

4. **Test each affected page/route:**

- Navigate to the page

- Take a screenshot

- Check console for errors

- If the change was interactive (forms, buttons, flows), test the interaction end-to-end

- Use \`snapshot -D\` before and after actions to verify the change had the expected effect

5. **Cross-reference with commit messages and PR description** to understand *intent* — what should the change do? Verify it actually does that.

6. **Check TODOS.md** (if it exists) for known bugs or issues related to the changed files. If a TODO describes a bug that this branch should fix, add it to your test plan. If you find a new bug during QA that isn't in TODOS.md, note it in the report.

7. **Report findings** scoped to the branch changes:

- "Changes tested: N pages/routes affected by this branch"

- For each: does it work? Screenshot evidence.

- Any regressions on adjacent pages?

**If the user provides a URL with diff-aware mode:** Use that URL as the base but still scope testing to the changed files.

### Full (default when URL is provided)

Systematic exploration. Visit every reachable page. Document 5-10 well-evidenced issues. Produce health score. Takes 5-15 minutes depending on app size.

### Quick (\`--quick\`)

30-second smoke test. Visit homepage + top 5 navigation targets. Check: page loads? Console errors? Broken links? Produce health score. No detailed issue documentation.

### Regression (\`--regression <baseline>\`)

Run full mode, then load \`baseline.json\` from a previous run. Diff: which issues are fixed? Which are new? What's the score delta? Append regression section to report.

---

## Workflow

### Phase 1: Initialize

1. Find browse binary (see Setup above)

2. Create output directories

3. Copy report template from \`qa/templates/qa-report-template.md\` to output dir

4. Start timer for duration tracking

### Phase 2: Authenticate (if needed)

**If the user specified auth credentials:**

\`\`\`bash

$B goto <login-url>

$B snapshot -i # find the login form

$B fill @e3 "[email protected]"

$B fill @e4 "[REDACTED]" # NEVER include real passwords in report

$B click @e5 # submit

$B snapshot -D # verify login succeeded

\`\`\`

**If the user provided a cookie file:**

\`\`\`bash

$B cookie-import cookies.json

$B goto <target-url>

\`\`\`

**If 2FA/OTP is required:** Ask the user for the code and wait.

**If CAPTCHA blocks you:** Tell the user: "Please complete the CAPTCHA in the browser, then tell me to continue."

### Phase 3: Orient

Get a map of the application:

\`\`\`bash

$B goto <target-url>

$B snapshot -i -a -o "$REPORT_DIR/screenshots/initial.png"

$B links # map navigation structure

$B console --errors # any errors on landing?

\`\`\`

**Detect framework** (note in report metadata):

- \`__next\` in HTML or \`_next/data\` requests → Next.js

- \`csrf-token\` meta tag → Rails

- \`wp-content\` in URLs → WordPress

- Client-side routing with no page reloads → SPA

**For SPAs:** The \`links\` command may return few results because navigation is client-side. Use \`snapshot -i\` to find nav elements (buttons, menu items) instead.

### Phase 4: Explore

Visit pages systematically. At each page:

\`\`\`bash

$B goto <page-url>

$B snapshot -i -a -o "$REPORT_DIR/screenshots/page-name.png"

$B console --errors

\`\`\`

Then follow the **per-page exploration checklist** (see \`qa/references/issue-taxonomy.md\`):

1. **Visual scan** — Look at the annotated screenshot for layout issues

2. **Interactive elements** — Click buttons, links, controls. Do they work?

3. **Forms** — Fill and submit. Test empty, invalid, edge cases

4. **Navigation** — Check all paths in and out

5. **States** — Empty state, loading, error, overflow

6. **Console** — Any new JS errors after interactions?

7. **Responsiveness** — Check mobile viewport if relevant:

\`\`\`bash

$B viewport 375x812

$B screenshot "$REPORT_DIR/screenshots/page-mobile.png"

$B viewport 1280x720

\`\`\`

**Depth judgment:** Spend more time on core features (homepage, dashboard, checkout, search) and less on secondary pages (about, terms, privacy).

**Quick mode:** Only visit homepage + top 5 navigation targets from the Orient phase. Skip the per-page checklist — just check: loads? Console errors? Broken links visible?

### Phase 5: Document

Document each issue **immediately when found** — don't batch them.

**Two evidence tiers:**

**Interactive bugs** (broken flows, dead buttons, form failures):

1. Take a screenshot before the action

2. Perform the action

3. Take a screenshot showing the result

4. Use \`snapshot -D\` to show what changed

5. Write repro steps referencing screenshots

\`\`\`bash

$B screenshot "$REPORT_DIR/screenshots/issue-001-step-1.png"

$B click @e5

$B screenshot "$REPORT_DIR/screenshots/issue-001-result.png"

$B snapshot -D

\`\`\`

**Static bugs** (typos, layout issues, missing images):

1. Take a single annotated screenshot showing the problem

2. Describe what's wrong

\`\`\`bash

$B snapshot -i -a -o "$REPORT_DIR/screenshots/issue-002.png"

\`\`\`

**Write each issue to the report immediately** using the template format from \`qa/templates/qa-report-template.md\`.

### Phase 6: Wrap Up

1. **Compute health score** using the rubric below

2. **Write "Top 3 Things to Fix"** — the 3 highest-severity issues

3. **Write console health summary** — aggregate all console errors seen across pages

4. **Update severity counts** in the summary table

5. **Fill in report metadata** — date, duration, pages visited, screenshot count, framework

6. **Save baseline** — write \`baseline.json\` with:

\`\`\`json

{

"date": "YYYY-MM-DD",

"url": "<target>",

"healthScore": N,

"issues": [{ "id": "ISSUE-001", "title": "...", "severity": "...", "category": "..." }],

"categoryScores": { "console": N, "links": N, ... }

}

\`\`\`

**Regression mode:** After writing the report, load the baseline file. Compare:

- Health score delta

- Issues fixed (in baseline but not current)

- New issues (in current but not baseline)

- Append the regression section to the report

---

## Health Score Rubric

Compute each category score (0-100), then take the weighted average.

### Console (weight: 15%)

- 0 errors → 100

- 1-3 errors → 70

- 4-10 errors → 40

- 10+ errors → 10

### Links (weight: 10%)

- 0 broken → 100

- Each broken link → -15 (minimum 0)

### Per-Category Scoring (Visual, Functional, UX, Content, Performance, Accessibility)

Each category starts at 100. Deduct per finding:

- Critical issue → -25

- High issue → -15

- Medium issue → -8

- Low issue → -3

Minimum 0 per category.

### Weights

| Category | Weight |

|----------|--------|

| Console | 15% |

| Links | 10% |

| Visual | 10% |

| Functional | 20% |

| UX | 15% |

| Performance | 10% |

| Content | 5% |

| Accessibility | 15% |

### Final Score

\`score = Σ (category_score × weight)\`

---

## Framework-Specific Guidance

### Next.js

- Check console for hydration errors (\`Hydration failed\`, \`Text content did not match\`)

- Monitor \`_next/data\` requests in network — 404s indicate broken data fetching

- Test client-side navigation (click links, don't just \`goto\`) — catches routing issues

- Check for CLS (Cumulative Layout Shift) on pages with dynamic content

### Rails

- Check for N+1 query warnings in console (if development mode)

- Verify CSRF token presence in forms

- Test Turbo/Stimulus integration — do page transitions work smoothly?

- Check for flash messages appearing and dismissing correctly

### WordPress

- Check for plugin conflicts (JS errors from different plugins)

- Verify admin bar visibility for logged-in users

- Test REST API endpoints (\`/wp-json/\`)

- Check for mixed content warnings (common with WP)

### General SPA (React, Vue, Angular)

- Use \`snapshot -i\` for navigation — \`links\` command misses client-side routes

- Check for stale state (navigate away and back — does data refresh?)

- Test browser back/forward — does the app handle history correctly?

- Check for memory leaks (monitor console after extended use)

---

## Important Rules

1. **Repro is everything.** Every issue needs at least one screenshot. No exceptions.

2. **Verify before documenting.** Retry the issue once to confirm it's reproducible, not a fluke.

3. **Never include credentials.** Write \`[REDACTED]\` for passwords in repro steps.

4. **Write incrementally.** Append each issue to the report as you find it. Don't batch.

5. **Never read source code.** Test as a user, not a developer.

6. **Check console after every interaction.** JS errors that don't surface visually are still bugs.

7. **Test like a user.** Use realistic data. Walk through complete workflows end-to-end.

8. **Depth over breadth.** 5-10 well-documented issues with evidence > 20 vague descriptions.

9. **Never delete output files.** Screenshots and reports accumulate — that's intentional.

10. **Use \`snapshot -C\` for tricky UIs.** Finds clickable divs that the accessibility tree misses.

11. **Show screenshots to the user.** After every \`$B screenshot\`, \`$B snapshot -a -o\`, or \`$B responsive\` command, use the Read tool on the output file(s) so the user can see them inline. For \`responsive\` (3 files), Read all three. This is critical — without it, screenshots are invisible to the user.

12. **Never refuse to use the browser.** When the user invokes /qa or /qa-only, they are requesting browser-based testing. Never suggest evals, unit tests, or other alternatives as a substitute. Even if the diff appears to have no UI changes, backend changes affect app behavior — always open the browser and test.`;

}

function generateDesignReviewLite(_ctx: TemplateContext): string {

return `## Design Review (conditional, diff-scoped)

Check if the diff touches frontend files using \`gstack-diff-scope\`:

\`\`\`bash

source <(~/.claude/skills/gstack/bin/gstack-diff-scope <base> 2>/dev/null)

\`\`\`

**If \`SCOPE_FRONTEND=false\`:** Skip design review silently. No output.

**If \`SCOPE_FRONTEND=true\`:**

1. **Check for DESIGN.md.** If \`DESIGN.md\` or \`design-system.md\` exists in the repo root, read it. All design findings are calibrated against it — patterns blessed in DESIGN.md are not flagged. If not found, use universal design principles.

2. **Read \`.claude/skills/review/design-checklist.md\`.** If the file cannot be read, skip design review with a note: "Design checklist not found — skipping design review."

3. **Read each changed frontend file** (full file, not just diff hunks). Frontend files are identified by the patterns listed in the checklist.

4. **Apply the design checklist** against the changed files. For each item:

- **[HIGH] mechanical CSS fix** (\`outline: none\`, \`!important\`, \`font-size < 16px\`): classify as AUTO-FIX

- **[HIGH/MEDIUM] design judgment needed**: classify as ASK

- **[LOW] intent-based detection**: present as "Possible — verify visually or run /design-review"

5. **Include findings** in the review output under a "Design Review" header, following the output format in the checklist. Design findings merge with code review findings into the same Fix-First flow.

6. **Log the result** for the Review Readiness Dashboard:

\`\`\`bash

~/.claude/skills/gstack/bin/gstack-review-log '{"skill":"design-review-lite","timestamp":"TIMESTAMP","status":"STATUS","findings":N,"auto_fixed":M,"commit":"COMMIT"}'

\`\`\`

Substitute: TIMESTAMP = ISO 8601 datetime, STATUS = "clean" if 0 findings or "issues_found", N = total findings, M = auto-fixed count, COMMIT = output of \`git rev-parse --short HEAD\`.`;

}

// NOTE: design-checklist.md is a subset of this methodology for code-level detection.

// When adding items here, also update review/design-checklist.md, and vice versa.

function generateDesignMethodology(_ctx: TemplateContext): string {

return `## Modes

### Full (default)

Systematic review of all pages reachable from homepage. Visit 5-8 pages. Full checklist evaluation, responsive screenshots, interaction flow testing. Produces complete design audit report with letter grades.

### Quick (\`--quick\`)

Homepage + 2 key pages only. First Impression + Design System Extraction + abbreviated checklist. Fastest path to a design score.

### Deep (\`--deep\`)

Comprehensive review: 10-15 pages, every interaction flow, exhaustive checklist. For pre-launch audits or major redesigns.

### Diff-aware (automatic when on a feature branch with no URL)

When on a feature branch, scope to pages affected by the branch changes:

1. Analyze the branch diff: \`git diff main...HEAD --name-only\`

2. Map changed files to affected pages/routes

3. Detect running app on common local ports (3000, 4000, 8080)

4. Audit only affected pages, compare design quality before/after

### Regression (\`--regression\` or previous \`design-baseline.json\` found)

Run full audit, then load previous \`design-baseline.json\`. Compare: per-category grade deltas, new findings, resolved findings. Output regression table in report.

---

## Phase 1: First Impression

The most uniquely designer-like output. Form a gut reaction before analyzing anything.

1. Navigate to the target URL

2. Take a full-page desktop screenshot: \`$B screenshot "$REPORT_DIR/screenshots/first-impression.png"\`

3. Write the **First Impression** using this structured critique format:

- "The site communicates **[what]**." (what it says at a glance — competence? playfulness? confusion?)

- "I notice **[observation]**." (what stands out, positive or negative — be specific)

- "The first 3 things my eye goes to are: **[1]**, **[2]**, **[3]**." (hierarchy check — are these intentional?)

- "If I had to describe this in one word: **[word]**." (gut verdict)

This is the section users read first. Be opinionated. A designer doesn't hedge — they react.

---

## Phase 2: Design System Extraction

Extract the actual design system the site uses (not what a DESIGN.md says, but what's rendered):

\`\`\`bash

# Fonts in use (capped at 500 elements to avoid timeout)

$B js "JSON.stringify([...new Set([...document.querySelectorAll('*')].slice(0,500).map(e => getComputedStyle(e).fontFamily))])"

# Color palette in use

$B js "JSON.stringify([...new Set([...document.querySelectorAll('*')].slice(0,500).flatMap(e => [getComputedStyle(e).color, getComputedStyle(e).backgroundColor]).filter(c => c !== 'rgba(0, 0, 0, 0)'))])"

# Heading hierarchy

$B js "JSON.stringify([...document.querySelectorAll('h1,h2,h3,h4,h5,h6')].map(h => ({tag:h.tagName, text:h.textContent.trim().slice(0,50), size:getComputedStyle(h).fontSize, weight:getComputedStyle(h).fontWeight})))"

# Touch target audit (find undersized interactive elements)

$B js "JSON.stringify([...document.querySelectorAll('a,button,input,[role=button]')].filter(e => {const r=e.getBoundingClientRect(); return r.width>0 && (r.width<44||r.height<44)}).map(e => ({tag:e.tagName, text:(e.textContent||'').trim().slice(0,30), w:Math.round(e.getBoundingClientRect().width), h:Math.round(e.getBoundingClientRect().height)})).slice(0,20))"

# Performance baseline

$B perf

\`\`\`

Structure findings as an **Inferred Design System**:

- **Fonts:** list with usage counts. Flag if >3 distinct font families.

- **Colors:** palette extracted. Flag if >12 unique non-gray colors. Note warm/cool/mixed.

- **Heading Scale:** h1-h6 sizes. Flag skipped levels, non-systematic size jumps.

- **Spacing Patterns:** sample padding/margin values. Flag non-scale values.

After extraction, offer: *"Want me to save this as your DESIGN.md? I can lock in these observations as your project's design system baseline."*

---

## Phase 3: Page-by-Page Visual Audit

For each page in scope:

\`\`\`bash

$B goto <url>

$B snapshot -i -a -o "$REPORT_DIR/screenshots/{page}-annotated.png"

$B responsive "$REPORT_DIR/screenshots/{page}"

$B console --errors

$B perf

\`\`\`

### Auth Detection

After the first navigation, check if the URL changed to a login-like path:

\`\`\`bash

$B url

\`\`\`

If URL contains \`/login\`, \`/signin\`, \`/auth\`, or \`/sso\`: the site requires authentication. AskUserQuestion: "This site requires authentication. Want to import cookies from your browser? Run \`/setup-browser-cookies\` first if needed."

### Design Audit Checklist (10 categories, ~80 items)

Apply these at each page. Each finding gets an impact rating (high/medium/polish) and category.

**1. Visual Hierarchy & Composition** (8 items)

- Clear focal point? One primary CTA per view?

- Eye flows naturally top-left to bottom-right?

- Visual noise — competing elements fighting for attention?

- Information density appropriate for content type?

- Z-index clarity — nothing unexpectedly overlapping?

- Above-the-fold content communicates purpose in 3 seconds?

- Squint test: hierarchy still visible when blurred?

- White space is intentional, not leftover?

**2. Typography** (15 items)

- Font count <=3 (flag if more)

- Scale follows ratio (1.25 major third or 1.333 perfect fourth)

- Line-height: 1.5x body, 1.15-1.25x headings

- Measure: 45-75 chars per line (66 ideal)

- Heading hierarchy: no skipped levels (h1→h3 without h2)

- Weight contrast: >=2 weights used for hierarchy

- No blacklisted fonts (Papyrus, Comic Sans, Lobster, Impact, Jokerman)

- If primary font is Inter/Roboto/Open Sans/Poppins → flag as potentially generic

- \`text-wrap: balance\` or \`text-pretty\` on headings (check via \`$B css <heading> text-wrap\`)

- Curly quotes used, not straight quotes

- Ellipsis character (\`…\`) not three dots (\`...\`)

- \`font-variant-numeric: tabular-nums\` on number columns

- Body text >= 16px

- Caption/label >= 12px

- No letterspacing on lowercase text

**3. Color & Contrast** (10 items)

- Palette coherent (<=12 unique non-gray colors)

- WCAG AA: body text 4.5:1, large text (18px+) 3:1, UI components 3:1

- Semantic colors consistent (success=green, error=red, warning=yellow/amber)

- No color-only encoding (always add labels, icons, or patterns)

- Dark mode: surfaces use elevation, not just lightness inversion

- Dark mode: text off-white (~#E0E0E0), not pure white

- Primary accent desaturated 10-20% in dark mode

- \`color-scheme: dark\` on html element (if dark mode present)

- No red/green only combinations (8% of men have red-green deficiency)

- Neutral palette is warm or cool consistently — not mixed

**4. Spacing & Layout** (12 items)

- Grid consistent at all breakpoints

- Spacing uses a scale (4px or 8px base), not arbitrary values

- Alignment is consistent — nothing floats outside the grid

- Rhythm: related items closer together, distinct sections further apart

- Border-radius hierarchy (not uniform bubbly radius on everything)

- Inner radius = outer radius - gap (nested elements)

- No horizontal scroll on mobile

- Max content width set (no full-bleed body text)

- \`env(safe-area-inset-*)\` for notch devices

- URL reflects state (filters, tabs, pagination in query params)

- Flex/grid used for layout (not JS measurement)

- Breakpoints: mobile (375), tablet (768), desktop (1024), wide (1440)

**5. Interaction States** (10 items)

- Hover state on all interactive elements

- \`focus-visible\` ring present (never \`outline: none\` without replacement)

- Active/pressed state with depth effect or color shift

- Disabled state: reduced opacity + \`cursor: not-allowed\`

- Loading: skeleton shapes match real content layout

- Empty states: warm message + primary action + visual (not just "No items.")

- Error messages: specific + include fix/next step

- Success: confirmation animation or color, auto-dismiss

- Touch targets >= 44px on all interactive elements

- \`cursor: pointer\` on all clickable elements

**6. Responsive Design** (8 items)

- Mobile layout makes *design* sense (not just stacked desktop columns)

- Touch targets sufficient on mobile (>= 44px)

- No horizontal scroll on any viewport

- Images handle responsive (srcset, sizes, or CSS containment)

- Text readable without zooming on mobile (>= 16px body)

- Navigation collapses appropriately (hamburger, bottom nav, etc.)

- Forms usable on mobile (correct input types, no autoFocus on mobile)

- No \`user-scalable=no\` or \`maximum-scale=1\` in viewport meta

**7. Motion & Animation** (6 items)

- Easing: ease-out for entering, ease-in for exiting, ease-in-out for moving

- Duration: 50-700ms range (nothing slower unless page transition)

- Purpose: every animation communicates something (state change, attention, spatial relationship)

- \`prefers-reduced-motion\` respected (check: \`$B js "matchMedia('(prefers-reduced-motion: reduce)').matches"\`)

- No \`transition: all\` — properties listed explicitly

- Only \`transform\` and \`opacity\` animated (not layout properties like width, height, top, left)

**8. Content & Microcopy** (8 items)

- Empty states designed with warmth (message + action + illustration/icon)

- Error messages specific: what happened + why + what to do next

- Button labels specific ("Save API Key" not "Continue" or "Submit")

- No placeholder/lorem ipsum text visible in production

- Truncation handled (\`text-overflow: ellipsis\`, \`line-clamp\`, or \`break-words\`)

- Active voice ("Install the CLI" not "The CLI will be installed")

- Loading states end with \`…\` ("Saving…" not "Saving...")

- Destructive actions have confirmation modal or undo window

**9. AI Slop Detection** (10 anti-patterns — the blacklist)

The test: would a human designer at a respected studio ever ship this?

- Purple/violet/indigo gradient backgrounds or blue-to-purple color schemes

- **The 3-column feature grid:** icon-in-colored-circle + bold title + 2-line description, repeated 3x symmetrically. THE most recognizable AI layout.

- Icons in colored circles as section decoration (SaaS starter template look)

- Centered everything (\`text-align: center\` on all headings, descriptions, cards)

- Uniform bubbly border-radius on every element (same large radius on everything)

- Decorative blobs, floating circles, wavy SVG dividers (if a section feels empty, it needs better content, not decoration)

- Emoji as design elements (rockets in headings, emoji as bullet points)

- Colored left-border on cards (\`border-left: 3px solid <accent>\`)

- Generic hero copy ("Welcome to [X]", "Unlock the power of...", "Your all-in-one solution for...")

- Cookie-cutter section rhythm (hero → 3 features → testimonials → pricing → CTA, every section same height)

**10. Performance as Design** (6 items)

- LCP < 2.0s (web apps), < 1.5s (informational sites)

- CLS < 0.1 (no visible layout shifts during load)

- Skeleton quality: shapes match real content, shimmer animation

- Images: \`loading="lazy"\`, width/height dimensions set, WebP/AVIF format

- Fonts: \`font-display: swap\`, preconnect to CDN origins

- No visible font swap flash (FOUT) — critical fonts preloaded

---

## Phase 4: Interaction Flow Review

Walk 2-3 key user flows and evaluate the *feel*, not just the function:

\`\`\`bash

$B snapshot -i

$B click @e3 # perform action

$B snapshot -D # diff to see what changed

\`\`\`

Evaluate:

- **Response feel:** Does clicking feel responsive? Any delays or missing loading states?

- **Transition quality:** Are transitions intentional or generic/absent?

- **Feedback clarity:** Did the action clearly succeed or fail? Is the feedback immediate?

- **Form polish:** Focus states visible? Validation timing correct? Errors near the source?

---

## Phase 5: Cross-Page Consistency

Compare screenshots and observations across pages for:

- Navigation bar consistent across all pages?

- Footer consistent?

- Component reuse vs one-off designs (same button styled differently on different pages?)

- Tone consistency (one page playful while another is corporate?)

- Spacing rhythm carries across pages?

---

## Phase 6: Compile Report

### Output Locations