@hegemonart/get-design-done 1.41.5 → 1.43.0

package/dist/claude-code/.claude/skills/watch-authorities/SKILL.md

@@ -0,0 +1,82 @@
+---
+name: gdd-watch-authorities
+description: "Fetches the design-authority feed whitelist, diffs against .design/authority-snapshot.json, and writes .design/authority-report.md (consumed by /gdd:reflect). Authority monitoring only - no trend-watching."
+argument-hint: "[--refresh] [--since <date>] [--feed <name>] [--schedule <weekly|daily|monthly>]"
+tools: Read, Write, Task, Bash
+---
+
+# /gdd:watch-authorities
+
+Runs `design-authority-watcher` on demand. Fetches the curated design-authority feed whitelist, diffs against the prior snapshot, classifies new entries into five buckets, and writes `.design/authority-report.md`. Phase 11's reflector picks up the report automatically when you next run `/gdd:reflect`.
+
+Authority-monitoring only. Not trend-watching. See `reference/authority-feeds.md` §"Rejected kinds" for what this skill will never fetch.
+
+## Steps
+
+1. **Parse args.** Extract optional flags: `--refresh`, `--since <date>`, `--feed <name>`, `--schedule <cadence>`. Anything that doesn't match one of these is an error - print `Unknown flag: <arg>. Valid flags: --refresh --since <date> --feed <name> --schedule <weekly|daily|monthly>.` and STOP.
+
+   Mutual exclusion rules:
+   - `--schedule` is handled entirely by this skill - it does not combine with the other three. If `--schedule` is present alongside any of `--refresh | --since | --feed`, print `--schedule cannot combine with other flags. Schedule registration runs this skill with no flags at the configured cadence.` and STOP.
+   - `--refresh` and `--since` are mutually exclusive - print `--refresh and --since are mutually exclusive. --refresh re-seeds the snapshot silently; --since surfaces a backlog from a boundary date. Pick one.` and STOP.
+
+2. **Handle `--schedule <cadence>` branch** (early-return).
+
+   If `--schedule` is set:
+   - Validate cadence ∈ {`weekly`, `daily`, `monthly`}; else print `Unknown cadence: <value>. Use one of: weekly, daily, monthly.` and STOP.
+   - Probe for the scheduled-tasks MCP via ToolSearch:
+
+     ```
+     ToolSearch({ query: "scheduled-tasks", max_results: 3 })
+     ```
+
+   - If the probe returns an empty result set: print `scheduled-tasks MCP not connected. Install it with: claude mcp add scheduled-tasks ... then retry with --schedule.` - this is a documented fallback (not an error). Terminate with `## WATCH COMPLETE` and exit 0.
+   - If the probe returns one or more `scheduled-tasks` tools: register the cron. Discover the MCP's registration tool name at runtime from the ToolSearch result and follow its schema. Target command: `/gdd:watch-authorities` with NO flags (the cron invokes the default diff-and-report behavior). Cadence → cron expression mapping:
+     - `weekly`  → `0 9 * * 1` (Mondays 09:00 local)
+     - `daily`   → `0 9 * * *` (every day 09:00 local)
+     - `monthly` → `0 9 1 * *` (1st of each month 09:00 local)
+   - After registration: print `Scheduled /gdd:watch-authorities to run <cadence>.` and terminate with `## WATCH COMPLETE`.
+
+3. **Validate `--since <date>`** (if present).
+
+   Accept ISO8601 (`YYYY-MM-DD` or `YYYY-MM-DDTHH:MM:SSZ`). Sanity-check via Bash `date -d "<value>" +%s` (GNU) or the POSIX equivalent `python3 -c "from datetime import datetime; datetime.fromisoformat('<value>'.replace('Z','+00:00'))"`. On parse failure: print `Invalid --since value: <value>. Use ISO8601 (YYYY-MM-DD or YYYY-MM-DDTHH:MM:SSZ).` and STOP.
+
+   If the parsed date is earlier than `2020-01-01`, ask: `Very old --since value: <value>. Did you mean something more recent? Proceed? [y/N]`. On anything other than `y`/`Y`, STOP.
+
+4. **Spawn the watcher.**
+
+   Build the `Task(subagent_type="design-authority-watcher", ...)` prompt. The prompt supplies the agent's required-reading block (watcher step 0), echoes the invocation flags verbatim (watcher Flags section), and instructs the agent to follow its own fetch/diff/classify/write loop:
+
+   ```
+   Task("design-authority-watcher", """
+   <required_reading>
+   @reference/authority-feeds.md
+   @.design/authority-snapshot.json
+   @.design/STATE.md
+   </required_reading>
+
+   Invocation flags: <joined flag list or "none">
+
+   Fetch the feeds listed in reference/authority-feeds.md, diff against .design/authority-snapshot.json,
+   classify new entries per the D-17 decision table, write .design/authority-snapshot.json and
+   .design/authority-report.md.
+
+   Terminate with ## WATCH COMPLETE.
+   """)
+   ```
+
+   `<joined flag list>` is the subset of `--refresh | --since <date> | --feed <name>` actually passed - e.g., `--refresh`, `--since 2026-03-01`, `--feed wai-aria-apg`, `--refresh --feed radix-ui-releases`, or literally `none` when no flags were supplied.
+
+5. **Print summary.**
+
+   After the agent returns:
+   - If STATE.md gained a `<blocker type="contract-violation">` on this run (snapshot version mismatch, hash-format violation, or over-200 entries per feed), surface the blocker verbatim and stop - do not print the default "review and reflect" line.
+   - Otherwise print the agent's one-line stdout summary (normal mode: `Surfaced N entries across M feeds. K skipped. See .design/authority-report.md.`; first-run / refresh mode: `Seeded snapshot for N feeds — next run will surface new entries.`) followed by: `Review and reflect: /gdd:reflect`.
+
+6. **Terminate with `## WATCH COMPLETE`.**
+
+## Do Not
+
+- Do not modify `agents/design-authority-watcher.md`.
+- Do not modify `agents/design-reflector.md` - Phase 13.2 does not touch the reflector agent (CONTEXT.md D-25).
+- Do not write to `.design/authority-snapshot.json` or `.design/authority-report.md` directly - those are the agent's writes.
+- Do not fetch URLs outside `reference/authority-feeds.md`. The whitelist is the allow-list.

package/dist/claude-code/.claude/skills/zoom-out/SKILL.md

@@ -0,0 +1,26 @@
+---
+name: zoom-out
+description: "Asks the agent to go up a layer of abstraction and map the relevant modules and callers using the project's CONTEXT.md vocabulary. Use when the user is working in an unfamiliar area of code and needs orientation before deep work."
+disable-model-invocation: true
+argument-hint: "[scope]"
+---
+
+Source: mattpocock/skills (MIT) - adapted with permission. See `../NOTICE` for the full attribution block.
+
+# Zoom Out
+
+**Role:** Give the user a map, not a fix.
+
+I don't know this area of code well. Go up a layer of abstraction. Give me a map of all the relevant modules and callers, using the project's domain glossary (`CONTEXT.md`) vocabulary.
+
+When invoked, produce a one-screen map that names:
+
+1. **Modules in scope** - one-line description of each, using terms from `CONTEXT.md` (see `./../reference/context-md-format.md` for the schema). Do not invent terms.
+2. **Callers** - who calls these modules from elsewhere, with file paths.
+3. **Seams** - where data crosses module boundaries, named per `./../reference/architecture-vocabulary.md`.
+
+Do not propose fixes. Do not write code. The output is a map.
+
+If `CONTEXT.md` is absent, suggest `/gdd:discuss` to start one, but still produce the map using basenames and inferred terms.
+
+## ZOOM-OUT COMPLETE

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@hegemonart/get-design-done",
-  "version": "1.41.5",
+  "version": "1.43.0",
   "description": "A design-quality pipeline for AI coding agents: brief, plan, implement, and verify UI work against your design system.",
   "author": "Hegemon",
   "homepage": "https://github.com/hegemonart/get-design-done",
@@ -23,6 +23,7 @@
     "sdk/",
     "recipes/",
     "docs/i18n/",
+    "dist/claude-code/",
     "scripts/lib/",
     "scripts/cli/",
     "scripts/install.cjs",
@@ -47,6 +48,8 @@
   },
   "scripts": {
     "build:bundles": "node scripts/build-distribution-bundles.cjs",
+    "build:skills": "node scripts/build-skills.cjs",
+    "build:skills:check": "node scripts/build-skills.cjs --check",
     "build:sdk": "node scripts/build-sdk-bins.cjs",
     "prepack": "npm run build:sdk",
     "postpack": "node scripts/build-sdk-bins.cjs --clean",
@@ -58,7 +61,10 @@
     "lint:links": "npx --yes lychee --no-progress --accept 200,206,403,429 \"**/*.md\" || true",
     "lint:agentskills": "node scripts/lint-agentskills-spec.cjs",
     "lint:changelog": "node scripts/lint-changelog.cjs",
+    "lint:prose": "node scripts/lint-prose.cjs",
     "lint:design": "node bin/gdd-detect test/fixtures/detect/negative --json",
+    "build:style": "node scripts/generate-style-md.cjs",
+    "build:style:check": "node scripts/generate-style-md.cjs --check",
     "sync:rule-catalogue": "node scripts/sync-rule-catalogue.cjs --check",
     "validate:manifest": "node scripts/validate-manifest.cjs --check",
     "validate:schemas": "node --experimental-strip-types scripts/validate-schemas.ts",
@@ -77,7 +83,7 @@
     "@types/node": "^25.6.0",
     "ajv-cli": "^5.0.0",
     "ajv-formats": "^3.0.1",
-    "esbuild": "^0.25.12",
+    "esbuild": "^0.28.0",
     "json-schema-to-typescript": "^15.0.0",
     "typescript": "^6.0.3"
   },

package/reference/DEPRECATIONS.md

@@ -9,11 +9,11 @@ the scanner pattern list in lockstep.
 
 ## Namespaces
 
-- **`/design:<cmd>`** → `/gdd:<cmd>` — deprecated in Phase 7 (namespace rename). All commands now use the `/gdd:` prefix. Migrated: every shipped skill invocation and agent reference now uses `/gdd:`.
+- **`/design:<cmd>`** → `/gdd:<cmd>` - deprecated in Phase 7 (namespace rename). All commands now use the `/gdd:` prefix. Migrated: every shipped skill invocation and agent reference now uses `/gdd:`.
 
 ## Agents
 
-- **`design-context-builder`** — replaced by the Phase 3 agent split (design-context-reader + design-context-summarizer). Mentioned only in historical documentation; new work must spawn the split agents directly.
+- **`design-context-builder`** - replaced by the Phase 3 agent split (design-context-reader + design-context-summarizer). Mentioned only in historical documentation; new work must spawn the split agents directly.
 - **`design-pattern-mapper`** (monolithic) → split into 5 domain mappers in Phase 3 (migrated):
   - `token-mapper`
   - `component-taxonomy-mapper`
@@ -28,11 +28,25 @@ the scanner pattern list in lockstep.
 - **`scan`** (stage name) → merged/renamed into `explore` in Phase 3. Migration: references to the `scan` stage in shipped skills and agents were replaced with `explore`.
 - **`discover`** (stage name) → merged/renamed into `explore` in Phase 3. Migration: references to the `discover` stage in shipped skills and agents were replaced with `explore`.
 
+## Authoring surfaces
+
+- **`skills/` as the authoring source** → **`source/skills/`** - deprecated in Phase 42 (multi-harness
+  source compilation). Skills are now authored once in `source/skills/` with placeholders
+  (`{{command_prefix}}` et al.; see `reference/skill-placeholders.md`) and compiled per-harness by
+  `scripts/build-skills.cjs`. The committed `skills/` tree is now a **generated artifact** (the Claude-Code
+  compile target) - CI's `npm run build:skills:check` drift-gates `committed === generated`.
+
+  Migration for contributors: **edit `source/skills/`, never `skills/` directly**, then run
+  `npm run build:skills` (or `gdd-sdk build skills`) and commit the regenerated `skills/` +
+  `dist/claude-code/`. `.claude-plugin/plugin.json`'s `"skills": ["./skills/"]` is unchanged - the plugin
+  still loads `skills/`, now produced from `source/skills/`. This is a path/authoring move only; no
+  stale-ref token is emitted (both paths are live), so the `detect-stale-refs.cjs` list is not extended.
+
 ## Scanner scope
 
 `scripts/detect-stale-refs.cjs` flags these tokens (line-granular match):
 
-- `/design:<cmd>` — any occurrence of the legacy namespace
+- `/design:<cmd>` - any occurrence of the legacy namespace
 - `design-context-builder` (standalone word)
 - `design-pattern-mapper` (when not followed by `-<suffix>`)
 - `scan/SKILL.md` and `discover/SKILL.md` path references
@@ -42,7 +56,7 @@ The scanner excludes `.planning/`, `.claude/`, `.design/`, `node_modules/`,
 
 ## Path migrations (machine-readable)
 
-Phase 39.5 adds a machine-readable registry of **path** migrations — modules/files GDD moved or
+Phase 39.5 adds a machine-readable registry of **path** migrations - modules/files GDD moved or
 removed. `scripts/lib/deprecation-registry.cjs` parses the table below; `/gdd:migrate` consults it to
 help users update local references; `test/suite/deprecation-completeness.test.cjs` asserts every row
 is honest (a `removed` row's `Old` path must be gone from the tree; a `deprecated` row's `Old` path
@@ -52,9 +66,9 @@ must still carry a shim).
 
 A row's status is derived from the running plugin version `v`:
 
-- **pending** — `v` < `Since` (deprecation announced for a future version; rare).
-- **deprecated** — `Since` ≤ `v` < `Removed in` (the old path still works via a shim; update at leisure).
-- **removed** — `v` ≥ `Removed in` (the old path is gone; you MUST use the new path).
+- **pending** - `v` < `Since` (deprecation announced for a future version; rare).
+- **deprecated** - `Since` ≤ `v` < `Removed in` (the old path still works via a shim; update at leisure).
+- **removed** - `v` ≥ `Removed in` (the old path is gone; you MUST use the new path).
 
 **Default shim lifetime is one minor version** (the Phase 31.5 precedent): a path deprecated in `x.y.z`
 is removed in the next minor `x.(y+1).0`. The `Removed in` column is authoritative per row.

package/reference/STATE-TEMPLATE.md

@@ -8,8 +8,8 @@ This is the canonical template for the design pipeline's runtime state file.
 - `.design/` is gitignored (not distributed with the plugin); only this template ships.
 
 **Distinction from `.planning/STATE.md`:**
-- `.planning/STATE.md` is GSD development state — used by the developers building this plugin.
-- `.design/STATE.md` is pipeline runtime state — used by the pipeline when it runs in a user's project.
+- `.planning/STATE.md` is GSD development state - used by the developers building this plugin.
+- `.design/STATE.md` is pipeline runtime state - used by the pipeline when it runs in a user's project.
 - Keep them strictly separate. Cross-references between them are deferred to Phase 6 per CONTEXT.md.
 
 ---
@@ -140,22 +140,22 @@ verify_completed_at: ~
 | Field | Type | Set by | Purpose |
 |-------|------|--------|---------|
 | `pipeline_state_version` | float | fixed at `1.0` | Forward-compat marker for future format changes |
-| `stage` | enum | every stage at entry | Current stage — one of: `brief|explore|plan|design|verify` |
+| `stage` | enum | every stage at entry | Current stage - one of: `brief|explore|plan|design|verify` |
 | `cycle` | string | lifecycle commands | Cycle identifier for Wave B multi-cycle projects (default: empty string) |
 | `wave` | int | every stage | Wave number within current stage |
-| `started_at` | ISO 8601 | scan at creation | Immutable — never updated after creation |
+| `started_at` | ISO 8601 | scan at creation | Immutable - never updated after creation |
 | `last_checkpoint` | ISO 8601 | every stage at exit | Updated on every stage transition and on mid-stage checkpoint |
 
 ### `<position>`
 
-Mirrors frontmatter stage/wave plus progress and status. Duplication is intentional — frontmatter is scannable by tooling; `<position>` is scannable by prose reading.
+Mirrors frontmatter stage/wave plus progress and status. Duplication is intentional - frontmatter is scannable by tooling; `<position>` is scannable by prose reading.
 
-- `task_progress`: `<completed>/<total>` — e.g. `3/7` means 3 of 7 tasks in the current stage complete
+- `task_progress`: `<completed>/<total>` - e.g. `3/7` means 3 of 7 tasks in the current stage complete
 - `status`: one of
-  - `initialized` — scan just created the file, no work done
-  - `in_progress` — stage is actively running
-  - `completed` — stage finished successfully; next stage may begin
-  - `blocked` — stage cannot proceed; see `<blockers>`
+  - `initialized` - scan just created the file, no work done
+  - `in_progress` - stage is actively running
+  - `completed` - stage finished successfully; next stage may begin
+  - `blocked` - stage cannot proceed; see `<blockers>`
 
 ### `<decisions>`
 
@@ -173,25 +173,25 @@ Discover stage populates with observable behaviors. Verify stage updates status.
 
 ### `<prototyping>`
 
-Phase 25 surface (D-01). A checkpoint log — NOT a stage. Tracks sketch and spike outcomes plus cycle-scoped skip suppressions for the prototype gate.
+Phase 25 surface (D-01). A checkpoint log - NOT a stage. Tracks sketch and spike outcomes plus cycle-scoped skip suppressions for the prototype gate.
 
-- `<sketch slug=… cycle=… decision=D-XX status=resolved/>` — written by `sketch-wrap-up` after a sketch resolves into a D-XX decision.
-- `<spike slug=… cycle=… decision=D-XX verdict=yes|no|partial status=resolved/>` — written by `spike-wrap-up` after a spike resolves; `verdict` captures the answer.
-- `<skipped at=… cycle=… reason=…/>` — written by the prototype gate when the user declines to sketch/spike at a firing point. Cycle-scoped suppression (D-02): a `<skipped/>` entry suppresses re-asking for the rest of the named cycle.
+- `<sketch slug=… cycle=… decision=D-XX status=resolved/>` - written by `sketch-wrap-up` after a sketch resolves into a D-XX decision.
+- `<spike slug=… cycle=… decision=D-XX verdict=yes|no|partial status=resolved/>` - written by `spike-wrap-up` after a spike resolves; `verdict` captures the answer.
+- `<skipped at=… cycle=… reason=…/>` - written by the prototype gate when the user declines to sketch/spike at a firing point. Cycle-scoped suppression (D-02): a `<skipped/>` entry suppresses re-asking for the rest of the named cycle.
 
-The block is **optional** — fresh STATE.md files do not carry it. The serializer omits the block entirely when no entries exist; appending the first entry is what materializes the block.
+The block is **optional** - fresh STATE.md files do not carry it. The serializer omits the block entirely when no entries exist; appending the first entry is what materializes the block.
 
 ### `<quality_gate>`
 
-Phase 25 surface (Plan 25-03 / D-06..D-09). Captures the most recent run of the Stage 4.5 quality gate (lint / typecheck / test / visual-regression) between Design and Verify. The block houses a single self-closing `<run/>` element — append-mode is overkill, so each gate completion overwrites the entry.
+Phase 25 surface (Plan 25-03 / D-06..D-09). Captures the most recent run of the Stage 4.5 quality gate (lint / typecheck / test / visual-regression) between Design and Verify. The block houses a single self-closing `<run/>` element - append-mode is overkill, so each gate completion overwrites the entry.
 
-- `started_at` — ISO 8601 at which the parallel command run entered.
-- `completed_at` — ISO 8601 at which the gate produced its terminal status.
-- `status` — `pass | fail | timeout | skipped`. `pass` clears the verify-entry gate; `fail` blocks; `timeout` warns + proceeds (D-07); `skipped` indicates the detection chain resolved zero commands.
-- `iteration` — non-negative integer fix-loop count (D-08). `1` = single clean pass; `N === max_iters` with `status === 'fail'` = bounded exhaustion.
-- `commands_run` — comma-separated names of the commands actually executed in Step 2 (e.g., `lint,typecheck,test`). Empty string when `status === 'skipped'`.
+- `started_at` - ISO 8601 at which the parallel command run entered.
+- `completed_at` - ISO 8601 at which the gate produced its terminal status.
+- `status` - `pass | fail | timeout | skipped`. `pass` clears the verify-entry gate; `fail` blocks; `timeout` warns + proceeds (D-07); `skipped` indicates the detection chain resolved zero commands.
+- `iteration` - non-negative integer fix-loop count (D-08). `1` = single clean pass; `N === max_iters` with `status === 'fail'` = bounded exhaustion.
+- `commands_run` - comma-separated names of the commands actually executed in Step 2 (e.g., `lint,typecheck,test`). Empty string when `status === 'skipped'`.
 
-The block is **optional** — fresh STATE.md files do not carry it. The serializer omits the block entirely when `quality_gate === null`; the SKILL writes the first `<run/>` to materialize it.
+The block is **optional** - fresh STATE.md files do not carry it. The serializer omits the block entirely when `quality_gate === null`; the SKILL writes the first `<run/>` to materialize it.
 
 ### `<connections>`
 
@@ -202,7 +202,7 @@ One line per external connection. Detected at scan entry via MCP availability pr
 
 ### `<blockers>`
 
-Append-only log of active blockers. Format: `[stage] [ISO date]: [description]`. Cleared manually when blocker resolves (do not auto-clear — preserve the record).
+Append-only log of active blockers. Format: `[stage] [ISO date]: [description]`. Cleared manually when blocker resolves (do not auto-clear - preserve the record).
 
 ### `<timestamps>`
 
@@ -217,7 +217,7 @@ Every stage that runs in the pipeline MUST follow this contract when reading and
 **At entry:**
 1. Read `.design/STATE.md`. If the file does not exist and the current stage is `scan`, create it from this template with `started_at` = now and `last_checkpoint` = now; otherwise abort with a clear error ("run scan first").
 2. Parse frontmatter `stage` and `<position>` `status`.
-3. If `stage == current_stage` and `status == in_progress`: RESUME — pick up from `task_progress` offset; do not reset progress.
+3. If `stage == current_stage` and `status == in_progress`: RESUME - pick up from `task_progress` offset; do not reset progress.
 4. If `stage != current_stage`: this is a normal stage transition. Set frontmatter `stage = current_stage`, `<position>` `stage = current_stage`, `<position>` `status = in_progress`, `<position>` `task_progress = 0/<total>`.
 5. Update `<connections>` by probing each MCP tool; write the detected status.
 6. Update `last_checkpoint` to now.
@@ -248,6 +248,6 @@ Every stage that runs in the pipeline MUST follow this contract when reading and
 ## Notes for Phase 2 implementors
 
 - Do not add new top-level XML sections without updating this template.
-- The write contract is non-negotiable — stages that skip the read-at-entry step break resume.
+- The write contract is non-negotiable - stages that skip the read-at-entry step break resume.
 - `<decisions>` and `<must_haves>` identifiers are sequential per-project, not globally unique. A new pipeline run on the same project starts at `D-01` / `M-01`.
-- When in doubt, prefer appending new fields to existing sections over introducing new sections — preserves compatibility with `pipeline_state_version: 1.0`.
+- When in doubt, prefer appending new fields to existing sections over introducing new sections - preserves compatibility with `pipeline_state_version: 1.0`.

package/reference/accessibility.md

@@ -1,10 +1,10 @@
-# Accessibility — Thresholds and Requirements
+# Accessibility - Thresholds and Requirements
 
 These are concrete, measurable standards. WCAG 2.1 AA is the minimum baseline for all design work unless the client explicitly requires AAA or specifies otherwise.
 
 ---
 
-## WCAG 2.1 AA — Required Thresholds
+## WCAG 2.1 AA - Required Thresholds
 
 ### Color Contrast
 
@@ -12,20 +12,20 @@ These are concrete, measurable standards. WCAG 2.1 AA is the minimum baseline fo
 |---|---|---|
 | Normal text (< 18pt / < 14pt bold) | **4.5 : 1** | 7 : 1 |
 | Large text (≥ 18pt or ≥ 14pt bold) | **3 : 1** | 4.5 : 1 |
-| UI components and graphical objects | **3 : 1** | — |
-| Decorative elements | No requirement | — |
+| UI components and graphical objects | **3 : 1** | - |
+| Decorative elements | No requirement | - |
 
 **Calculate contrast**: `(L1 + 0.05) / (L2 + 0.05)` where L1 is the lighter luminance.
 
 Common pitfalls:
-- Placeholder text in inputs: must meet 4.5:1 (often doesn't — gray placeholders fail)
+- Placeholder text in inputs: must meet 4.5:1 (often doesn't - gray placeholders fail)
 - Disabled state text: WCAG exempts disabled elements, but aim for ≥ 3:1 anyway
 - Link color vs body text: must be distinguishable by more than color alone (underline or 3:1 ratio vs background)
 - Focus ring color vs its background: must meet 3:1
 
 Tools: Use browser DevTools > Accessibility tab, or pass hex values through contrast calculation.
 
-**See also:** [`./contrast-advanced.md`](./contrast-advanced.md) — APCA (WCAG 3 draft) for perceptual contrast when WCAG 2.1 4.5:1 misranks thin/large/colored text. Recommended dual-target pattern: enforce WCAG 2.1 AA as a floor + APCA Lc-thresholds (75 / 60 / 45 / 30) for perceptual accuracy.
+**See also:** [`./contrast-advanced.md`](./contrast-advanced.md) - APCA (WCAG 3 draft) for perceptual contrast when WCAG 2.1 4.5:1 misranks thin/large/colored text. Recommended dual-target pattern: enforce WCAG 2.1 AA as a floor + APCA Lc-thresholds (75 / 60 / 45 / 30) for perceptual accuracy.
 
 ### Touch Target Size
 
@@ -34,7 +34,7 @@ Tools: Use browser DevTools > Accessibility tab, or pass hex values through cont
 | iOS (Apple HIG) | **44 × 44 pt** |
 | Android (Material Design) | **48 × 48 dp** |
 | Web (WCAG 2.5.5 AAA) | **44 × 44 px** |
-| Web (WCAG 2.5.8 AA — WCAG 2.2) | **24 × 24 px** (minimum, with spacing) |
+| Web (WCAG 2.5.8 AA - WCAG 2.2) | **24 × 24 px** (minimum, with spacing) |
 
 Recommended target: 44 × 44 px on all platforms. Never smaller for primary actions.
 
@@ -49,7 +49,7 @@ hitSlop={{ top: 8, bottom: 8, left: 8, right: 8 }}
 
 All interactive elements must have a visible focus indicator.
 
-**Required for WCAG 2.4.11 (AA — WCAG 2.2):**
+**Required for WCAG 2.4.11 (AA - WCAG 2.2):**
 - Focus indicator at minimum: **2px solid** outline, encloses the component
 - Contrast between focused and unfocused: **3:1**
 - Focus indicator doesn't overlap component content
@@ -71,13 +71,13 @@ Recommended focus ring: **3px solid**, `2px offset`, brand primary or `#2563eb`.
 
 ### Semantic Structure
 
-- One `<h1>` per page. Headings are sequential: `h1` → `h2` → `h3` — never skip levels.
-- Interactive elements are focusable: use `<button>` for buttons, `<a href>` for links — never `<div onClick>`.
-- Form inputs have associated `<label for="id">` — not just placeholder text.
+- One `<h1>` per page. Headings are sequential: `h1` → `h2` → `h3` - never skip levels.
+- Interactive elements are focusable: use `<button>` for buttons, `<a href>` for links - never `<div onClick>`.
+- Form inputs have associated `<label for="id">` - not just placeholder text.
 - Images have descriptive `alt=""` for meaningful images; `alt=""` for decorative.
 - Icon-only buttons have `aria-label`: `<button aria-label="Close dialog">×</button>`.
 
-**See:** [`./i18n.md`](./i18n.md) §WCAG i18n for SC 3.1.1 (`<html lang>`) and SC 3.1.2 (`<span lang="…">` language-of-parts) patterns — screen readers select voice/pronunciation packs from these attributes; a missing or wrong `lang` value forces the user to hear French announced in an English accent.
+**See:** [`./i18n.md`](./i18n.md) §WCAG i18n for SC 3.1.1 (`<html lang>`) and SC 3.1.2 (`<span lang="…">` language-of-parts) patterns - screen readers select voice/pronunciation packs from these attributes; a missing or wrong `lang` value forces the user to hear French announced in an English accent.
 
 ### Color Must Not Be The Only Differentiator
 
@@ -154,7 +154,7 @@ font-size: 16px;
 
 All animations must respect `prefers-reduced-motion: reduce`. See `reference/motion.md`.
 
-The `prefers-reduced-motion` check is an accessibility requirement (WCAG 2.3.3 AAA; WCAG 2.2 reduces to recommendation — but implement it regardless).
+The `prefers-reduced-motion` check is an accessibility requirement (WCAG 2.3.3 AAA; WCAG 2.2 reduces to recommendation - but implement it regardless).
 
 ---
 

package/reference/adr-format.md

@@ -7,13 +7,13 @@ tags: [adr, decision, project-scoped, architecture, offer-gate]
 last_updated: 2026-05-18
 ---
 
-Source: mattpocock/skills (MIT) — adapted with permission. See `../NOTICE` for the full attribution block.
+Source: mattpocock/skills (MIT) - adapted with permission. See `../NOTICE` for the full attribution block.
 
 # ADR Format
 
 An Architecture Decision Record (ADR) is a project-scoped record of a decision that
 outlives the current cycle. ADRs live at `docs/adr/NNNN-<slug>.md` (zero-padded sequence,
-kebab-case slug) and are offered SPARINGLY — only when all three criteria of the offer
+kebab-case slug) and are offered SPARINGLY - only when all three criteria of the offer
 gate hold (D-04). Most decisions stay in `STATE.md` and roll over with the cycle; ADRs
 are the rare exception. See `./context-md-format.md` for the lighter glossary form that
 shares the same project-scoped lifetime.
@@ -31,12 +31,12 @@ the decision in `STATE.md` instead.
   stated reasons. Decisions with no plausible alternative (e.g., "use HTTPS") do not
   qualify.
 
-Worked example — **qualifier:** "Switch from REST to GraphQL for the public API."
+Worked example - **qualifier:** "Switch from REST to GraphQL for the public API."
 Hard-to-reverse (clients integrate against the schema), surprising-without-context (most
 greenfield APIs default to REST), real-tradeoff (tRPC and gRPC were rejected for stated
 reasons). Ship an ADR.
 
-Worked example — **disqualifier:** "Rename the `users` table to `accounts`." Hard-to-reverse,
+Worked example - **disqualifier:** "Rename the `users` table to `accounts`." Hard-to-reverse,
 but the rationale is obvious from the rename and there is no real alternative once the
 domain has settled on the word. Log in `STATE.md`, not an ADR.
 
@@ -63,14 +63,14 @@ supersedes: <optional — ADR number this one replaces, e.g., "0042">
 ## Body structure
 
 The ADR body uses four `##` sections in the following order. Each section is a thin
-paragraph or short bullet list — ADRs are decision records, not design docs.
+paragraph or short bullet list - ADRs are decision records, not design docs.
 
-- `## Context` — what situation made this decision necessary; cite the originating
+- `## Context` - what situation made this decision necessary; cite the originating
   cycle's `BRIEF.md` or `STATE.md` if relevant.
-- `## Decision` — what was chosen, stated as an imperative.
-- `## Alternatives` — what was considered and rejected, with brief rationale per
+- `## Decision` - what was chosen, stated as an imperative.
+- `## Alternatives` - what was considered and rejected, with brief rationale per
   alternative.
-- `## Consequences` — what this enables, what it costs, what it constrains downstream.
+- `## Consequences` - what this enables, what it costs, what it constrains downstream.
 
 ## Status lifecycle
 
@@ -81,16 +81,16 @@ truth; transitions are explicit, never silent.
   does not cite Proposed ADRs.
 - **Accepted.** Decision active; downstream work cites this ADR by number.
 - **Superseded.** Replaced by a later ADR. The later ADR's `supersedes:` field points
-  here, and this ADR's status is flipped to Superseded. NEVER delete a Superseded ADR —
+  here, and this ADR's status is flipped to Superseded. NEVER delete a Superseded ADR -
   the audit trail is the point.
 - **Deprecated.** No longer relevant (e.g., the system the ADR governed was removed).
   Kept for history.
 
 ## Cross-references
 
-- Domain terms used in the ADR body should already appear in `CONTEXT.md` — see
+- Domain terms used in the ADR body should already appear in `CONTEXT.md` - see
   `./context-md-format.md`. If a term is missing, the writer adds it before referencing it.
-- Cycle-scoped decisions (most routine choices) stay in `STATE.md` — see
+- Cycle-scoped decisions (most routine choices) stay in `STATE.md` - see
   `./STATE-TEMPLATE.md`.
-- Skill structural rules (length cap, frontmatter, progressive disclosure) — see
+- Skill structural rules (length cap, frontmatter, progressive disclosure) - see
   `./skill-authoring-contract.md`.

package/reference/ai-native-tool-interface.md

@@ -1,4 +1,4 @@
-# AI-Native Design Tool Interface — Capability Contract
+# AI-Native Design Tool Interface - Capability Contract
 
 This file defines the capability-based contract that AI-native design tools must implement to integrate with the get-design-done pipeline. Two sub-categories are defined: **canvas** and **component-generator**. Future tools implement one sub-category and plug in via the same probe/read/write or probe/generate/adopt surface.
 
@@ -26,8 +26,8 @@ write(proposal) → { confirmed | rejected }
 ```
 
 **Implementations:**
-- `connections/paper-design.md` — MCP-based; 24-tool server; budget: 100 calls/week (free)
-- `connections/pencil-dev.md` — file-based; `.pen` YAML spec files; git-tracked; no MCP
+- `connections/paper-design.md` - MCP-based; 24-tool server; budget: 100 calls/week (free)
+- `connections/pencil-dev.md` - file-based; `.pen` YAML spec files; git-tracked; no MCP
 
 **Pipeline stages:** `explore` (read) + `verify` (screenshot) + `design` (write via writer agent)
 
@@ -53,8 +53,8 @@ adopt(variant: object) → { confirmed | rejected }
 ```
 
 **Implementations:**
-- `connections/21st-dev.md` — Magic MCP; `npx @21st-dev/magic@latest init`; marketplace prior-art gate
-- `connections/magic-patterns.md` — Claude connector (`mcp__magic_patterns*`) + API key fallback; DS-aware generation
+- `connections/21st-dev.md` - Magic MCP; `npx @21st-dev/magic@latest init`; marketplace prior-art gate
+- `connections/magic-patterns.md` - Claude connector (`mcp__magic_patterns*`) + API key fallback; DS-aware generation
 
 **Pipeline stages:** `explore` (prior-art gate for 21st.dev) + `design` (generate + adopt)
 

package/reference/anti-patterns.md

@@ -8,7 +8,7 @@ Use during Discover (baseline audit), Design (prevention), and Verify (complianc
 
 Before shipping any artifact: **"If I told someone 'AI made this,' would they believe me immediately?"**
 
-If yes — redo. The training-set monoculture has specific fingerprints. Learn them all.
+If yes - redo. The training-set monoculture has specific fingerprints. Learn them all.
 
 ---
 
@@ -28,7 +28,7 @@ border-right: 3px solid #6366f1;
 
 **Why**: The border-left accent card is the most recognizable AI default. It signals no design thinking happened.
 
-**Fix**: Use different element structure — colored icon, colored background section, or inline accent element.
+**Fix**: Use different element structure - colored icon, colored background section, or inline accent element.
 
 **Grep**: `border-left:\s*[2-9][0-9]*px|border-right:\s*[2-9][0-9]*px`
 
@@ -89,7 +89,7 @@ background: rgb(0, 0, 0);
 
 **Why**: Pure black in dark mode creates harsh contrast and looks amateur.
 
-**Fix**: oklch(12% 0 0) through oklch(18% 0.005 [hue]) — slightly warm or cool near-black.
+**Fix**: oklch(12% 0 0) through oklch(18% 0.005 [hue]) - slightly warm or cool near-black.
 
 **Grep**: `background.*#000000|background.*rgb\(0,\s*0,\s*0\)`
 
@@ -194,7 +194,7 @@ Glassmorphism as the default card treatment signals no layout thinking.
 
 Using Inter, DM Sans, Space Grotesk, or Plus Jakarta Sans without a documented brand reason.
 
-**Test**: Can you give 3 concrete reasons this font matches the product's brand? If not — choose again.
+**Test**: Can you give 3 concrete reasons this font matches the product's brand? If not - choose again.
 
 ### SLOP-06: Card-in-Card
 
@@ -235,7 +235,7 @@ Pastel-colored isometric illustrations with floating icons. Figma community temp
 ### Color Errors
 
 - Gray on colored backgrounds (fails contrast, not "subtle")
-- Pure gray neutrals — add 0.005–0.015 chroma toward brand hue
+- Pure gray neutrals - add 0.005–0.015 chroma toward brand hue
 - Red + green as the only meaning carrier (colorblind failure)
 - Text over image without scrim or overlay
 - Alpha-heavy transparency everywhere (incomplete palette signal)
@@ -274,7 +274,7 @@ Pastel-colored isometric illustrations with floating icons. Figma community temp
 
 - `ease-in` on entrances (use `ease-out`)
 - Same duration for enter and exit (exit should be 60–70% of enter)
-- Animating `width`/`height` (triggers layout — use `transform` only)
+- Animating `width`/`height` (triggers layout - use `transform` only)
 - No `prefers-reduced-motion` media query
 - Popover origin `transform-origin: center` (should come from trigger element)
 - Button with no `:active` press feedback
@@ -292,11 +292,11 @@ Pastel-colored isometric illustrations with floating icons. Figma community temp
 - No progressive disclosure on long forms (show all fields upfront)
 
 ### Feedback
-- Instant (0ms) state transitions — feels broken
+- Instant (0ms) state transitions - feels broken
 - "Loading..." spinners with no context ("Loading contacts..." is better)
 - Success toast that blocks the next interaction
 - Destructive action with no undo and no confirmation
-- Confirmation dialog for reversible action (annoyance — use undo instead)
+- Confirmation dialog for reversible action (annoyance - use undo instead)
 
 ### Navigation
 - Browser back button breaks app state
@@ -359,7 +359,7 @@ If YES to any → rewrite that element before proceeding.
 
 bdId: BAN-10
 
-Applying the same `border-radius` to a container and an element inside it (when the element is separated by padding) makes the inner element appear to "float" — the radii should be concentric, not equal.
+Applying the same `border-radius` to a container and an element inside it (when the element is separated by padding) makes the inner element appear to "float" - the radii should be concentric, not equal.
 
 **Grep (Tailwind):**
 ```