@hegemonart/get-design-done 1.42.0 → 1.43.0

package/dist/claude-code/.claude/skills/connections/connections-onboarding.md

@@ -7,27 +7,27 @@ tags: [connections, onboarding, probes, mcp, wizard, procedure, extracted]
 last_updated: 2026-05-18
 ---
 
-Source: extracted from `skills/connections/SKILL.md` (Phase 28.5 rework — D-10 extract-then-link).
-The skill's load-bearing routing + invocation-mode dispatch stays in `../skills/connections/SKILL.md`;
+Source: extracted from `skills/connections/SKILL.md` (Phase 28.5 rework - D-10 extract-then-link).
+The skill's essential routing + invocation-mode dispatch stays in `../skills/connections/SKILL.md`;
 this file holds the 33 probe scripts, bucket categorization, per-connection setup screen,
 auto-run eligibility matrix, value-prop one-liners, and STATE.md / config.json write contracts.
 
 # Connections Onboarding Procedure
 
-Detailed procedure for the `/gdd:connections` interactive wizard — companion to
+Detailed procedure for the `/gdd:connections` interactive wizard - companion to
 `../skills/connections/SKILL.md`. Read this file when executing a specific probe, deciding
 auto-run vs manual, writing config.json, or merging STATE.md `<connections>`. The SKILL.md
-keeps the load-bearing top-level flow + AskUserQuestion routing; this file holds the deep
+keeps the essential top-level flow + AskUserQuestion routing; this file holds the deep
 methodology + per-connection detail.
 
 For the cross-skill probe pattern + connection handshake (ToolSearch → live call → STATE.md
 write), see `./shared-preamble.md#connection-handshake-summary`. The canonical per-connection
-specs (setup commands, OAuth flows, capability matrix) live in `../connections/<name>.md` —
+specs (setup commands, OAuth flows, capability matrix) live in `../connections/<name>.md` -
 this file does NOT duplicate them; it points at them by name.
 
 ---
 
-## Step 1 — Probe all 33 connections
+## Step 1 - Probe all 33 connections
 
 Run every probe below in order. MCP probes call `ToolSearch` first (deferred tools fail silently without it). Write every result to `STATE.md <connections>` when done.
 
@@ -86,49 +86,49 @@ ToolSearch({ query: "mcp__magic_patterns", max_results: 5 })
 → Non-empty → magic_patterns: available
 ```
 
-**lazyweb:** (discover Tier 1 — free, tried first; D-01)
+**lazyweb:** (discover Tier 1 - free, tried first; D-01)
 ```
 ToolSearch({ query: "lazyweb", max_results: 5 })
 → Empty → lazyweb: not_configured
 → Non-empty → lazyweb: available
 ```
 
-**mobbin:** (discover Tier 2 — paid, mobile/flow-level; D-01)
+**mobbin:** (discover Tier 2 - paid, mobile/flow-level; D-01)
 ```
 ToolSearch({ query: "mobbin", max_results: 5 })
 → Empty → mobbin: not_configured
 → Non-empty → mobbin: available
 ```
 
-**slack:** (notify — Team Surfaces, env-based)
+**slack:** (notify - Team Surfaces, env-based)
 ```
 Bash: test -n "$SLACK_WEBHOOK_URL"  (and GDD_DISABLE_SLACK != 1)
 → empty / disabled → slack: not_configured
 → non-empty        → slack: available
 ```
 
-**discord:** (notify — parity, env-based)
+**discord:** (notify - parity, env-based)
 ```
 Bash: test -n "$DISCORD_WEBHOOK_URL"  (and GDD_DISABLE_DISCORD != 1)
 → empty / disabled → discord: not_configured
 → non-empty        → discord: available
 ```
 
-**linear:** (ticket-sync — MCP)
+**linear:** (ticket-sync - MCP)
 ```
 ToolSearch({ query: "linear", max_results: 5 })
 → Empty / GDD_DISABLE_LINEAR=1 → linear: not_configured
 → Non-empty                    → linear: available
 ```
 
-**jira:** (ticket-sync — Atlassian MCP)
+**jira:** (ticket-sync - Atlassian MCP)
 ```
 ToolSearch({ query: "atlassian jira", max_results: 5 })
 → Empty / GDD_DISABLE_JIRA=1   → jira: not_configured
 → Non-empty                    → jira: available
 ```
 
-**notion:** (export write-path — MCP)
+**notion:** (export write-path - MCP)
 ```
 ToolSearch({ query: "notion", max_results: 5 })
 → Empty / GDD_DISABLE_NOTION=1 → notion: not_configured
@@ -171,7 +171,7 @@ Bash: find . -name "*.pen" -not -path "*/node_modules/*" -not -path "*/.git/*" 2
   → Non-empty   → pencil_dev: available
 ```
 
-**claude-design** (file probe — handoff bundle):
+**claude-design** (file probe - handoff bundle):
 ```
 Bash: ls .design/handoff/ 2>/dev/null || find . -maxdepth 3 \
         \( -name "*.claude-design.html" -o -name "*.claude-design.zip" \
@@ -180,7 +180,7 @@ Bash: ls .design/handoff/ 2>/dev/null || find . -maxdepth 3 \
   → Non-empty → claude_design: available
 ```
 
-**lottie** (file probe — Lottie JSON motion export):
+**lottie** (file probe - Lottie JSON motion export):
 ```
 Bash: find . -name "*.json" -not -path "*/node_modules/*" 2>/dev/null | head   (confirm the Lottie signature: top-level v / fr / layers)
       grep -lE '"lottie-web"|@lottiefiles|lottie-react' package.json 2>/dev/null
@@ -188,7 +188,7 @@ Bash: find . -name "*.json" -not -path "*/node_modules/*" 2>/dev/null | head   (
   → none                                → lottie: not_configured
 ```
 
-**rive** (file probe — Rive .riv motion export):
+**rive** (file probe - Rive .riv motion export):
 ```
 Bash: find . -name "*.riv" -not -path "*/node_modules/*" 2>/dev/null | head
       grep -E '@rive-app|rive-react' package.json 2>/dev/null
@@ -196,84 +196,84 @@ Bash: find . -name "*.riv" -not -path "*/node_modules/*" 2>/dev/null | head
   → none                               → rive: not_configured
 ```
 
-**framer:** (AI-native Wave 2 — canvas; MCP or API token)
+**framer:** (AI-native Wave 2 - canvas; MCP or API token)
 ```
 ToolSearch({ query: "framer", max_results: 5 })
 → Empty → framer: not_configured
 → Non-empty → framer: available
 ```
 
-**penpot:** (AI-native Wave 2 — canvas; self-hosted URL/token or cloud)
+**penpot:** (AI-native Wave 2 - canvas; self-hosted URL/token or cloud)
 ```
 ToolSearch({ query: "penpot", max_results: 5 })
 → Empty → penpot: not_configured
 → Non-empty → penpot: available
 ```
 
-**webflow:** (AI-native Wave 2 — generator; MCP or WEBFLOW token)
+**webflow:** (AI-native Wave 2 - generator; MCP or WEBFLOW token)
 ```
 ToolSearch({ query: "webflow", max_results: 5 })
 → Empty → webflow: not_configured
 → Non-empty → webflow: available
 ```
 
-**v0-dev:** (AI-native Wave 2 — generator; MCP-first, else V0_API_KEY)
+**v0-dev:** (AI-native Wave 2 - generator; MCP-first, else V0_API_KEY)
 ```
 ToolSearch({ query: "v0", max_results: 5 })
 → Empty → v0-dev: not_configured
 → Non-empty → v0-dev: available
 ```
 
-**plasmic:** (AI-native Wave 2 — generator+canvas; MCP or token)
+**plasmic:** (AI-native Wave 2 - generator+canvas; MCP or token)
 ```
 ToolSearch({ query: "plasmic", max_results: 5 })
 → Empty → plasmic: not_configured
 → Non-empty → plasmic: available
 ```
 
-**builder-io:** (AI-native Wave 2 — generator; MCP-first, else BUILDER_API_KEY)
+**builder-io:** (AI-native Wave 2 - generator; MCP-first, else BUILDER_API_KEY)
 ```
 ToolSearch({ query: "builder", max_results: 5 })
 → Empty → builder-io: not_configured
 → Non-empty → builder-io: available
 ```
 
-**launchdarkly:** (Outcome — experiment-source; read-only A/B)
+**launchdarkly:** (Outcome - experiment-source; read-only A/B)
 ```
 ToolSearch({ query: "launchdarkly", max_results: 5 })  (else check the platform API-key env)
 → Empty / GDD_DISABLE_LAUNCHDARKLY=1 → launchdarkly: not_configured
 → Non-empty / key set                       → launchdarkly: available
 ```
 
-**statsig:** (Outcome — experiment-source; read-only)
+**statsig:** (Outcome - experiment-source; read-only)
 ```
 ToolSearch({ query: "statsig", max_results: 5 })  (else check the platform API-key env)
 → Empty / GDD_DISABLE_STATSIG=1 → statsig: not_configured
 → Non-empty / key set                       → statsig: available
 ```
 
-**growthbook:** (Outcome — experiment-source; self-host/cloud)
+**growthbook:** (Outcome - experiment-source; self-host/cloud)
 ```
 ToolSearch({ query: "growthbook", max_results: 5 })  (else check the platform API-key env)
 → Empty / GDD_DISABLE_GROWTHBOOK=1 → growthbook: not_configured
 → Non-empty / key set                       → growthbook: available
 ```
 
-**usertesting:** (Outcome — user-research; pseudonymize-first)
+**usertesting:** (Outcome - user-research; pseudonymize-first)
 ```
 ToolSearch({ query: "usertesting", max_results: 5 })  (else check the platform API-key env)
 → Empty / GDD_DISABLE_USERTESTING=1 → usertesting: not_configured
 → Non-empty / key set                       → usertesting: available
 ```
 
-**maze:** (Outcome — user-research; pseudonymize-first)
+**maze:** (Outcome - user-research; pseudonymize-first)
 ```
 ToolSearch({ query: "maze", max_results: 5 })  (else check the platform API-key env)
 → Empty / GDD_DISABLE_MAZE=1 → maze: not_configured
 → Non-empty / key set                       → maze: available
 ```
 
-**hotjar:** (Outcome — user-research; indexed insights only)
+**hotjar:** (Outcome - user-research; indexed insights only)
 ```
 ToolSearch({ query: "hotjar", max_results: 5 })  (else check the platform API-key env)
 → Empty / GDD_DISABLE_HOTJAR=1 → hotjar: not_configured
@@ -284,7 +284,7 @@ After all 33 probes complete, merge results into `STATE.md <connections>`. Prese
 
 ---
 
-## Step 2 — Bucket categorization
+## Step 2 - Bucket categorization
 
 ### Project-hint detection
 
@@ -306,7 +306,7 @@ HAS_FIGMA_HINT=$( grep -r "figma\.com/file" -l . --include="*.md" 2>/dev/null |
 | **recommended** | probe returned `not_configured` AND matches a project hint below |
 | **optional** | probe returned `not_configured` AND no project hint match |
 | **skipped** | name appears in `config.json connections.skip[]` |
-| **unavailable** | probe returned `unavailable` (configured but broken — needs attention) |
+| **unavailable** | probe returned `unavailable` (configured but broken - needs attention) |
 
 ### Recommendation mapping
 
@@ -316,11 +316,11 @@ HAS_FIGMA_HINT=$( grep -r "figma\.com/file" -l . --include="*.md" 2>/dev/null |
 | `HAS_STORYBOOK_DIR` or storybook available | storybook, chromatic |
 | `HAS_PEN_FILES` | pencil-dev |
 | `HAS_REACT` | 21st-dev, magic-patterns |
-| Always | refero, preview, lazyweb (free — cost-aware default, D-01) |
+| Always | refero, preview, lazyweb (free - cost-aware default, D-01) |
 
 ---
 
-## Step 3 — Summary table
+## Step 3 - Summary table
 
 ```
 ┌── Connections ──────────────────────────
@@ -361,31 +361,31 @@ One-line value props (use verbatim):
 | pencil-dev | `.pen` spec files as canonical design source |
 | 21st-dev | AI component generator (marketplace search) |
 | magic-patterns | AI component generator (DS-aware) |
-| lazyweb | free design reference search (pricing/onboarding/redesign) — discover Tier 1 |
-| mobbin | curated mobile + flow-level references (paid) — discover Tier 2 |
-| slack | notify — route verify-fail/audit-pass/ship to a Slack channel (redacted) |
-| discord | notify — route pipeline events to a Discord channel (redacted) |
-| linear | ticket-sync — link a cycle to a Linear issue; read comments + transition on completion |
-| jira | ticket-sync — parity with Linear via the Atlassian MCP |
-| notion | export — `/gdd:export --format notion` writes a stakeholder page (degrade-to-HTML) |
-| lottie | verify — Lottie JSON motion check (frame-rate / duration / bloat / perf-budget), WARN-never-block |
-| rive | verify — Rive `.riv` motion check (size + state-machine reachability via the opt-in runtime), WARN-never-block |
-| framer | design — read Framer frames + write proposals (canvas, Wave 2) |
-| penpot | design — open-source Figma alt; read boards (self-hosted or cloud) |
-| webflow | design — read site structure as an adaptation source (Wave 2) |
-| v0-dev | generator — Vercel v0 prompt→component (MCP-first → REST + V0_API_KEY) |
-| plasmic | generator + canvas — emit code + read the Plasmic canvas |
-| builder-io | generator — Builder.io Visual Copilot (pull-only this phase) |
-| launchdarkly | outcome — read A/B results → design_arms posterior (experiment-source) |
-| statsig | outcome — read experiment/pulse results → design_arms (experiment-source) |
-| growthbook | outcome — read experiment results → design_arms (experiment-source; OSS) |
-| usertesting | outcome — read test reports → brief findings (user-research; pseudonymized) |
-| maze | outcome — read usability metrics → brief findings (user-research; pseudonymized) |
-| hotjar | outcome — read indexed insights → brief findings (user-research; pseudonymized) |
+| lazyweb | free design reference search (pricing/onboarding/redesign) - discover Tier 1 |
+| mobbin | curated mobile + flow-level references (paid) - discover Tier 2 |
+| slack | notify - route verify-fail/audit-pass/ship to a Slack channel (redacted) |
+| discord | notify - route pipeline events to a Discord channel (redacted) |
+| linear | ticket-sync - link a cycle to a Linear issue; read comments + transition on completion |
+| jira | ticket-sync - parity with Linear via the Atlassian MCP |
+| notion | export - `/gdd:export --format notion` writes a stakeholder page (degrade-to-HTML) |
+| lottie | verify - Lottie JSON motion check (frame-rate / duration / bloat / perf-budget), WARN-never-block |
+| rive | verify - Rive `.riv` motion check (size + state-machine reachability via the opt-in runtime), WARN-never-block |
+| framer | design - read Framer frames + write proposals (canvas, Wave 2) |
+| penpot | design - open-source Figma alt; read boards (self-hosted or cloud) |
+| webflow | design - read site structure as an adaptation source (Wave 2) |
+| v0-dev | generator - Vercel v0 prompt→component (MCP-first → REST + V0_API_KEY) |
+| plasmic | generator + canvas - emit code + read the Plasmic canvas |
+| builder-io | generator - Builder.io Visual Copilot (pull-only this phase) |
+| launchdarkly | outcome - read A/B results → design_arms posterior (experiment-source) |
+| statsig | outcome - read experiment/pulse results → design_arms (experiment-source) |
+| growthbook | outcome - read experiment results → design_arms (experiment-source; OSS) |
+| usertesting | outcome - read test reports → brief findings (user-research; pseudonymized) |
+| maze | outcome - read usability metrics → brief findings (user-research; pseudonymized) |
+| hotjar | outcome - read indexed insights → brief findings (user-research; pseudonymized) |
 
 ---
 
-## Step 4 — Route by mode
+## Step 4 - Route by mode
 
 ### Mode: `list` or `--auto`
 
@@ -413,7 +413,7 @@ If recommended bucket is empty, swap that option for "Show all 33 and pick."
 
 ---
 
-## Step 5 — Per-connection setup screen
+## Step 5 - Per-connection setup screen
 
 ### 5.1 Read the spec
 
@@ -455,26 +455,26 @@ options:
 | Connection | Install kind | Auto-run? | Rationale |
 |---|---|---|---|
 | figma | `claude mcp add` (remote MCP) | ✓ yes | Reversible via `claude mcp remove` |
-| preview | built-in, no install | — | Already present or not — no command to run |
+| preview | built-in, no install | - | Already present or not - no command to run |
 | paper-design | `claude mcp add` | ✓ yes | Reversible |
 | magic-patterns | `claude mcp add` | ✓ yes | Reversible |
 | pinterest | `npx -y @smithery/cli install` | ✓ yes | Smithery CLI manages entry |
-| refero | vendor-specific install | ✗ no | Vendor doesn't document a stable CLI — print link only |
-| storybook | `npx storybook init` | ✗ no | Mutates repo files — force manual |
-| chromatic | `npm install --save-dev chromatic` + env var | ✗ no | Writes package.json + needs `CHROMATIC_PROJECT_TOKEN` — force manual |
-| graphify | `pip install` + `gsd-tools config-set` | ✗ no | Python install + cross-tool config — force manual |
-| 21st-dev | `npx @21st-dev/magic init` + env var | ✗ no | Env var required — force manual |
-| pencil-dev | VS Code extension | ✗ no | IDE-level install — force manual |
-| claude-design | handoff bundle drop | ✗ no | User-driven file drop — force manual |
+| refero | vendor-specific install | ✗ no | Vendor doesn't document a stable CLI - print link only |
+| storybook | `npx storybook init` | ✗ no | Mutates repo files - force manual |
+| chromatic | `npm install --save-dev chromatic` + env var | ✗ no | Writes package.json + needs `CHROMATIC_PROJECT_TOKEN` - force manual |
+| graphify | `pip install` + `gsd-tools config-set` | ✗ no | Python install + cross-tool config - force manual |
+| 21st-dev | `npx @21st-dev/magic init` + env var | ✗ no | Env var required - force manual |
+| pencil-dev | VS Code extension | ✗ no | IDE-level install - force manual |
+| claude-design | handoff bundle drop | ✗ no | User-driven file drop - force manual |
 | mobbin | `claude mcp add mobbin --transport http https://api.mobbin.com/mcp` | ✓ yes | Reversible MCP add; no credential filesystem-write (OAuth on first call) |
-| lazyweb | `claude plugin install lazyweb@lazyweb` (after token write to `~/.lazyweb/`) | ✗ no | Writes a bearer token to disk — force manual (user-consent step) |
-| slack | set `SLACK_WEBHOOK_URL` env (Slack Incoming Webhook URL) | ✗ no | Env credential — user sets it; no install command (degrade-to-noop when unset) |
-| discord | set `DISCORD_WEBHOOK_URL` env (Discord channel Webhook URL) | ✗ no | Env credential — user sets it; no install command (degrade-to-noop when unset) |
+| lazyweb | `claude plugin install lazyweb@lazyweb` (after token write to `~/.lazyweb/`) | ✗ no | Writes a bearer token to disk - force manual (user-consent step) |
+| slack | set `SLACK_WEBHOOK_URL` env (Slack Incoming Webhook URL) | ✗ no | Env credential - user sets it; no install command (degrade-to-noop when unset) |
+| discord | set `DISCORD_WEBHOOK_URL` env (Discord channel Webhook URL) | ✗ no | Env credential - user sets it; no install command (degrade-to-noop when unset) |
 | linear | `claude mcp add linear ...` (Linear MCP) | ✓ yes | Reversible MCP add; OAuth on first call, no credential filesystem-write |
 | jira | `claude mcp add atlassian ...` (Atlassian MCP) | ✓ yes | Reversible MCP add; OAuth on first call |
 | notion | `claude mcp add notion ...` (Notion MCP) | ✓ yes | Reversible MCP add; OAuth on first call |
-| lottie | (file-based — no install; drop a Lottie `.json` export in the repo) | n/a | Detected from Lottie exports / a `lottie-web` dep; live player opt-in |
-| rive | (file-based — no install; add a `.riv` export / `@rive-app` dep) | n/a | Detected from `.riv` files / a `@rive-app` dep; Rive runtime opt-in |
+| lottie | (file-based - no install; drop a Lottie `.json` export in the repo) | n/a | Detected from Lottie exports / a `lottie-web` dep; live player opt-in |
+| rive | (file-based - no install; add a `.riv` export / `@rive-app` dep) | n/a | Detected from `.riv` files / a `@rive-app` dep; Rive runtime opt-in |
 | framer | `claude mcp add framer ...` (or API token) | ✓ yes | Reversible MCP add; canvas-category |
 | penpot | `claude mcp add penpot ...` (self-hosted URL or cloud + token) | ✓ yes | Reversible; self-host vs cloud |
 | webflow | `claude mcp add webflow ...` (or WEBFLOW token) | ✓ yes | Reversible; reads structure, not CMS authoring |
@@ -490,21 +490,21 @@ options:
 
 For non-auto-run connections, hide the "Run install command now" option entirely in 5.3.
 
-### 5.4a — Auto-run path
+### 5.4a - Auto-run path
 
 Bash the install command. On success: print stdout, print `"Installed. Session restart required before <name> is usable."`, append `<name>` to `.design/config.json > connections_onboarding.pending_verification[]`.
 
 On failure: print stderr, print `"Install failed. Copy the command and run it manually, then rerun /gdd:connections <name> to verify."` Do not record pending_verification.
 
-### 5.4b — Manual path
+### 5.4b - Manual path
 
 Print the install command inside a fenced code block for easy copy. Print: `"After installing, restart the session and run /gdd:connections <name> to verify."` Append `<name>` to `connections_onboarding.pending_verification[]`.
 
-### 5.4c — Skip for now
+### 5.4c - Skip for now
 
 No config change. Continue loop.
 
-### 5.4d — Never ask again
+### 5.4d - Never ask again
 
 Read `.design/config.json`. Ensure `connections.skip` is an array. Append `<name>` if not present. Write back.
 
@@ -514,7 +514,7 @@ If mode is `<connection-name>` (single-target invocation), skip straight to Step
 
 ---
 
-## Step 6 — Verification pass
+## Step 6 - Verification pass
 
 Re-probe every connection whose name appears in `connections_onboarding.pending_verification[]`. For each:
 
@@ -546,7 +546,7 @@ If `.design/config.json > connections_onboarding.pending_verification[]` is non-
 
 1. Print: `"Resuming — <N> connections pending verification: <list>"`
 2. Run Step 6 (verification pass) immediately.
-3. If resumption completes cleanly (empty pending list), emit `## CONNECTIONS COMPLETE` and exit — do not re-enter the wizard.
+3. If resumption completes cleanly (empty pending list), emit `## CONNECTIONS COMPLETE` and exit - do not re-enter the wizard.
 4. Otherwise, fall through to Step 3 (summary) with the still-pending connections visible as `unavailable`.
 
 ---
@@ -582,7 +582,7 @@ Deleted automatically when empty after a verification pass:
 
 ### `STATE.md <connections>` write
 
-Always merge, never replace — other stages may have written entries this skill did not probe.
+Always merge, never replace - other stages may have written entries this skill did not probe.
 
 Key normalization:
 - `21st-dev` → `twenty_first` in STATE.md (no leading digit in XML-ish key).
@@ -605,4 +605,4 @@ Key normalization:
 
 ---
 
-*Imported by: `../skills/connections/SKILL.md`. Maintained as part of Phase 28.5 (Bucket 2 rework — D-10).*
+*Imported by: `../skills/connections/SKILL.md`. Maintained as part of Phase 28.5 (Bucket 2 rework - D-10).*

package/dist/claude-code/.claude/skills/continue/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: gdd-continue
-description: "Alias for /gdd:resume — restore session context from the most recent checkpoint."
+description: "Alias for /gdd:resume - restore session context from the most recent checkpoint."
 argument-hint: "[<checkpoint-N>]"
 tools: Read, Write, Bash, Glob
 disable-model-invocation: true
@@ -12,7 +12,7 @@ disable-model-invocation: true
 
 Alias for `/gdd:resume`. Delegates immediately to the resume skill with the same argument.
 
-This alias exists for discoverability — users familiar with `git continue` or similar conventions find `/gdd:continue` more intuitive than `/gdd:resume` after a pause.
+This alias exists for discoverability - users familiar with `git continue` or similar conventions find `/gdd:continue` more intuitive than `/gdd:resume` after a pause.
 
 ## Steps
 

package/dist/claude-code/.claude/skills/darkmode/SKILL.md

@@ -1,11 +1,11 @@
 ---
 name: gdd-darkmode
-description: "Audit a project's dark mode implementation — detects architecture (CSS custom props, Tailwind `dark:` prefix, or JS class toggle), runs architecture-specific contrast / token-override / anti-pattern / meta-property checks, and writes a prioritized fix list to `.design/DARKMODE-AUDIT.md`. Use when the user wants to verify dark mode quality without re-running the full design pipeline. Read-only — no score writeback to `DESIGN.md`."
+description: "Audit a project's dark mode implementation - detects architecture (CSS custom props, Tailwind `dark:` prefix, or JS class toggle), runs architecture-specific contrast / token-override / anti-pattern / meta-property checks, and writes a prioritized fix list to `.design/DARKMODE-AUDIT.md`. Use when the user wants to verify dark mode quality without re-running the full design pipeline. Read-only - no score writeback to `DESIGN.md`."
 argument-hint: ""
 user-invocable: true
 ---
 
-# gdd-darkmode — Dark Mode Audit
+# gdd-darkmode - Dark Mode Audit
 
 Standalone dark mode audit. Detects the project's dark mode architecture, runs architecture-specific checks across contrast, token completeness, anti-patterns, and meta properties, then writes a prioritized fix list to `.design/DARKMODE-AUDIT.md`.
 
@@ -15,13 +15,13 @@ For the full step-by-step methodology (architecture-detection greps, WCAG contra
 
 ## Scope
 
-This command is a **standalone audit** — not a pipeline stage:
+This command is a **standalone audit** - not a pipeline stage:
 
-- Does NOT update `DESIGN.md` scores (V2-05 deferred — two-sources-of-truth risk).
-- Does NOT invoke `design-auditor` (Pitfall 4 — darkmode runs its own inline audit, separate from the `DESIGN-AUDIT.md` pipeline).
+- Does NOT update `DESIGN.md` scores (V2-05 deferred - two-sources-of-truth risk).
+- Does NOT invoke `design-auditor` (Pitfall 4 - darkmode runs its own inline audit, separate from the `DESIGN-AUDIT.md` pipeline).
 - Does NOT write to `.design/STATE.md`, `DESIGN-CONTEXT.md`, `DESIGN-PLAN.md`, `DESIGN-SUMMARY.md`, or `DESIGN-VERIFICATION.md`.
 - Writes exactly ONE artifact: `.design/DARKMODE-AUDIT.md`.
-- Does NOT execute fixes — audit-only per V2-07 deferral (fixes belong in the design pipeline's color task).
+- Does NOT execute fixes - audit-only per V2-07 deferral (fixes belong in the design pipeline's color task).
 
 Output artifact prefix `DARKMODE-AUDIT` is distinct from the pipeline namespace (`DESIGN-*.md`). No naming conflict.
 
@@ -39,13 +39,13 @@ Probe `preview` connection per `../../reference/shared-preamble.md#connection-ha
 
 ## Workflow
 
-1. **Architecture Detection (DARK-02)** — run three greps (CSS custom props / Tailwind `dark:` / JS class toggle), classify primary architecture or `Hybrid` or `None`. If `None`, abort. Detail: `./darkmode-audit-procedure.md#step-1-architecture-detection-dark-02`.
-2. **Contrast Audit (DARK-03)** — extract dark-context token pairs for the detected architecture, compute WCAG 2.1 ratios, flag failures at 4.5:1 (body) / 3:1 (large text + UI boundaries). Cross-check with APCA from `../../reference/contrast-advanced.md` for thin / large / colored text. Detail: `./darkmode-audit-procedure.md#step-2-contrast-audit-dark-03`.
-3. **Token Override Completeness (DARK-04)** — every light-mode color token must have a dark-mode override. Flag missing overrides → P1. Detail: `./darkmode-audit-procedure.md#step-3-token-override-completeness-dark-04`.
-4. **Dark-Specific Anti-Patterns (DARK-05)** — Images/SVGs without dark variant (P2), pure-black backgrounds in dark context = BAN-05 (P1), missing `@media (forced-colors)` (P2). Detail: `./darkmode-audit-procedure.md#step-4-dark-specific-anti-patterns-dark-05`.
-5. **Meta Property Check (DARK-06)** — `color-scheme` property + `prefers-color-scheme` query. Each absent → P2. Detail: `./darkmode-audit-procedure.md#step-5-meta-property-check-dark-06`.
-6. **Visual Rendering (preview: available only)** — capture light/dark screenshot pair to `.design/screenshots/darkmode/{light,dark}.png`. Detail: `./darkmode-audit-procedure.md#step-5b-dark-mode-rendering-screenshots-when-preview-available`.
-7. **Write `.design/DARKMODE-AUDIT.md`** — group flagged issues by priority (P0 → P1 → P2 → P3). Full template at `./darkmode-audit-procedure.md#step-6-darkmode-auditmd-template`.
+1. **Architecture Detection (DARK-02)** - run three greps (CSS custom props / Tailwind `dark:` / JS class toggle), classify primary architecture or `Hybrid` or `None`. If `None`, abort. Detail: `./darkmode-audit-procedure.md#step-1-architecture-detection-dark-02`.
+2. **Contrast Audit (DARK-03)** - extract dark-context token pairs for the detected architecture, compute WCAG 2.1 ratios, flag failures at 4.5:1 (body) / 3:1 (large text + UI boundaries). Cross-check with APCA from `../../reference/contrast-advanced.md` for thin / large / colored text. Detail: `./darkmode-audit-procedure.md#step-2-contrast-audit-dark-03`.
+3. **Token Override Completeness (DARK-04)** - every light-mode color token must have a dark-mode override. Flag missing overrides → P1. Detail: `./darkmode-audit-procedure.md#step-3-token-override-completeness-dark-04`.
+4. **Dark-Specific Anti-Patterns (DARK-05)** - Images/SVGs without dark variant (P2), pure-black backgrounds in dark context = BAN-05 (P1), missing `@media (forced-colors)` (P2). Detail: `./darkmode-audit-procedure.md#step-4-dark-specific-anti-patterns-dark-05`.
+5. **Meta Property Check (DARK-06)** - `color-scheme` property + `prefers-color-scheme` query. Each absent → P2. Detail: `./darkmode-audit-procedure.md#step-5-meta-property-check-dark-06`.
+6. **Visual Rendering (preview: available only)** - capture light/dark screenshot pair to `.design/screenshots/darkmode/{light,dark}.png`. Detail: `./darkmode-audit-procedure.md#step-5b-dark-mode-rendering-screenshots-when-preview-available`.
+7. **Write `.design/DARKMODE-AUDIT.md`** - group flagged issues by priority (P0 → P1 → P2 → P3). Full template at `./darkmode-audit-procedure.md#step-6-darkmode-auditmd-template`.
 
 ---
 
@@ -54,9 +54,9 @@ Probe `preview` connection per `../../reference/shared-preamble.md#connection-ha
 This command MUST NOT (per `../../reference/shared-preamble.md#output-contract-reminders`):
 
 - Write to `DESIGN.md`, `DESIGN-SUMMARY.md`, `DESIGN-VERIFICATION.md`, `DESIGN-CONTEXT.md`, or `.design/STATE.md`.
-- Invoke `design-auditor` (Pitfall 4 — this is a separate audit with its own inline checks).
-- Execute any fixes — audit-only (V2-07 deferred).
-- Write scores back to `DESIGN.md` (V2-05 deferred — two-sources-of-truth risk).
+- Invoke `design-auditor` (Pitfall 4 - this is a separate audit with its own inline checks).
+- Execute any fixes - audit-only (V2-07 deferred).
+- Write scores back to `DESIGN.md` (V2-05 deferred - two-sources-of-truth risk).
 - Add rows to `DESIGN.md` or append to pipeline-owned artifacts.
 
 MUST write exactly one output file: `.design/DARKMODE-AUDIT.md`.
@@ -71,6 +71,6 @@ After writing the audit, print:
 Dark mode audit complete. Architecture: <X>. Fixes: P0=<N>, P1=<M>, P2=<K>, P3=<J>. See .design/DARKMODE-AUDIT.md.
 ```
 
-Do not summarize individual issues in the completion message — the file contains the full detail.
+Do not summarize individual issues in the completion message - the file contains the full detail.
 
 ## DARKMODE AUDIT COMPLETE

package/dist/claude-code/.claude/skills/darkmode/darkmode-audit-procedure.md

@@ -7,17 +7,17 @@ tags: [darkmode, dark-mode, contrast, audit, procedure, extracted]
 last_updated: 2026-05-18
 ---
 
-Source: extracted from `skills/darkmode/SKILL.md` (Phase 28.5 rework — D-10 extract-then-link).
-The skill's load-bearing routing + decision tree stays in `../skills/darkmode/SKILL.md`; this
+Source: extracted from `skills/darkmode/SKILL.md` (Phase 28.5 rework - D-10 extract-then-link).
+The skill's essential routing + decision tree stays in `../skills/darkmode/SKILL.md`; this
 file holds the architecture-detection greps, contrast computation, anti-pattern grep
 snippets, and the `DARKMODE-AUDIT.md` report template.
 
 # Dark Mode Audit Procedure
 
-Detailed procedure for the `gdd-darkmode` standalone audit — companion to
+Detailed procedure for the `gdd-darkmode` standalone audit - companion to
 `../skills/darkmode/SKILL.md`. Read this file when executing a specific audit step
 (architecture detection, contrast computation, anti-pattern grep, report layout). The
-SKILL.md keeps the load-bearing pre-flight + step routing; this file holds the deep
+SKILL.md keeps the essential pre-flight + step routing; this file holds the deep
 methodology.
 
 For the perceptual layer (APCA / WCAG 3 draft) sitting on top of the WCAG 2.1 ratios used
@@ -50,7 +50,7 @@ arch3_count=$(grep -rEn "classList.*dark|setAttribute.*dark|document\.documentEl
 
 | Condition | Classification |
 |-----------|---------------|
-| All three counts < 3 | No dark mode — abort: "No dark mode implementation detected — nothing to audit." |
+| All three counts < 3 | No dark mode - abort: "No dark mode implementation detected - nothing to audit." |
 | Exactly one count ≥ 3 | Primary architecture = that one |
 | Two or more counts ≥ 5 | Hybrid (list all detected architectures) |
 | One count ≥ 3, others < 5 | Primary = highest count |
@@ -87,7 +87,7 @@ grep -rEn "\.dark[[:space:]]*\{" "$SRC_ROOT" \
 
 **WCAG contrast computation:**
 
-Use the linearized-sRGB formula from `agents/design-executor.md` Type: accessibility (pre-calibrated — do not re-derive):
+Use the linearized-sRGB formula from `agents/design-executor.md` Type: accessibility (pre-calibrated - do not re-derive):
 
 1. Convert each hex channel to linear light: `c_lin = (c/255 ≤ 0.04045) ? c/255/12.92 : ((c/255 + 0.055)/1.055)^2.4`
 2. Relative luminance: `L = 0.2126 * R_lin + 0.7152 * G_lin + 0.0722 * B_lin`
@@ -255,4 +255,4 @@ If a priority bucket has no issues, omit that section or write "None."
 
 ---
 
-*Imported by: `../skills/darkmode/SKILL.md`. Maintained as part of Phase 28.5 (Bucket 2 rework — D-10).*
+*Imported by: `../skills/darkmode/SKILL.md`. Maintained as part of Phase 28.5 (Bucket 2 rework - D-10).*

package/dist/claude-code/.claude/skills/debug/SKILL.md

@@ -12,12 +12,12 @@ Systematic, checkpoint-driven design debugger. Loads framing from `./../referenc
 ## Steps
 
 1. **Load philosophy + feedback-loop catalog**: Read `reference/debugger-philosophy.md` (five principles) and `./debug-feedback-loops.md` (10 construction paths; iterate-on-loop discipline). Keep both in mind for the entire session.
-2. **Symptom**: If no symptom argument was passed, ask (AskUserQuestion): "What design symptom are you investigating? (observable only — 'cards look crowded', not 'padding is wrong')"
+2. **Symptom**: If no symptom argument was passed, ask (AskUserQuestion): "What design symptom are you investigating? (observable only - 'cards look crowded', not 'padding is wrong')"
 3. **Resume check**: Read `.design/DEBUG.md` if it exists. If there is an open session with no `### Fix Proposal` block, ask: "Resume existing session '<symptom>' or start a new one?"
 4. **Ground truth load**: Read `.design/DESIGN-PLAN.md` (goals), `.design/STATE.md` `<decisions>` block (D-XX items), and any source files pointed at by the symptom.
-5. **Phase 1 — Build a feedback loop**: Before ANY hypothesizing, build a deterministic, fast, agent-runnable pass/fail signal that reproduces the symptom. See `./debug-feedback-loops.md` for the 10 construction paths in priority order (failing test > curl > CLI fixture > headless browser > trace replay > throwaway harness > fuzz > bisect > differential > HITL bash). Iterate on the loop itself (cache setup, narrow scope, pin time, seed RNG, isolate filesystem, freeze network) before iterating on the bug. For non-deterministic bugs: raise reproduction rate to at least 30%, not clean repro. **Do not proceed to Phase 2 (hypothesis generation) until you have a loop you believe in.**
+5. **Phase 1 - Build a feedback loop**: Before ANY hypothesizing, build a deterministic, fast, agent-runnable pass/fail signal that reproduces the symptom. See `./debug-feedback-loops.md` for the 10 construction paths in priority order (failing test > curl > CLI fixture > headless browser > trace replay > throwaway harness > fuzz > bisect > differential > HITL bash). Iterate on the loop itself (cache setup, narrow scope, pin time, seed RNG, isolate filesystem, freeze network) before iterating on the bug. For non-deterministic bugs: raise reproduction rate to at least 30%, not clean repro. **Do not proceed to Phase 2 (hypothesis generation) until you have a loop you believe in.**
 6. **Optional rendered-output check**: Use ToolSearch to see if Playwright/Preview MCP tools are available. If yes, capture rendered state. If no, fall back to code-only analysis.
-7. **Phase 2 — Investigation loop** (one hypothesis at a time) — for each step:
+7. **Phase 2 - Investigation loop** (one hypothesis at a time) - for each step:
    - Form one hypothesis (one variable).
    - Investigate (read files, grep, measure). Re-run the Phase 1 feedback loop to confirm the hypothesis pinpoints the symptom.
    - Append to `.design/DEBUG.md`: