@lifeaitools/rdc-skills 0.24.37 → 0.24.39

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 (191) hide show
  1. package/.claude/settings.json +15 -15
  2. package/.claude-plugin/marketplace.json +21 -21
  3. package/.claude-plugin/plugin.json +1371 -1371
  4. package/.github/workflows/publish.yml +34 -34
  5. package/.github/workflows/self-test.yml +58 -58
  6. package/CHANGELOG.md +310 -310
  7. package/LICENSE +21 -21
  8. package/MANIFEST.md +221 -221
  9. package/README.md +377 -377
  10. package/README.sandbox.md +3 -3
  11. package/assets/watcher/viewer.html +164 -164
  12. package/bin/rdc-skills-mcp.mjs +316 -316
  13. package/commands/build.md +183 -183
  14. package/commands/collab.md +180 -180
  15. package/commands/deploy.md +152 -152
  16. package/commands/design.md +31 -31
  17. package/commands/edit.md +28 -28
  18. package/commands/fixit.md +124 -124
  19. package/commands/handoff.md +173 -173
  20. package/commands/help.md +95 -95
  21. package/commands/overnight.md +220 -220
  22. package/commands/plan.md +158 -158
  23. package/commands/preplan.md +131 -131
  24. package/commands/prototype.md +145 -145
  25. package/commands/release.md +49 -49
  26. package/commands/report.md +99 -99
  27. package/commands/review.md +120 -120
  28. package/commands/self-test.md +113 -113
  29. package/commands/status.md +86 -86
  30. package/commands/watch.md +98 -98
  31. package/commands/workitems.md +137 -137
  32. package/git-sha.json +1 -1
  33. package/guides/agent-bootstrap.md +295 -295
  34. package/guides/agents/backend.md +104 -104
  35. package/guides/agents/content.md +94 -94
  36. package/guides/agents/cs2.md +56 -56
  37. package/guides/agents/data.md +87 -87
  38. package/guides/agents/design.md +77 -77
  39. package/guides/agents/frontend.md +92 -92
  40. package/guides/agents/infrastructure.md +81 -81
  41. package/guides/agents/setup.md +281 -281
  42. package/guides/agents/verify.md +151 -151
  43. package/guides/agents/viz.md +106 -106
  44. package/guides/backend.md +146 -146
  45. package/guides/content.md +147 -147
  46. package/guides/cs2.md +190 -190
  47. package/guides/data.md +123 -123
  48. package/guides/design.md +116 -116
  49. package/guides/engineering-behavior.md +43 -43
  50. package/guides/escalation-protocol.md +125 -125
  51. package/guides/frontend.md +151 -151
  52. package/guides/history-md-spec.md +297 -297
  53. package/guides/infrastructure.md +179 -179
  54. package/guides/lessons-learned-spec.md +153 -153
  55. package/guides/output-contract.md +108 -108
  56. package/guides/publish-md-spec.md +289 -289
  57. package/guides/rdc-skills-startup.md +30 -30
  58. package/guides/verify.md +11 -11
  59. package/hooks/check-cwd.js +31 -31
  60. package/hooks/check-rdc-environment.js +164 -164
  61. package/hooks/check-services.js +6 -6
  62. package/hooks/check-stale-work-items.js +19 -19
  63. package/hooks/foreground-process-gate.js +128 -128
  64. package/hooks/gate-watchdog-selfcheck.js +257 -257
  65. package/hooks/hook-logger.js +25 -25
  66. package/hooks/lib/run-evidence-gate.mjs +241 -241
  67. package/hooks/no-stop-open-epics.js +127 -127
  68. package/hooks/post-tool-batch-gate.js +203 -203
  69. package/hooks/post-work-check.js +21 -21
  70. package/hooks/postcompact-log.js +13 -13
  71. package/hooks/precompact-log.js +13 -13
  72. package/hooks/rate-limit-retry.js +46 -46
  73. package/hooks/rdc-invocation-marker.js +157 -157
  74. package/hooks/rdc-output-contract-gate.js +94 -94
  75. package/hooks/require-work-item-on-commit.js +294 -294
  76. package/hooks/restart-brief.js +19 -19
  77. package/hooks/run-hidden-hook.ps1 +47 -47
  78. package/hooks/task-completed-gate.js +274 -274
  79. package/hooks/work-item-exit-gate.js +944 -944
  80. package/lib/catalog.mjs +236 -236
  81. package/lib/cloud-rewrite.mjs +155 -155
  82. package/package.json +56 -56
  83. package/rules/work-items-rpc.md +520 -520
  84. package/scaffold/templates/HISTORY.md.template +39 -39
  85. package/scaffold/templates/PUBLISH.md.template +21 -21
  86. package/scaffold/templates/brochure-studio-default.html +70 -70
  87. package/scripts/acceptance.mjs +502 -502
  88. package/scripts/fixtures/guides/bad-guide.md +15 -15
  89. package/scripts/fixtures/guides-clean/good-guide.md +16 -16
  90. package/scripts/install-rdc-skills.js +1289 -1289
  91. package/scripts/install.ps1 +202 -202
  92. package/scripts/install.sh +132 -132
  93. package/scripts/lib/assertions.mjs +287 -287
  94. package/scripts/lib/manifest-schema.mjs +754 -754
  95. package/scripts/lib/runner.mjs +465 -465
  96. package/scripts/lib/sandbox.mjs +435 -435
  97. package/scripts/prepack.mjs +32 -32
  98. package/scripts/rdc-brochure.mjs +464 -464
  99. package/scripts/rdc-design-cli.mjs +134 -134
  100. package/scripts/rebuild-mcp.mjs +107 -107
  101. package/scripts/self-test.mjs +1460 -1460
  102. package/scripts/stamp-git-sha.mjs +29 -29
  103. package/scripts/test-guide-validator.mjs +196 -196
  104. package/scripts/test-rdc-hooks.mjs +145 -145
  105. package/scripts/uninstall.ps1 +77 -77
  106. package/scripts/uninstall.sh +69 -69
  107. package/scripts/update.ps1 +43 -43
  108. package/scripts/update.sh +43 -43
  109. package/scripts/validate-place-histories.js +461 -461
  110. package/scripts/validate-publish-manifests.js +424 -424
  111. package/scripts/watch-init.mjs +100 -100
  112. package/skills/brochure/SKILL.md +107 -107
  113. package/skills/build/SKILL.md +563 -554
  114. package/skills/channel-formatter/SKILL.md +533 -533
  115. package/skills/co-develop/SKILL.md +196 -196
  116. package/skills/collab/SKILL.md +239 -239
  117. package/skills/convert/SKILL.md +140 -140
  118. package/skills/deploy/SKILL.md +541 -541
  119. package/skills/design/SKILL.md +211 -211
  120. package/skills/design/reference/ownership.md +16 -16
  121. package/skills/design/reference/rampa.md +92 -92
  122. package/skills/design/reference/studio-model.md +153 -153
  123. package/skills/edit/SKILL.md +98 -98
  124. package/skills/fixit/SKILL.md +165 -165
  125. package/skills/fs-mcp/SKILL.md +148 -148
  126. package/skills/handoff/SKILL.md +236 -200
  127. package/skills/help/SKILL.md +143 -143
  128. package/skills/housekeeping/SKILL.md +189 -189
  129. package/skills/lifeai-brochure-author/SKILL.md +340 -340
  130. package/skills/overnight/SKILL.md +251 -251
  131. package/skills/plan/SKILL.md +345 -314
  132. package/skills/preplan/SKILL.md +90 -90
  133. package/skills/prototype/SKILL.md +150 -150
  134. package/skills/rdc-brochurify/SKILL.md +245 -245
  135. package/skills/rdc-extract-verifier-rules/SKILL.md +191 -191
  136. package/skills/release/SKILL.md +140 -140
  137. package/skills/report/SKILL.md +100 -100
  138. package/skills/review/SKILL.md +152 -152
  139. package/skills/rpms-filemap/SKILL.cloud.md +111 -111
  140. package/skills/rpms-filemap/SKILL.md +111 -111
  141. package/skills/self-test/SKILL.md +132 -132
  142. package/skills/status/SKILL.md +99 -99
  143. package/skills/terminal-config/SKILL.md +62 -62
  144. package/skills/tests/MATRIX.md +54 -54
  145. package/skills/tests/README.md +47 -47
  146. package/skills/tests/rdc-brochure.test.json +34 -34
  147. package/skills/tests/rdc-build.test.json +36 -36
  148. package/skills/tests/rdc-channel-formatter.test.json +45 -45
  149. package/skills/tests/rdc-co-develop.test.json +29 -29
  150. package/skills/tests/rdc-collab.test.json +29 -29
  151. package/skills/tests/rdc-convert.test.json +35 -35
  152. package/skills/tests/rdc-deploy.test.json +30 -30
  153. package/skills/tests/rdc-design.test.json +27 -27
  154. package/skills/tests/rdc-edit.test.json +29 -29
  155. package/skills/tests/rdc-fixit.test.json +36 -36
  156. package/skills/tests/rdc-fs-mcp.test.json +36 -36
  157. package/skills/tests/rdc-handoff.test.json +28 -28
  158. package/skills/tests/rdc-help.test.json +29 -29
  159. package/skills/tests/rdc-housekeeping.test.json +31 -31
  160. package/skills/tests/rdc-lifeai-brochure-author.test.json +35 -35
  161. package/skills/tests/rdc-overnight.test.json +37 -37
  162. package/skills/tests/rdc-plan.test.json +27 -27
  163. package/skills/tests/rdc-preplan.test.json +31 -31
  164. package/skills/tests/rdc-prototype.test.json +28 -28
  165. package/skills/tests/rdc-rdc-brochurify.test.json +23 -23
  166. package/skills/tests/rdc-rdc-extract-verifier-rules.test.json +34 -34
  167. package/skills/tests/rdc-release.test.json +29 -29
  168. package/skills/tests/rdc-report.test.json +28 -28
  169. package/skills/tests/rdc-review.test.json +29 -29
  170. package/skills/tests/rdc-rpms-filemap.test.json +28 -28
  171. package/skills/tests/rdc-self-test.test.json +24 -24
  172. package/skills/tests/rdc-status.test.json +29 -29
  173. package/skills/tests/rdc-terminal-config.test.json +29 -29
  174. package/skills/tests/rdc-watch.test.json +24 -24
  175. package/skills/tests/rdc-workitems.test.json +27 -27
  176. package/skills/watch/SKILL.md +97 -97
  177. package/skills/workitems/SKILL.md +151 -151
  178. package/tests/acceptance.test.mjs +59 -59
  179. package/tests/channel-formatter.contract.test.mjs +251 -251
  180. package/tests/curl-surface.test.mjs +289 -289
  181. package/tests/harness-gates.test.mjs +325 -325
  182. package/tests/help-surface.test.mjs +61 -61
  183. package/tests/install-rdc-skills.test.mjs +49 -49
  184. package/tests/manifest-contract-fields.test.mjs +78 -78
  185. package/tests/mcp.test.mjs +271 -271
  186. package/tests/require-work-item-on-commit.test.mjs +162 -162
  187. package/tests/run-evidence-gate.test.mjs +82 -82
  188. package/tests/skill-test-matrix.test.mjs +66 -66
  189. package/tests/validate-skills.js +27 -27
  190. package/tests/work-item-exit-gate-l2.test.mjs +368 -368
  191. package/tests/work-item-exit-gate-l3.test.mjs +197 -197
@@ -1,153 +1,153 @@
1
- # Studio Model for RDC Design
2
-
3
- Studio is the token authority and live website editor for LIFEAI brands. It is not a page builder. The design skill must work with Studio's real routes, APIs, token tables, and editor/debug model.
4
-
5
- ## Required Source Docs
6
-
7
- Read these before Studio design work:
8
-
9
- - `docs/systems/studio/ARCHITECTURE.md`
10
- - `apps/studio/CLAUDE.md`
11
- - `.claude/context/design-system-global.md`
12
-
13
- ## Runtime Locations
14
-
15
- - local Studio: `http://localhost:3011`
16
- - staging Studio: `https://staged.studio.regendevcorp.com`
17
- - production Studio: `https://studio.regendevcorp.com`
18
-
19
- ## Brand Pages
20
-
21
- - `/brands`
22
- - `/brands/new`
23
- - `/brands/[id]/colors`
24
- - `/brands/[id]/typography`
25
- - `/brands/[id]/spacing`
26
- - `/brands/[id]/diff`
27
- - `/brands/[id]/book`
28
- - `/brands/[id]/voice`
29
- - `/brands/[id]/assets`
30
- - `/brands/[id]/export`
31
- - `/brands/[id]/table-styles`
32
-
33
- ## Editor Routes
34
-
35
- - `/editor`
36
- - `/editor/local/[brandSlug]`
37
- - `/editor/local-test-target`
38
- - legacy `/editor/[brandSlug]` may redirect to local editor unless `?legacy=1`
39
-
40
- Read local debug docs:
41
-
42
- - `docs/systems/studio/local-debug-agent.md`
43
-
44
- Clauth relay route families:
45
-
46
- - `/studio/debug/*`
47
- - `/studio/claude/*`
48
-
49
- ## Native Local Debug Model
50
-
51
- Studio live editing must use the RDC-owned local debug system, not an external live-edit runtime:
52
-
53
- 1. Studio starts a local session with `POST /studio/debug/start`.
54
- 2. Studio embeds the returned local `devUrl` with debug query params.
55
- 3. `/api/editor/local-debug` injects Studio's own `local-debug-browser.js` picker.
56
- 4. Browser/user events go to `/studio/debug/:sessionId/events`.
57
- 5. Claude Code polls `/studio/claude/:sessionId/poll` with `scripts/studio-debug-poll.mjs`.
58
- 6. Claude edits source files directly and replies to `/studio/claude/:sessionId/reply`.
59
- 7. HMR updates the iframe.
60
-
61
- The disposable proof target is:
62
-
63
- - `/editor/local/test`
64
- - `apps/studio/src/app/editor/local-test-target/page.tsx`
65
-
66
- Direct edits must make exactly one source edit unless impossible. Variant edits should return alternatives without editing unless explicitly instructed to apply one. Reference replacement requires an explicit reference. Notes must not edit source.
67
-
68
- ## Token APIs
69
-
70
- - `GET /api/public/tokens/[slug]` returns legacy public token payload and CSS variables.
71
- - `GET /api/v2/tokens/[slug]` returns DTCG/M3 token JSON.
72
- - `GET /api/v2/tokens/[slug]/css` returns shadcn-compatible CSS vars.
73
-
74
- Palette APIs currently start here:
75
-
76
- - `apps/studio/src/app/api/palettes/route.ts`
77
- - `apps/studio/src/app/api/palettes/apply/route.ts`
78
-
79
- ## Canonical Tables
80
-
81
- Current token and theme work should prefer v2 where available:
82
-
83
- - `global_design_tokens_v2`
84
- - `brand_token_overrides_v2`
85
- - `brand_semantic_tokens`
86
- - `brand_components`
87
- - `brand_patterns`
88
- - `token_inheritance_audit`
89
-
90
- Legacy/current website token tables:
91
-
92
- - `brand_token_overrides`
93
- - `brand_font_assignments`
94
- - `brand_fonts`
95
-
96
- Legacy read-only or migration tables:
97
-
98
- - `global_design_tokens`
99
- - `brand_colors`
100
- - `brand_typography`
101
- - `brand_spacing`
102
-
103
- Docs/narrative:
104
-
105
- - `brand_design_docs`
106
-
107
- Registry/hierarchy:
108
-
109
- - `brand_entities`
110
- - `org_entities`
111
-
112
- ## Key Files
113
-
114
- - `apps/studio/src/contexts/BrandStudioContext.tsx`
115
- - `apps/studio/src/lib/token-resolver.ts`
116
- - `apps/studio/src/lib/token-resolver-v2.ts`
117
- - `apps/studio/src/lib/token-export.ts`
118
- - `packages/design-tokens/src/types.ts`
119
- - `packages/ui/src/components/WebsiteLayout.tsx`
120
- - `packages/ui/src/styles/website-base.css`
121
-
122
- ## BrandStudioContext
123
-
124
- Child pages under `/brands/[id]/*` should use `useBrandStudio()` instead of re-fetching tokens. It provides:
125
-
126
- - `brand`
127
- - `resolved`
128
- - `setResolved`
129
- - `globals`
130
- - `overrides`
131
- - `loaded`
132
-
133
- ## Token Rules
134
-
135
- - Use Studio tokens for every production design decision.
136
- - Never invent a brand slug. Query `brand_entities`.
137
- - Never modify locked governance tokens without an explicit governance decision.
138
- - Missing token protocol: create a work item, use closest existing token temporarily, and mark the gap.
139
- - Production code should use `var(--color-*)` or resolved Studio token output.
140
-
141
- ## Palette Designer Boundary
142
-
143
- The forked Palette Designer is a separate tool. Studio should launch it only when installed/enabled/healthy. It should load and save through Palette Library APIs, then Studio should reflect saved palettes.
144
-
145
- Do not rebuild Palette Designer inside the colors page in the first pass.
146
-
147
- ## Deprecated Routes
148
-
149
- Do not extend:
150
-
151
- - `/api/editor/render`
152
- - `/api/layout/scan` unless maintaining legacy scanner behavior
153
- - `/api/layout/sync`
1
+ # Studio Model for RDC Design
2
+
3
+ Studio is the token authority and live website editor for LIFEAI brands. It is not a page builder. The design skill must work with Studio's real routes, APIs, token tables, and editor/debug model.
4
+
5
+ ## Required Source Docs
6
+
7
+ Read these before Studio design work:
8
+
9
+ - `docs/systems/studio/ARCHITECTURE.md`
10
+ - `apps/studio/CLAUDE.md`
11
+ - `.claude/context/design-system-global.md`
12
+
13
+ ## Runtime Locations
14
+
15
+ - local Studio: `http://localhost:3011`
16
+ - staging Studio: `https://staged.studio.regendevcorp.com`
17
+ - production Studio: `https://studio.regendevcorp.com`
18
+
19
+ ## Brand Pages
20
+
21
+ - `/brands`
22
+ - `/brands/new`
23
+ - `/brands/[id]/colors`
24
+ - `/brands/[id]/typography`
25
+ - `/brands/[id]/spacing`
26
+ - `/brands/[id]/diff`
27
+ - `/brands/[id]/book`
28
+ - `/brands/[id]/voice`
29
+ - `/brands/[id]/assets`
30
+ - `/brands/[id]/export`
31
+ - `/brands/[id]/table-styles`
32
+
33
+ ## Editor Routes
34
+
35
+ - `/editor`
36
+ - `/editor/local/[brandSlug]`
37
+ - `/editor/local-test-target`
38
+ - legacy `/editor/[brandSlug]` may redirect to local editor unless `?legacy=1`
39
+
40
+ Read local debug docs:
41
+
42
+ - `docs/systems/studio/local-debug-agent.md`
43
+
44
+ Clauth relay route families:
45
+
46
+ - `/studio/debug/*`
47
+ - `/studio/claude/*`
48
+
49
+ ## Native Local Debug Model
50
+
51
+ Studio live editing must use the RDC-owned local debug system, not an external live-edit runtime:
52
+
53
+ 1. Studio starts a local session with `POST /studio/debug/start`.
54
+ 2. Studio embeds the returned local `devUrl` with debug query params.
55
+ 3. `/api/editor/local-debug` injects Studio's own `local-debug-browser.js` picker.
56
+ 4. Browser/user events go to `/studio/debug/:sessionId/events`.
57
+ 5. Claude Code polls `/studio/claude/:sessionId/poll` with `scripts/studio-debug-poll.mjs`.
58
+ 6. Claude edits source files directly and replies to `/studio/claude/:sessionId/reply`.
59
+ 7. HMR updates the iframe.
60
+
61
+ The disposable proof target is:
62
+
63
+ - `/editor/local/test`
64
+ - `apps/studio/src/app/editor/local-test-target/page.tsx`
65
+
66
+ Direct edits must make exactly one source edit unless impossible. Variant edits should return alternatives without editing unless explicitly instructed to apply one. Reference replacement requires an explicit reference. Notes must not edit source.
67
+
68
+ ## Token APIs
69
+
70
+ - `GET /api/public/tokens/[slug]` returns legacy public token payload and CSS variables.
71
+ - `GET /api/v2/tokens/[slug]` returns DTCG/M3 token JSON.
72
+ - `GET /api/v2/tokens/[slug]/css` returns shadcn-compatible CSS vars.
73
+
74
+ Palette APIs currently start here:
75
+
76
+ - `apps/studio/src/app/api/palettes/route.ts`
77
+ - `apps/studio/src/app/api/palettes/apply/route.ts`
78
+
79
+ ## Canonical Tables
80
+
81
+ Current token and theme work should prefer v2 where available:
82
+
83
+ - `global_design_tokens_v2`
84
+ - `brand_token_overrides_v2`
85
+ - `brand_semantic_tokens`
86
+ - `brand_components`
87
+ - `brand_patterns`
88
+ - `token_inheritance_audit`
89
+
90
+ Legacy/current website token tables:
91
+
92
+ - `brand_token_overrides`
93
+ - `brand_font_assignments`
94
+ - `brand_fonts`
95
+
96
+ Legacy read-only or migration tables:
97
+
98
+ - `global_design_tokens`
99
+ - `brand_colors`
100
+ - `brand_typography`
101
+ - `brand_spacing`
102
+
103
+ Docs/narrative:
104
+
105
+ - `brand_design_docs`
106
+
107
+ Registry/hierarchy:
108
+
109
+ - `brand_entities`
110
+ - `org_entities`
111
+
112
+ ## Key Files
113
+
114
+ - `apps/studio/src/contexts/BrandStudioContext.tsx`
115
+ - `apps/studio/src/lib/token-resolver.ts`
116
+ - `apps/studio/src/lib/token-resolver-v2.ts`
117
+ - `apps/studio/src/lib/token-export.ts`
118
+ - `packages/design-tokens/src/types.ts`
119
+ - `packages/ui/src/components/WebsiteLayout.tsx`
120
+ - `packages/ui/src/styles/website-base.css`
121
+
122
+ ## BrandStudioContext
123
+
124
+ Child pages under `/brands/[id]/*` should use `useBrandStudio()` instead of re-fetching tokens. It provides:
125
+
126
+ - `brand`
127
+ - `resolved`
128
+ - `setResolved`
129
+ - `globals`
130
+ - `overrides`
131
+ - `loaded`
132
+
133
+ ## Token Rules
134
+
135
+ - Use Studio tokens for every production design decision.
136
+ - Never invent a brand slug. Query `brand_entities`.
137
+ - Never modify locked governance tokens without an explicit governance decision.
138
+ - Missing token protocol: create a work item, use closest existing token temporarily, and mark the gap.
139
+ - Production code should use `var(--color-*)` or resolved Studio token output.
140
+
141
+ ## Palette Designer Boundary
142
+
143
+ The forked Palette Designer is a separate tool. Studio should launch it only when installed/enabled/healthy. It should load and save through Palette Library APIs, then Studio should reflect saved palettes.
144
+
145
+ Do not rebuild Palette Designer inside the colors page in the first pass.
146
+
147
+ ## Deprecated Routes
148
+
149
+ Do not extend:
150
+
151
+ - `/api/editor/render`
152
+ - `/api/layout/scan` unless maintaining legacy scanner behavior
153
+ - `/api/layout/sync`
@@ -1,98 +1,98 @@
1
- ---
2
- name: rdc:edit
3
- description: "Usage `rdc:edit <site|brand|route|file>` — open the local website editor host for a target site, brand, route, or file. Resolves the target, launches or reuses the local editor host on port 3015, and opens the target in the browser when not under `RDC_TEST=1`."
4
- ---
5
-
6
- > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
7
- > Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
8
- > One checklist upfront, updated in place, shown again at end with a 1-line verdict.
9
-
10
- > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`).
11
-
12
- > **Sandbox contract:** This skill honors `RDC_TEST=1`. Under test, do not steal focus or rely on foreground-only browser automation; report the resolved editor URL instead.
13
-
14
-
15
- # rdc:edit — Local Website Editor Launcher
16
-
17
- ## When to Use
18
- - The user wants to open a site, brand, route, or file in the local editor app
19
- - The user says "open this in the editor" or asks for the editor-host workflow
20
- - The target should be loaded in `@regen/editor-host` rather than Studio
21
-
22
- ## Arguments
23
- - `rdc:edit <site|brand|route|file>` — resolve the target and open it in the local editor host
24
-
25
- ## Procedure
26
-
27
- ### 1. Read the local editor contract
28
- - Read `apps/editor/CLAUDE.md` before launching anything.
29
- - If the target is Studio-specific, prefer `rdc:design edit <target>` instead.
30
-
31
- ### 2. Resolve the target
32
- - For known LIFEAI brand targets, map to the obvious brand/app pair first.
33
- - `prtrust.fund` and `dev.prtrust.fund` resolve to `brandSlug=prt` and `appSlug=prt`.
34
- - `test`, `studio_test`, and `studio-test` resolve to `brandSlug=test` and `appSlug=studio_test`.
35
- - If the target is a local file or route and the brand/app is unclear, ask one concise question.
36
-
37
- Resolve the **target dev server** (package + port) so the preview iframe has
38
- something live to load. Read the brand app's `package.json` `name` and its
39
- `dev` script port — never hard-code a stale port:
40
-
41
- | Target | App dir | Package (`name`) | Dev port | `targetUrl` |
42
- |--------|---------|------------------|----------|-------------|
43
- | `prt` / `prtrust.fund` | `apps/prt` | `@regen/prt-portal` | `3006` | `http://localhost:3006` |
44
- | `test` / `studio_test` | (bundled) | — (editor host serves it) | `3015` | auto (`/editor/local-test-target`) |
45
-
46
- For any other brand, derive the package name and port by reading
47
- `apps/<app>/package.json` (`name` field and the `--port` in the `dev` script).
48
- `brandSlug=test` needs no target server — the editor host serves the fixture
49
- on its own origin.
50
-
51
- ### 3. Start or reuse BOTH servers (edit starts everything)
52
- `rdc:edit` must bring up everything the preview needs — the editor host AND the
53
- target brand's dev server. Start-or-reuse each: probe the port first, only
54
- launch if it is dead.
55
-
56
- **3a. Editor host (`http://localhost:3015`)**
57
- - Probe: `curl -s -o /dev/null -w "%{http_code}" http://localhost:3015/` — any
58
- non-`000` means it is already up; reuse it.
59
- - Launch only if down (background, do not block the session):
60
- ```powershell
61
- pnpm --filter @regen/editor-host dev
62
- ```
63
-
64
- **3b. Target brand dev server (skip for `brandSlug=test`)**
65
- - Probe the resolved dev port (e.g. `http://localhost:3006/`). Non-`000` =
66
- already running; reuse it. `EADDRINUSE` on launch also means reuse — not an error.
67
- - Launch only if down (background), then health-wait on the port before opening:
68
- ```powershell
69
- pnpm --filter <package> dev
70
- ```
71
- Bounded health-wait only (no `for`/`seq`/`sleep` polling loops):
72
- ```bash
73
- until curl -s -o /dev/null http://localhost:<port>/; do sleep 2; done
74
- ```
75
- - Open the editor page for the resolved target once BOTH report a live code:
76
- ```txt
77
- http://localhost:3015/editor/local/<brandSlug>?appSlug=<appSlug>&targetUrl=<targetUrl>
78
- ```
79
-
80
- ### 4. Open the page
81
- - Normal use: open the URL in the browser and confirm the editor loaded.
82
- Open via PowerShell `Start-Process`, NOT `cmd start` — `cmd` treats the `&`
83
- between query params as a command separator and truncates the URL:
84
- ```powershell
85
- Start-Process 'http://localhost:3015/editor/local/<brandSlug>?appSlug=<appSlug>&targetUrl=<targetUrl>'
86
- ```
87
- - `RDC_TEST=1`: do not force a foreground browser action; report the exact editor URL and whether the target was resolved.
88
-
89
- ### 5. Report the result
90
- - Return a concise line with:
91
- - the resolved target
92
- - the editor URL
93
- - whether the page was opened or only prepared in test mode
94
-
95
- ## Guardrails
96
- - Do not turn this into a full design audit.
97
- - Do not start Studio unless the target actually belongs there.
98
- - Do not do broad discovery when one target mapping is enough.
1
+ ---
2
+ name: rdc:edit
3
+ description: "Usage `rdc:edit <site|brand|route|file>` — open the local website editor host for a target site, brand, route, or file. Resolves the target, launches or reuses the local editor host on port 3015, and opens the target in the browser when not under `RDC_TEST=1`."
4
+ ---
5
+
6
+ > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
7
+ > Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
8
+ > One checklist upfront, updated in place, shown again at end with a 1-line verdict.
9
+
10
+ > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md`).
11
+
12
+ > **Sandbox contract:** This skill honors `RDC_TEST=1`. Under test, do not steal focus or rely on foreground-only browser automation; report the resolved editor URL instead.
13
+
14
+
15
+ # rdc:edit — Local Website Editor Launcher
16
+
17
+ ## When to Use
18
+ - The user wants to open a site, brand, route, or file in the local editor app
19
+ - The user says "open this in the editor" or asks for the editor-host workflow
20
+ - The target should be loaded in `@regen/editor-host` rather than Studio
21
+
22
+ ## Arguments
23
+ - `rdc:edit <site|brand|route|file>` — resolve the target and open it in the local editor host
24
+
25
+ ## Procedure
26
+
27
+ ### 1. Read the local editor contract
28
+ - Read `apps/editor/CLAUDE.md` before launching anything.
29
+ - If the target is Studio-specific, prefer `rdc:design edit <target>` instead.
30
+
31
+ ### 2. Resolve the target
32
+ - For known LIFEAI brand targets, map to the obvious brand/app pair first.
33
+ - `prtrust.fund` and `dev.prtrust.fund` resolve to `brandSlug=prt` and `appSlug=prt`.
34
+ - `test`, `studio_test`, and `studio-test` resolve to `brandSlug=test` and `appSlug=studio_test`.
35
+ - If the target is a local file or route and the brand/app is unclear, ask one concise question.
36
+
37
+ Resolve the **target dev server** (package + port) so the preview iframe has
38
+ something live to load. Read the brand app's `package.json` `name` and its
39
+ `dev` script port — never hard-code a stale port:
40
+
41
+ | Target | App dir | Package (`name`) | Dev port | `targetUrl` |
42
+ |--------|---------|------------------|----------|-------------|
43
+ | `prt` / `prtrust.fund` | `apps/prt` | `@regen/prt-portal` | `3006` | `http://localhost:3006` |
44
+ | `test` / `studio_test` | (bundled) | — (editor host serves it) | `3015` | auto (`/editor/local-test-target`) |
45
+
46
+ For any other brand, derive the package name and port by reading
47
+ `apps/<app>/package.json` (`name` field and the `--port` in the `dev` script).
48
+ `brandSlug=test` needs no target server — the editor host serves the fixture
49
+ on its own origin.
50
+
51
+ ### 3. Start or reuse BOTH servers (edit starts everything)
52
+ `rdc:edit` must bring up everything the preview needs — the editor host AND the
53
+ target brand's dev server. Start-or-reuse each: probe the port first, only
54
+ launch if it is dead.
55
+
56
+ **3a. Editor host (`http://localhost:3015`)**
57
+ - Probe: `curl -s -o /dev/null -w "%{http_code}" http://localhost:3015/` — any
58
+ non-`000` means it is already up; reuse it.
59
+ - Launch only if down (background, do not block the session):
60
+ ```powershell
61
+ pnpm --filter @regen/editor-host dev
62
+ ```
63
+
64
+ **3b. Target brand dev server (skip for `brandSlug=test`)**
65
+ - Probe the resolved dev port (e.g. `http://localhost:3006/`). Non-`000` =
66
+ already running; reuse it. `EADDRINUSE` on launch also means reuse — not an error.
67
+ - Launch only if down (background), then health-wait on the port before opening:
68
+ ```powershell
69
+ pnpm --filter <package> dev
70
+ ```
71
+ Bounded health-wait only (no `for`/`seq`/`sleep` polling loops):
72
+ ```bash
73
+ until curl -s -o /dev/null http://localhost:<port>/; do sleep 2; done
74
+ ```
75
+ - Open the editor page for the resolved target once BOTH report a live code:
76
+ ```txt
77
+ http://localhost:3015/editor/local/<brandSlug>?appSlug=<appSlug>&targetUrl=<targetUrl>
78
+ ```
79
+
80
+ ### 4. Open the page
81
+ - Normal use: open the URL in the browser and confirm the editor loaded.
82
+ Open via PowerShell `Start-Process`, NOT `cmd start` — `cmd` treats the `&`
83
+ between query params as a command separator and truncates the URL:
84
+ ```powershell
85
+ Start-Process 'http://localhost:3015/editor/local/<brandSlug>?appSlug=<appSlug>&targetUrl=<targetUrl>'
86
+ ```
87
+ - `RDC_TEST=1`: do not force a foreground browser action; report the exact editor URL and whether the target was resolved.
88
+
89
+ ### 5. Report the result
90
+ - Return a concise line with:
91
+ - the resolved target
92
+ - the editor URL
93
+ - whether the page was opened or only prepared in test mode
94
+
95
+ ## Guardrails
96
+ - Do not turn this into a full design audit.
97
+ - Do not start Studio unless the target actually belongs there.
98
+ - Do not do broad discovery when one target mapping is enough.