@hegemonart/get-design-done 1.59.2 → 1.59.4

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (161) hide show
  1. package/.claude-plugin/marketplace.json +2 -2
  2. package/.claude-plugin/plugin.json +1 -1
  3. package/CHANGELOG.md +56 -0
  4. package/SKILL.md +2 -0
  5. package/agents/design-advisor.md +1 -1
  6. package/agents/design-context-checker-gate.md +0 -1
  7. package/agents/design-context-checker.md +0 -1
  8. package/agents/design-context-reviewer-gate.md +0 -1
  9. package/agents/design-context-reviewer.md +0 -1
  10. package/agents/design-integration-checker-gate.md +0 -1
  11. package/agents/design-integration-checker.md +0 -1
  12. package/agents/design-plan-checker.md +0 -1
  13. package/agents/design-verifier-gate.md +0 -1
  14. package/agents/design-verifier.md +0 -1
  15. package/agents/prototype-gate.md +0 -1
  16. package/agents/quality-gate-runner.md +0 -1
  17. package/figma-plugin/README.md +61 -0
  18. package/figma-plugin/code.ts +36 -0
  19. package/figma-plugin/manifest.json +12 -0
  20. package/figma-plugin/package-lock.json +35 -0
  21. package/figma-plugin/package.json +12 -0
  22. package/figma-plugin/src/export-variables.ts +144 -0
  23. package/figma-plugin/src/payload-schema.ts +250 -0
  24. package/figma-plugin/tsconfig.json +16 -0
  25. package/figma-plugin/ui.html +44 -0
  26. package/hooks/gdd-intel-trigger.js +3 -3
  27. package/package.json +6 -1
  28. package/reference/DEPRECATIONS.md +3 -3
  29. package/reference/live-mode-integration.md +1 -1
  30. package/reference/registry.json +1 -1
  31. package/reference/skill-metadata.md +4 -4
  32. package/reference/skill-placeholders.md +2 -2
  33. package/scripts/build-skills.cjs +146 -0
  34. package/scripts/generate-skill-frontmatter.cjs +243 -0
  35. package/scripts/lib/manifest/scaffolder.cjs +1 -1
  36. package/scripts/lib/manifest/schemas/skills.schema.json +1 -1
  37. package/scripts/lib/manifest/skills.json +1 -1
  38. package/scripts/lib/new-addendum.cjs +1 -1
  39. package/scripts/skill-templates/README.md +90 -0
  40. package/scripts/skill-templates/add-backlog/SKILL.md +48 -0
  41. package/scripts/skill-templates/analyze-dependencies/SKILL.md +95 -0
  42. package/scripts/skill-templates/apply-reflections/SKILL.md +109 -0
  43. package/scripts/skill-templates/apply-reflections/apply-reflections-procedure.md +170 -0
  44. package/scripts/skill-templates/audit/SKILL.md +79 -0
  45. package/scripts/skill-templates/bandit-reset/SKILL.md +91 -0
  46. package/scripts/skill-templates/bandit-status/SKILL.md +94 -0
  47. package/scripts/skill-templates/benchmark/SKILL.md +65 -0
  48. package/scripts/skill-templates/bootstrap-ds/SKILL.md +43 -0
  49. package/scripts/skill-templates/brief/SKILL.md +145 -0
  50. package/scripts/skill-templates/budget/SKILL.md +45 -0
  51. package/scripts/skill-templates/cache-manager/SKILL.md +66 -0
  52. package/scripts/skill-templates/cache-manager/cache-policy.md +126 -0
  53. package/scripts/skill-templates/check-update/SKILL.md +98 -0
  54. package/scripts/skill-templates/compare/SKILL.md +82 -0
  55. package/scripts/skill-templates/compare/compare-rubric.md +171 -0
  56. package/scripts/skill-templates/complete-cycle/SKILL.md +81 -0
  57. package/scripts/skill-templates/connections/SKILL.md +71 -0
  58. package/scripts/skill-templates/connections/connections-onboarding.md +608 -0
  59. package/scripts/skill-templates/context/SKILL.md +137 -0
  60. package/scripts/skill-templates/continue/SKILL.md +24 -0
  61. package/scripts/skill-templates/darkmode/SKILL.md +76 -0
  62. package/scripts/skill-templates/darkmode/darkmode-audit-procedure.md +258 -0
  63. package/scripts/skill-templates/debug/SKILL.md +41 -0
  64. package/scripts/skill-templates/debug/debug-feedback-loops.md +119 -0
  65. package/scripts/skill-templates/design/SKILL.md +118 -0
  66. package/scripts/skill-templates/design/design-procedure.md +304 -0
  67. package/scripts/skill-templates/discuss/SKILL.md +96 -0
  68. package/scripts/skill-templates/do/SKILL.md +45 -0
  69. package/scripts/skill-templates/explore/SKILL.md +118 -0
  70. package/scripts/skill-templates/explore/explore-procedure.md +267 -0
  71. package/scripts/skill-templates/export/SKILL.md +30 -0
  72. package/scripts/skill-templates/extract-learnings/SKILL.md +114 -0
  73. package/scripts/skill-templates/fast/SKILL.md +91 -0
  74. package/scripts/skill-templates/figma-extract/SKILL.md +64 -0
  75. package/scripts/skill-templates/figma-write/SKILL.md +50 -0
  76. package/scripts/skill-templates/graphify/SKILL.md +49 -0
  77. package/scripts/skill-templates/health/SKILL.md +99 -0
  78. package/scripts/skill-templates/health/health-mcp-detection.md +44 -0
  79. package/scripts/skill-templates/health/health-skill-length-report.md +69 -0
  80. package/scripts/skill-templates/help/SKILL.md +60 -0
  81. package/scripts/skill-templates/instinct/SKILL.md +111 -0
  82. package/scripts/skill-templates/list-assumptions/SKILL.md +61 -0
  83. package/scripts/skill-templates/list-pins/SKILL.md +27 -0
  84. package/scripts/skill-templates/live/SKILL.md +98 -0
  85. package/scripts/skill-templates/locale/SKILL.md +51 -0
  86. package/scripts/skill-templates/map/SKILL.md +89 -0
  87. package/scripts/skill-templates/migrate/SKILL.md +70 -0
  88. package/scripts/skill-templates/migrate-context/SKILL.md +123 -0
  89. package/scripts/skill-templates/new-addendum/SKILL.md +81 -0
  90. package/scripts/skill-templates/new-cycle/SKILL.md +37 -0
  91. package/scripts/skill-templates/new-project/SKILL.md +53 -0
  92. package/scripts/skill-templates/new-skill/SKILL.md +90 -0
  93. package/scripts/skill-templates/next/SKILL.md +68 -0
  94. package/scripts/skill-templates/note/SKILL.md +48 -0
  95. package/scripts/skill-templates/openrouter-status/SKILL.md +86 -0
  96. package/scripts/skill-templates/optimize/SKILL.md +97 -0
  97. package/scripts/skill-templates/override/SKILL.md +86 -0
  98. package/scripts/skill-templates/paper-write/SKILL.md +54 -0
  99. package/scripts/skill-templates/pause/SKILL.md +77 -0
  100. package/scripts/skill-templates/peer-cli-add/SKILL.md +88 -0
  101. package/scripts/skill-templates/peer-cli-add/peer-cli-protocol.md +161 -0
  102. package/scripts/skill-templates/peer-cli-customize/SKILL.md +89 -0
  103. package/scripts/skill-templates/peers/SKILL.md +96 -0
  104. package/scripts/skill-templates/pencil-write/SKILL.md +54 -0
  105. package/scripts/skill-templates/pin/SKILL.md +37 -0
  106. package/scripts/skill-templates/plan/SKILL.md +105 -0
  107. package/scripts/skill-templates/plan/plan-procedure.md +278 -0
  108. package/scripts/skill-templates/plant-seed/SKILL.md +48 -0
  109. package/scripts/skill-templates/pr-branch/SKILL.md +32 -0
  110. package/scripts/skill-templates/progress/SKILL.md +107 -0
  111. package/scripts/skill-templates/quality-gate/SKILL.md +90 -0
  112. package/scripts/skill-templates/quality-gate/threat-modeling.md +101 -0
  113. package/scripts/skill-templates/quick/SKILL.md +44 -0
  114. package/scripts/skill-templates/reapply-patches/SKILL.md +32 -0
  115. package/scripts/skill-templates/recall/SKILL.md +75 -0
  116. package/scripts/skill-templates/reflect/SKILL.md +85 -0
  117. package/scripts/skill-templates/reflect/procedures/capability-gap-scan.md +119 -0
  118. package/scripts/skill-templates/report-issue/SKILL.md +53 -0
  119. package/scripts/skill-templates/report-issue/report-issue-procedure.md +119 -0
  120. package/scripts/skill-templates/resume/SKILL.md +93 -0
  121. package/scripts/skill-templates/review-backlog/SKILL.md +46 -0
  122. package/scripts/skill-templates/review-decisions/SKILL.md +42 -0
  123. package/scripts/skill-templates/roi/SKILL.md +54 -0
  124. package/scripts/skill-templates/rollout-status/SKILL.md +35 -0
  125. package/scripts/skill-templates/router/SKILL.md +89 -0
  126. package/scripts/skill-templates/router/capability-gap-emitter.md +65 -0
  127. package/scripts/skill-templates/router/router-pick-emitter.md +78 -0
  128. package/scripts/skill-templates/router/router-rules.md +84 -0
  129. package/scripts/skill-templates/settings/SKILL.md +87 -0
  130. package/scripts/skill-templates/ship/SKILL.md +48 -0
  131. package/scripts/skill-templates/sketch/SKILL.md +78 -0
  132. package/scripts/skill-templates/sketch-wrap-up/SKILL.md +92 -0
  133. package/scripts/skill-templates/skill-manifest/SKILL.md +79 -0
  134. package/scripts/skill-templates/spike/SKILL.md +67 -0
  135. package/scripts/skill-templates/spike-wrap-up/SKILL.md +86 -0
  136. package/scripts/skill-templates/start/SKILL.md +67 -0
  137. package/scripts/skill-templates/start/start-procedure.md +115 -0
  138. package/scripts/skill-templates/state/SKILL.md +106 -0
  139. package/scripts/skill-templates/stats/SKILL.md +51 -0
  140. package/scripts/skill-templates/style/SKILL.md +71 -0
  141. package/scripts/skill-templates/style/style-doc-procedure.md +150 -0
  142. package/scripts/skill-templates/synthesize/SKILL.md +94 -0
  143. package/scripts/skill-templates/timeline/SKILL.md +66 -0
  144. package/scripts/skill-templates/todo/SKILL.md +64 -0
  145. package/scripts/skill-templates/turn-closeout/SKILL.md +95 -0
  146. package/scripts/skill-templates/undo/SKILL.md +31 -0
  147. package/scripts/skill-templates/unlock-decision/SKILL.md +54 -0
  148. package/scripts/skill-templates/unpin/SKILL.md +31 -0
  149. package/scripts/skill-templates/update/SKILL.md +56 -0
  150. package/scripts/skill-templates/using-gdd/SKILL.md +78 -0
  151. package/scripts/skill-templates/verify/SKILL.md +113 -0
  152. package/scripts/skill-templates/verify/verify-procedure.md +511 -0
  153. package/scripts/skill-templates/warm-cache/SKILL.md +81 -0
  154. package/scripts/skill-templates/watch-authorities/SKILL.md +82 -0
  155. package/scripts/skill-templates/zoom-out/SKILL.md +26 -0
  156. package/sdk/cli/commands/build.ts +2 -2
  157. package/sdk/cli/index.js +2 -2
  158. package/sdk/cli/index.ts +1 -1
  159. package/skills/README.md +22 -14
  160. package/skills/help/SKILL.md +28 -55
  161. package/skills/new-skill/SKILL.md +5 -5
package/scripts/skill-templates/sketch/SKILL.md ADDED
@@ -0,0 +1,78 @@
1
+ ---
2
+ name: gdd-sketch
3
+ description: "Multi-variant HTML design exploration that creates .design/sketches/<slug>/ with N standalone variants (default 3), browser-openable directly via file:// without a build step. Use when answering 'what could this look like?' before committing to a direction."
4
+ argument-hint: "[topic] [--variants N] [--quick]"
5
+ tools: Read, Write, AskUserQuestion, Bash
6
+ ---
7
+
8
+ # Get Design Done - Sketch
9
+
10
+ **Role:** Multi-variant HTML exploration. Answers "what could this look like?" by generating N standalone HTML variants from a topic prompt. Variants are browser-openable directly - no build step - and can be screenshot by Phase 8 Preview/Playwright tooling later.
11
+
12
+ Unlike `{{command_prefix}}spike` (which tests feasibility), `{{command_prefix}}sketch` explores visual/directional variants.
13
+
14
+ ## Flag parsing
15
+
16
+ Parse `$ARGUMENTS`:
17
+ - `[topic]` → kebab-case slug (e.g., "hero-redesign")
18
+ - `--variants N` → number of variants (default: 3)
19
+ - `--quick` → skip intake, use DESIGN-CONTEXT.md tokens + sensible defaults
20
+
21
+ ## Step 1 - Intake (unless `--quick`)
22
+
23
+ AskUserQuestion, one at a time:
24
+ 1. "What are you sketching? (component, layout, page)"
25
+ 2. "What directions should the variants explore? (minimal/maximal, dense/spacious, flat/layered, playful/restrained, etc.)"
26
+ 3. "Which design tokens apply? (pick from DESIGN-CONTEXT.md, or use defaults)"
27
+
28
+ If `--quick`: derive directions from topic + pull tokens from `.design/DESIGN-CONTEXT.md` if present, else defaults.
29
+
30
+ ## Step 2 - Create sketch directory
31
+
32
+ - Derive `<slug>` from the topic (kebab-case).
33
+ - `mkdir -p .design/sketches/<slug>/` via Bash.
34
+
35
+ ## Step 3 - Write INTAKE.md
36
+
37
+ Write `.design/sketches/<slug>/INTAKE.md` with:
38
+ - Topic
39
+ - Directions (one bullet per variant)
40
+ - Token references (link to DESIGN-CONTEXT.md or inline list)
41
+ - Timestamp
42
+
43
+ ## Step 4 - Generate N standalone HTML variants
44
+
45
+ For each of N variants (default 3), write `variant-<n>.html` as a **complete standalone HTML file**:
46
+ - `<!DOCTYPE html>` + `<html>` + `<head>` + `<body>`
47
+ - `<style>` block inline with CSS custom properties for tokens (`--color-*`, `--space-*`, `--font-*`)
48
+ - Semantic HTML5 (`<header>`, `<main>`, `<nav>`, `<section>`, etc.)
49
+ - No imports, no bundler, no JS framework - opens in a browser directly via `file://`
50
+ - Each variant explores a different direction from intake
51
+
52
+ ## Step 5 - Write README.md
53
+
54
+ Write `.design/sketches/<slug>/README.md` with:
55
+ - Topic + one-line summary
56
+ - List of variants: `variant-1.html` - direction label - one-line description
57
+ - How to view: "Open each `variant-*.html` in a browser."
58
+ - Next step: "Run `{{command_prefix}}sketch-wrap-up <slug>` when ready to pick a winner."
59
+
60
+ ## After writing
61
+
62
+ ```
63
+ ━━━ Sketches created ━━━
64
+ Slug: <slug>
65
+ Directory: .design/sketches/<slug>/
66
+ Variants: N standalone HTML files
67
+ Open variant-*.html in a browser.
68
+ Next: {{command_prefix}}sketch-wrap-up <slug>
69
+ ━━━━━━━━━━━━━━━━━━━━━━━━
70
+ ```
71
+
72
+ ## Do Not
73
+
74
+ - Do not write to `src/` - sketches live in `.design/sketches/` only.
75
+ - Do not use build-step syntax (JSX, TS, imports). Standalone HTML only.
76
+ - Do not overwrite an existing sketch slug without asking.
77
+
78
+ ## SKETCH COMPLETE
package/scripts/skill-templates/sketch-wrap-up/SKILL.md ADDED
@@ -0,0 +1,92 @@
1
+ ---
2
+ name: gdd-sketch-wrap-up
3
+ description: "Walk through sketches, pick winner + rationale, group by design area, write project skills to ./.claude/skills/design-<area>-conventions.md."
4
+ argument-hint: "[slug]"
5
+ tools: Read, Write, Glob, AskUserQuestion
6
+ ---
7
+
8
+ # Get Design Done - Sketch Wrap-Up
9
+
10
+ **Role:** Close an open sketch - elicit the winner + rationale from the user, group the decision by design area, and codify it as a project-local skill at `./.claude/skills/design-<area>-conventions.md` so future gdd sessions auto-load the decision. See `./reference/cycle-handoff-preamble.md` for the cycle-handoff framing this decision-archive feeds into.
11
+
12
+ ## Step 1 - Find sketches
13
+
14
+ - Glob `.design/sketches/*/`.
15
+ - If `[slug]` provided → use it directly.
16
+ - If multiple pending (no `WINNER.md`) → AskUserQuestion: "Which sketch are you wrapping up?"
17
+ - If none → print `No open sketches. Run {{command_prefix}}sketch first.` and exit.
18
+
19
+ ## Step 2 - Walk variants
20
+
21
+ Read the sketch's `README.md`. For each `variant-N.html`:
22
+
23
+ - Show the variant's one-line description from README.
24
+ - AskUserQuestion: "Is variant-N a keeper, maybe, or rejected?"
25
+
26
+ ## Step 3 - Elicit winner rationale
27
+
28
+ AskUserQuestion in sequence:
29
+
30
+ 1. "Which variant is the winner?"
31
+ 2. "What makes variant-N the winning direction? (grounds the decision for future sessions)"
32
+ 3. "Any token implications? (e.g., spacing scale clamp, color adjustment, font-weight shift)"
33
+
34
+ ## Step 4 - Group by design area
35
+
36
+ AskUserQuestion: "Which design area does this winner inform?" Options: `typography / color / layout / motion / component / interaction`.
37
+
38
+ ## Step 5 - Write project skill
39
+
40
+ Append to `./.claude/skills/design-<area>-conventions.md` (create if missing):
41
+
42
+ ```markdown
43
+ # Design <Area> Conventions (Project-Local)
44
+
45
+ Auto-loaded in gdd sessions. Captures decisions codified from `{{command_prefix}}sketch-wrap-up`.
46
+
47
+ ## Decision from sketch: <slug> (YYYY-MM-DD)
48
+ **Winner**: variant-N (<direction label>)
49
+ **Rationale**: <user rationale>
50
+ **Token implications**: <implications, or "none">
51
+ ```
52
+
53
+ ## Step 6 - Write WINNER.md
54
+
55
+ Write `.design/sketches/<slug>/WINNER.md` with: `# Winner: variant-N`, then bold-prefixed fields **Slug**, **Area**, **Rationale**, **Captured** (YYYY-MM-DD), **Project skill written to** (path from Step 5).
56
+
57
+ ## Step 7 - Append D-XX + `<prototyping>` outcome to STATE.md
58
+
59
+ Two coupled writes - both must succeed so the sketch resolution surfaces in both `<decisions>` (all downstream stages) and `<prototyping>` (planner-specific context via decision-injector). Compute `D-XX` as max existing `D-NN` + 1 (scan `<decisions>` for `D-\d+:`, zero-pad to 2 digits).
60
+
61
+ - **Write 1 (`<decisions>`):** `D-XX: sketch/<slug> — winner: variant-N — <rationale> (locked)\n Source: .design/sketches/<slug>/WINNER.md`
62
+ - **Write 2 (`<prototyping>`):** `<sketch slug="<slug>" cycle="<cycle>" decision="D-XX" status="resolved"/>`. `<cycle>` from STATE.md frontmatter; empty string valid for single-cycle Wave A projects. If `<prototyping>` block does not exist, materialize between `<must_haves>` and `<connections>` per STATE template; append the `<sketch …/>` as first child.
63
+
64
+ Prefer MCP `gdd_state` typed mutators (byte-identical output): `mcp__gdd_state__add_decision({id, text, status})` + `mcp__gdd_state__add_prototyping({type:"sketch", slug, cycle, decision, status})`. Without MCP, edit `.design/STATE.md` directly via Read + Write.
65
+
66
+ ## Step 8 - Update sketches SUMMARY.md
67
+
68
+ Append to `.design/sketches/SUMMARY.md` (create if missing):
69
+
70
+ ```
71
+ - <slug> (YYYY-MM-DD) — winner: variant-N — area: <area> — D-XX — <one-line rationale>
72
+ ```
73
+
74
+ ## After writing
75
+
76
+ ```
77
+ ━━━ Sketch wrapped ━━━
78
+ Slug: <slug>
79
+ Winner: variant-N
80
+ Area: <area>
81
+ Decision recorded: D-XX
82
+ Prototyping entry: <sketch slug="<slug>" cycle="<cycle>" decision="D-XX" status="resolved"/>
83
+ Project skill: ./.claude/skills/design-<area>-conventions.md
84
+ ━━━━━━━━━━━━━━━━━━━━━
85
+ ```
86
+
87
+ ## Do Not
88
+
89
+ - Do not modify other sketch variants or rejected directions.
90
+ - Do not write to `src/` - conventions are design-layer only.
91
+
92
+ ## SKETCH-WRAP-UP COMPLETE
package/scripts/skill-templates/skill-manifest/SKILL.md ADDED
@@ -0,0 +1,79 @@
1
+ ---
2
+ name: gdd-skill-manifest
3
+ description: "Lists all registered GDD skills and agents, with descriptions, from the intel store. Falls back to directory scan if intel store not present."
4
+ tools: Bash, Read, Glob
5
+ ---
6
+
7
+ # {{command_prefix}}skill-manifest
8
+
9
+ **Role:** Print a manifest of all registered skills (commands) and agents available in this plugin installation.
10
+
11
+ ## Pre-flight check
12
+
13
+ ```bash
14
+ ls .design/intel/exports.json 2>/dev/null && echo "ready" || echo "missing"
15
+ ```
16
+
17
+ ## Mode 1 - Intel store available
18
+
19
+ Read `.design/intel/exports.json`. Group entries by `kind` (skill vs agent). Print:
20
+
21
+ ```
22
+ ━━━ Skill Manifest ━━━
23
+ Generated from intel store: .design/intel/exports.json
24
+
25
+ SKILLS (Commands)
26
+ ─────────────────
27
+ {{command_prefix}}scan gdd-scan
28
+ {{command_prefix}}discover gdd-discover
29
+ {{command_prefix}}plan gdd-plan
30
+ {{command_prefix}}design gdd-design
31
+ {{command_prefix}}verify gdd-verify
32
+ {{command_prefix}}style gdd-style
33
+ {{command_prefix}}darkmode gdd-darkmode
34
+ {{command_prefix}}compare gdd-compare
35
+ ... (all skills)
36
+
37
+ AGENTS
38
+ ──────
39
+ design-advisor Design advisor agent
40
+ design-auditor Design auditor agent
41
+ design-context-builder Builds DESIGN-CONTEXT.md from codebase scan
42
+ ... (all agents)
43
+
44
+ Total: <N> skills, <M> agents
45
+ ━━━━━━━━━━━━━━━━━━━━━
46
+ ```
47
+
48
+ To get the description for each skill/agent: read `exports.json` entry and look up the matching file in `files.json`, then read its frontmatter `description` field from `exports.json` (if stored) or from the file directly.
49
+
50
+ ## Mode 2 - Intel store missing (fallback)
51
+
52
+ If `.design/intel/exports.json` is not present, fall back to directory scan:
53
+
54
+ ```bash
55
+ ls skills/
56
+ ls agents/*.md
57
+ ```
58
+
59
+ Print a simplified manifest without descriptions:
60
+
61
+ ```
62
+ ━━━ Skill Manifest (no intel store — run build-intel.cjs for descriptions) ━━━
63
+
64
+ SKILLS: scan, discover, plan, design, verify, style, darkmode, compare, ...
65
+ AGENTS: design-advisor.md, design-auditor.md, ...
66
+ ━━━━━━━━━━━━━━━━━━━━━
67
+ ```
68
+
69
+ ## Filter mode
70
+
71
+ `{{command_prefix}}skill-manifest agents` - show agents only
72
+ `{{command_prefix}}skill-manifest skills` - show skills only
73
+ `{{command_prefix}}skill-manifest <keyword>` - filter by keyword in name or description
74
+
75
+ ## Required reading (conditional)
76
+
77
+ @.design/intel/exports.json (if present)
78
+
79
+ ## SKILL-MANIFEST COMPLETE
package/scripts/skill-templates/spike/SKILL.md ADDED
@@ -0,0 +1,67 @@
1
+ ---
2
+ name: gdd-spike
3
+ description: "Timeboxed feasibility experiment that creates .design/spikes/<slug>/ with HYPOTHESIS.md, success/failure criteria, scratch/ subdirectory, and a default 60-minute timebox. Use when answering 'can this work?' before betting design or implementation effort on a risky approach."
4
+ argument-hint: "[hypothesis] [--timebox <minutes>]"
5
+ tools: Read, Write, Bash, AskUserQuestion
6
+ ---
7
+
8
+ # Get Design Done - Spike
9
+
10
+ **Role:** Timeboxed feasibility experiment. Answers "can this work?" - e.g., "can we use view transitions for this flow?", "does this animation perform on mobile?". Unlike `{{command_prefix}}sketch` (visual variants), `{{command_prefix}}spike` tests a hypothesis.
11
+
12
+ ## Flag parsing
13
+
14
+ Parse `$ARGUMENTS`:
15
+ - `[hypothesis]` → summary phrase, derives the slug
16
+ - `--timebox <minutes>` → default 60
17
+
18
+ ## Step 1 - Intake
19
+
20
+ AskUserQuestion:
21
+ 1. "What's the hypothesis? (e.g., 'view transitions can replace our current route animations')"
22
+ 2. "What's the timebox? (default 60 minutes)"
23
+ 3. "What would prove it works? (success criteria)"
24
+ 4. "What would prove it doesn't? (failure criteria)"
25
+
26
+ ## Step 2 - Create spike directory
27
+
28
+ - Derive `<slug>` from the hypothesis (kebab-case, short).
29
+ - `mkdir -p .design/spikes/<slug>/scratch/` via Bash.
30
+
31
+ ## Step 3 - Write HYPOTHESIS.md
32
+
33
+ Write `.design/spikes/<slug>/HYPOTHESIS.md`:
34
+ ```markdown
35
+ # Spike: <slug>
36
+
37
+ **Hypothesis**: <statement>
38
+ **Timebox**: <N> minutes
39
+ **Started**: YYYY-MM-DD HH:MM
40
+
41
+ ## Success criteria
42
+ - <criterion>
43
+
44
+ ## Failure criteria
45
+ - <criterion>
46
+
47
+ ## Scratch area
48
+ Experimental code in `./scratch/` — not committed to src/.
49
+ ```
50
+
51
+ ## Step 4 - Announce
52
+
53
+ ```
54
+ ━━━ Spike started ━━━
55
+ Slug: <slug>
56
+ Timebox: <N> minutes
57
+ Work in: .design/spikes/<slug>/scratch/
58
+ When done: {{command_prefix}}spike-wrap-up <slug>
59
+ ━━━━━━━━━━━━━━━━━━━━━
60
+ ```
61
+
62
+ ## Do Not
63
+
64
+ - Do not write experimental code to `src/` - use `.design/spikes/<slug>/scratch/`.
65
+ - Do not exceed the timebox without explicit user approval; wrap up and reassess first.
66
+
67
+ ## SPIKE COMPLETE
package/scripts/skill-templates/spike-wrap-up/SKILL.md ADDED
@@ -0,0 +1,86 @@
1
+ ---
2
+ name: gdd-spike-wrap-up
3
+ description: "Close a spike - capture findings, write decision to STATE.md, update SUMMARY.md."
4
+ argument-hint: "[slug]"
5
+ tools: Read, Write, Glob, AskUserQuestion
6
+ ---
7
+
8
+ # Get Design Done - Spike Wrap-Up
9
+
10
+ **Role:** Close an open spike - capture the verdict, write findings, record a D-XX decision in STATE.md so `plan` sees it when creating tasks. See `./reference/cycle-handoff-preamble.md` for the cycle-handoff framing this archive feeds into.
11
+
12
+ ## Step 1 - Find spike
13
+
14
+ - Glob `.design/spikes/*/`.
15
+ - If `[slug]` provided → use it directly.
16
+ - If multiple pending (no `FINDINGS.md`) → AskUserQuestion: "Which spike are you wrapping up?"
17
+ - If none → print `No open spikes. Run {{command_prefix}}spike first.` and exit.
18
+
19
+ ## Step 2 - Re-surface hypothesis
20
+
21
+ Read `.design/spikes/<slug>/HYPOTHESIS.md`. Show the hypothesis + success/failure criteria to the user.
22
+
23
+ ## Step 3 - Elicit findings
24
+
25
+ AskUserQuestion in sequence:
26
+
27
+ 1. "Did it meet success criteria? (yes / no / partial)"
28
+ 2. "What was learned? (1–3 sentences)"
29
+ 3. "Recommendation? (adopt / reject / needs more investigation)"
30
+
31
+ ## Step 4 - Write FINDINGS.md
32
+
33
+ Write `.design/spikes/<slug>/FINDINGS.md`:
34
+
35
+ ```markdown
36
+ # Findings: <slug>
37
+
38
+ **Verdict**: yes / no / partial
39
+ **Recommendation**: adopt / reject / needs more investigation
40
+ **Completed**: YYYY-MM-DD HH:MM
41
+
42
+ ## What was learned
43
+ <1–3 sentences>
44
+
45
+ ## Next steps
46
+ <1–2 bullets>
47
+ ```
48
+
49
+ ## Step 5 - Record decision in STATE.md
50
+
51
+ Append under `<decisions>`: `D-XX: spike/<slug> — <verdict> — <recommendation>\n Rationale: <one line>\n Source: .design/spikes/<slug>/FINDINGS.md`. Compute `D-XX` as max existing `D-NN` + 1 (scan for `D-\d+:`, zero-pad to 2 digits). Prefer MCP `gdd_state` typed mutator when available: `mcp__gdd_state__add_decision({id, text, status:"locked"})`.
52
+
53
+ ## Step 6 - Append `<prototyping>` outcome to STATE.md
54
+
55
+ Coupled with Step 5 - both must succeed so the spike resolution surfaces in `<decisions>` (downstream stages) and `<prototyping>` (planner via decision-injector). Use **same `D-XX`**. Append under `<prototyping>`: `<spike slug="<slug>" cycle="<cycle>" decision="D-XX" verdict="yes|no|partial" status="resolved"/>`. `<cycle>` from STATE.md frontmatter (`cycle:` field; empty string valid for single-cycle Wave A); `verdict` from Step 3.
56
+
57
+ If `<prototyping>` block does not exist, materialize between `<must_haves>` and `<connections>` per STATE template; append `<spike …/>` as first child.
58
+
59
+ Prefer MCP typed mutator (byte-identical output): `mcp__gdd_state__add_prototyping({type:"spike", slug, cycle, decision:"D-XX", verdict, status:"resolved"})`. Without MCP, edit `.design/STATE.md` directly via Read + Write.
60
+
61
+ ## Step 7 - Update spikes SUMMARY.md
62
+
63
+ Append to `.design/spikes/SUMMARY.md` (create if missing):
64
+
65
+ ```
66
+ - <slug> (YYYY-MM-DD) — verdict: <yes|no|partial> — recommendation: <adopt|reject|more> — D-XX
67
+ ```
68
+
69
+ ## After writing
70
+
71
+ ```
72
+ ━━━ Spike wrapped ━━━
73
+ Slug: <slug>
74
+ Verdict: <verdict>
75
+ Decision recorded: D-XX
76
+ Prototyping entry: <spike slug="<slug>" cycle="<cycle>" decision="D-XX" verdict="<verdict>" status="resolved"/>
77
+ FINDINGS.md written.
78
+ ━━━━━━━━━━━━━━━━━━━━
79
+ ```
80
+
81
+ ## Do Not
82
+
83
+ - Do not delete the `scratch/` directory - it's a record of what was tried.
84
+ - Do not promote scratch code to `src/` automatically - require a follow-up plan task.
85
+
86
+ ## SPIKE-WRAP-UP COMPLETE
package/scripts/skill-templates/start/SKILL.md ADDED
@@ -0,0 +1,67 @@
1
+ ---
2
+ name: start
3
+ description: "First-Run Proof Path - one command that scans your UI code and returns one concrete first fix. Leaf command, no STATE.md writes, no pipeline entry. Writes .design/START-REPORT.md and exits."
4
+ argument-hint: "[--budget <fast|balanced|thorough>] [--skip-interview] [--dismiss-nudge]"
5
+ tools: Read, Grep, Glob, Bash, Write, Task
6
+ disable-model-invocation: true
7
+ ---
8
+
9
+ # Get Design Done - {{command_prefix}}start
10
+
11
+ **Role:** the canonical 0→1 proof path. A new user runs `{{command_prefix}}start`, answers five short questions, and receives `.design/START-REPORT.md` with three concrete findings in the user's own code, one `best_first_proof` selected by a deterministic rubric, and a single next command to run.
12
+
13
+ **Non-goals:** do NOT write/mutate `.design/STATE.md`, enter the pipeline state machine, modify source code, auto-install MCPs or run `{{command_prefix}}connections`, or capture before/after screenshots (that belongs to the full pipeline).
14
+
15
+ ---
16
+
17
+ ## When to use
18
+
19
+ - First time opening a repo with the get-design-done plugin installed.
20
+ - The user wants a single proof-of-value pass without committing to the pipeline.
21
+
22
+ ## When NOT to use
23
+
24
+ - `.design/STATE.md` already exists - route to `{{command_prefix}}progress` instead.
25
+ - User asked for a full audit - route to `{{command_prefix}}scan`.
26
+ - User asked to fix a specific file - route to `{{command_prefix}}fast`.
27
+
28
+ ---
29
+
30
+ ## Arguments
31
+
32
+ | Flag | Effect |
33
+ |------|--------|
34
+ | `--budget fast` | 90-second wall-clock cap on the findings scan. Skips thorough detectors. |
35
+ | `--budget balanced` *(default)* | 3-minute wall-clock cap. All detectors, bounded file walk. |
36
+ | `--budget thorough` | 5-minute wall-clock cap. Used only when the user opts in. |
37
+ | `--skip-interview` | Skip the 5-question interview; use sane defaults (pain=unspecified, area=detected, budget=balanced, framework=detected, figma=skip). |
38
+ | `--dismiss-nudge` | Touch `~/.claude/gdd-nudge-dismissed` and exit. Does not run the scan. |
39
+
40
+ ---
41
+
42
+ ## Workflow
43
+
44
+ Six steps, all documented in `./start-procedure.md`. Companion file `./reference/start-interview.md` holds the 5-question copy + defaults + validation.
45
+
46
+ | Step | What it does | Where to look |
47
+ |------|--------------|---------------|
48
+ | 0 | Dismiss-only shortcut (if `--dismiss-nudge`) | `start-procedure.md#step-0-dismiss-only-shortcut` |
49
+ | 1 | Detect UI root via `scripts/lib/detect-ui-root.cjs` (early-exit on backend-only or `kind: null`) | `start-procedure.md#step-1-detect-ui-root` |
50
+ | 2 | Run 5-question interview (or use `--skip-interview` defaults); write `.design/.start-context.json` (NOT STATE.md) | `start-procedure.md#step-2-run-the-5-question-interview` + `start-interview.md` |
51
+ | 3 | Invoke `scripts/lib/start-findings-engine.cjs` → up to 3 findings (`F1`..`F3`) + `bestFirstProofId` | `start-procedure.md#step-3-scan-findings` |
52
+ | 4 | Spawn `design-start-writer` Task → emit `.design/START-REPORT.md` (7 H2 sections + JSON block, no STATE.md write) | `start-procedure.md#step-4-spawn-the-writer` |
53
+ | 5 | Print one-line handoff with suggested command (fallback: `{{command_prefix}}brief` if `bestFirstProofId` is null); emit `## START COMPLETE` | `start-procedure.md#step-5-print-the-handoff` |
54
+
55
+ Failure handling: every error path exits with `## START COMPLETE` plus a one-line pointer. Do not half-write files - if the writer fails, keep `.design/.start-context.json` and tell the user they can rerun. Do not delete `.design/` unless it was empty before the run.
56
+
57
+ ---
58
+
59
+ ## Do Not
60
+
61
+ - Do not write or mutate `.design/STATE.md`.
62
+ - Do not modify source code.
63
+ - Do not auto-install MCPs or write to `.design/config.json`.
64
+ - Do not take more than the budgeted wall-clock - let the engine truncate findings rather than hang.
65
+ - Do not invent findings - the findings engine output is the sole source of truth.
66
+
67
+ ## START COMPLETE
package/scripts/skill-templates/start/start-procedure.md ADDED
@@ -0,0 +1,115 @@
1
+ ---
2
+ name: start-procedure
3
+ type: heuristic
4
+ version: 1.0.0
5
+ phase: 28.5
6
+ tags: [start, first-run, proof-path, scan, writer-agent, handoff]
7
+ last_updated: 2026-05-18
8
+ ---
9
+
10
+ # Start Skill - Full Procedure
11
+
12
+ Extracted from `skills/start/SKILL.md` per Phase 28.5 D-10 (extract-then-link, never delete
13
+ content). The skill keeps its arguments table, step headings, and non-goals; the per-step
14
+ operational detail (interview JSON shape, scan invocation, writer spawn payload, handoff
15
+ template) lives here so the SKILL stays under the 100-line cap.
16
+
17
+ The companion file `./start-interview.md` (Phase 27 ship) holds the 5-question copy,
18
+ defaults, and validation rules. This file documents what `{{command_prefix}}start` does WITH the answers.
19
+
20
+ ## Step 0 - Dismiss-only shortcut
21
+
22
+ If invoked with `--dismiss-nudge`:
23
+
24
+ 1. `touch ~/.claude/gdd-nudge-dismissed` (Windows: equivalent). Ignore errors silently.
25
+ 2. Print exactly: `Nudge dismissed. Delete ~/.claude/gdd-nudge-dismissed to re-enable.`
26
+ 3. Exit with `## START COMPLETE` marker.
27
+
28
+ Do not proceed to any other step.
29
+
30
+ ## Step 1 - Detect UI root
31
+
32
+ Run the detector:
33
+
34
+ ```bash
35
+ node "${CLAUDE_PLUGIN_ROOT}/scripts/lib/detect-ui-root.cjs" "$(pwd)"
36
+ ```
37
+
38
+ Capture the JSON output. Branches:
39
+
40
+ - `kind: "backend-only"` → print the frontend-only diagnostic below, write nothing, exit with `## START COMPLETE`. The diagnostic copy is:
41
+ > `{{command_prefix}}start` is for frontend codebases. This repo looks backend-only (detected `<framework>`). The plugin can still help with design references and component libraries imported by your clients - but there is no UI surface here to scan. Exiting without creating `.design/`.
42
+ - `kind: null` (no package.json, no UI dir) → print a short "Nothing recognizable here - point me at a frontend repo and try again." and exit.
43
+ - Any other `kind` → proceed with `detected.path` as the scan root.
44
+
45
+ ## Step 2 - Run the 5-question interview
46
+
47
+ Read `./start-interview.md` for the exact question copy, defaults, and validation rules.
48
+
49
+ If `--skip-interview`, skip this step and use the defaults documented in that file.
50
+
51
+ Otherwise, ask the five questions in order using `AskUserQuestion`:
52
+
53
+ 1. Pain point (text, required, single-line cap 120 chars)
54
+ 2. Target area confirmation (detected path)
55
+ 3. Budget / latency preference (enum: fast / balanced / thorough)
56
+ 4. Framework + design-system confirmation (from detection)
57
+ 5. Figma / canvas workflow (enum: figma / canvas / neither / skip)
58
+
59
+ Any early exit at Q1 → abort with a one-line pointer to `{{command_prefix}}scan`.
60
+
61
+ Store the answers + detection result in `.design/.start-context.json`:
62
+
63
+ ```json
64
+ {
65
+ "schema_version": "1.0",
66
+ "detected": { "kind": "...", "path": "...", "framework": "...", "design_system": "...", "confidence": 0.85 },
67
+ "interview": { "pain": "...", "target_area": "...", "budget": "balanced", "framework_confirmed": true, "design_system_confirmed": true, "figma_workflow": "skip" },
68
+ "generated_at": "<ISO-8601>"
69
+ }
70
+ ```
71
+
72
+ `.design/` is created here for the first time. `.design/STATE.md` is NOT written.
73
+
74
+ ## Step 3 - Scan findings
75
+
76
+ Run the findings engine:
77
+
78
+ ```bash
79
+ node "${CLAUDE_PLUGIN_ROOT}/scripts/lib/start-findings-engine.cjs" \
80
+ --root "<detected.path>" \
81
+ --budget "<budget>" \
82
+ --pain "<pain_point>"
83
+ ```
84
+
85
+ Capture the JSON. The output carries at most three findings, each with stable IDs `F1`..`F3`, plus `bestFirstProofId` (may be null).
86
+
87
+ Append the engine output to `.design/.start-context.json` under a `scan` key.
88
+
89
+ ## Step 4 - Spawn the writer
90
+
91
+ Dispatch `Task` with:
92
+
93
+ - `subagent_type: design-start-writer`
94
+ - `description: "Write .design/START-REPORT.md"`
95
+ - `prompt:` a short instruction pointing the agent at `.design/.start-context.json` and asking it to emit the report per its Output contract. Include a reminder that it must produce exactly 7 H2 sections plus the JSON block, and must not write `STATE.md`.
96
+
97
+ Wait for the agent to complete. The agent writes `.design/START-REPORT.md`.
98
+
99
+ ## Step 5 - Print the handoff
100
+
101
+ Read the final line of `.design/START-REPORT.md` to capture the suggested command.
102
+
103
+ Print exactly (one line, no emoji):
104
+
105
+ ```
106
+ Report written to .design/START-REPORT.md. Next: run <suggested_command> to see the first proof.
107
+ ```
108
+
109
+ If `bestFirstProofId` was null, the suggested command is `{{command_prefix}}brief` (the default fallback).
110
+
111
+ Emit `## START COMPLETE` and exit.
112
+
113
+ ## Failure handling
114
+
115
+ Every error path exits with `## START COMPLETE` and a one-line pointer. Do not half-write files: if the writer agent fails, keep `.design/.start-context.json` and tell the user they can rerun. Do not delete `.design/` unless it was empty before the run.