@lifeaitools/rdc-skills 0.24.38 → 0.24.41

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 (196) 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 +376 -375
  10. package/README.sandbox.md +3 -3
  11. package/RELEASE.md +42 -0
  12. package/assets/watcher/viewer.html +164 -164
  13. package/bin/rdc-skills-mcp.mjs +316 -316
  14. package/commands/build.md +183 -183
  15. package/commands/collab.md +180 -180
  16. package/commands/deploy.md +152 -152
  17. package/commands/design.md +31 -31
  18. package/commands/edit.md +28 -28
  19. package/commands/fixit.md +124 -124
  20. package/commands/handoff.md +173 -173
  21. package/commands/help.md +95 -95
  22. package/commands/overnight.md +220 -220
  23. package/commands/plan.md +158 -158
  24. package/commands/preplan.md +131 -131
  25. package/commands/prototype.md +145 -145
  26. package/commands/release.md +49 -49
  27. package/commands/report.md +99 -99
  28. package/commands/review.md +120 -120
  29. package/commands/self-test.md +113 -113
  30. package/commands/status.md +86 -86
  31. package/commands/watch.md +98 -98
  32. package/commands/workitems.md +137 -137
  33. package/git-sha.json +1 -1
  34. package/guides/agent-bootstrap.md +295 -295
  35. package/guides/agents/backend.md +104 -104
  36. package/guides/agents/content.md +94 -94
  37. package/guides/agents/cs2.md +56 -56
  38. package/guides/agents/data.md +87 -87
  39. package/guides/agents/design.md +77 -77
  40. package/guides/agents/frontend.md +92 -92
  41. package/guides/agents/infrastructure.md +81 -81
  42. package/guides/agents/setup.md +281 -281
  43. package/guides/agents/verify.md +151 -151
  44. package/guides/agents/viz.md +106 -106
  45. package/guides/backend.md +146 -146
  46. package/guides/content.md +147 -147
  47. package/guides/cs2.md +190 -190
  48. package/guides/data.md +123 -123
  49. package/guides/design.md +116 -116
  50. package/guides/engineering-behavior.md +43 -43
  51. package/guides/escalation-protocol.md +125 -125
  52. package/guides/frontend.md +151 -151
  53. package/guides/history-md-spec.md +297 -297
  54. package/guides/infrastructure.md +179 -179
  55. package/guides/lessons-learned-spec.md +151 -145
  56. package/guides/output-contract.md +108 -108
  57. package/guides/publish-md-spec.md +289 -289
  58. package/guides/rdc-skills-startup.md +30 -30
  59. package/guides/verify.md +11 -11
  60. package/hooks/check-cwd.js +31 -31
  61. package/hooks/check-rdc-environment.js +164 -164
  62. package/hooks/check-services.js +6 -6
  63. package/hooks/check-stale-work-items.js +19 -19
  64. package/hooks/foreground-process-gate.js +128 -128
  65. package/hooks/gate-watchdog-selfcheck.js +257 -257
  66. package/hooks/hook-logger.js +25 -25
  67. package/hooks/lib/run-evidence-gate.mjs +241 -241
  68. package/hooks/no-stop-open-epics.js +127 -127
  69. package/hooks/post-tool-batch-gate.js +203 -203
  70. package/hooks/post-work-check.js +21 -21
  71. package/hooks/postcompact-log.js +13 -13
  72. package/hooks/precompact-log.js +13 -13
  73. package/hooks/rate-limit-retry.js +46 -46
  74. package/hooks/rdc-invocation-marker.js +157 -157
  75. package/hooks/rdc-output-contract-gate.js +94 -94
  76. package/hooks/require-work-item-on-commit.js +294 -294
  77. package/hooks/restart-brief.js +19 -19
  78. package/hooks/run-hidden-hook.ps1 +47 -47
  79. package/hooks/task-completed-gate.js +274 -274
  80. package/hooks/work-item-exit-gate.js +944 -944
  81. package/lib/catalog.mjs +236 -236
  82. package/lib/cloud-rewrite.mjs +155 -155
  83. package/package.json +57 -56
  84. package/rules/work-items-rpc.md +520 -520
  85. package/scaffold/templates/HISTORY.md.template +39 -39
  86. package/scaffold/templates/PUBLISH.md.template +21 -21
  87. package/scaffold/templates/brochure-studio-default.html +70 -70
  88. package/scripts/acceptance.mjs +502 -502
  89. package/scripts/fixtures/guides/bad-guide.md +15 -15
  90. package/scripts/fixtures/guides-clean/good-guide.md +16 -16
  91. package/scripts/install-rdc-skills.js +1289 -1289
  92. package/scripts/install.ps1 +202 -202
  93. package/scripts/install.sh +132 -132
  94. package/scripts/lib/assertions.mjs +287 -287
  95. package/scripts/lib/manifest-schema.mjs +754 -754
  96. package/scripts/lib/runner.mjs +465 -465
  97. package/scripts/lib/sandbox.mjs +435 -435
  98. package/scripts/prepack.mjs +32 -32
  99. package/scripts/rdc-brochure.mjs +482 -464
  100. package/scripts/rdc-design-cli.mjs +134 -134
  101. package/scripts/rebuild-mcp.mjs +107 -107
  102. package/scripts/self-test.mjs +1460 -1460
  103. package/scripts/stamp-git-sha.mjs +29 -29
  104. package/scripts/test-guide-validator.mjs +196 -196
  105. package/scripts/test-rdc-hooks.mjs +145 -145
  106. package/scripts/uninstall.ps1 +77 -77
  107. package/scripts/uninstall.sh +69 -69
  108. package/scripts/update.ps1 +43 -43
  109. package/scripts/update.sh +43 -43
  110. package/scripts/validate-place-histories.js +461 -461
  111. package/scripts/validate-publish-manifests.js +424 -424
  112. package/scripts/watch-init.mjs +100 -100
  113. package/skills/brochure/SKILL.md +107 -107
  114. package/skills/build/SKILL.md +563 -563
  115. package/skills/channel-formatter/SKILL.md +533 -533
  116. package/skills/co-develop/SKILL.md +196 -196
  117. package/skills/collab/SKILL.md +239 -239
  118. package/skills/convert/SKILL.md +140 -140
  119. package/skills/deploy/SKILL.md +541 -541
  120. package/skills/design/SKILL.md +211 -211
  121. package/skills/design/reference/ownership.md +16 -16
  122. package/skills/design/reference/rampa.md +92 -92
  123. package/skills/design/reference/studio-model.md +153 -153
  124. package/skills/edit/SKILL.md +98 -98
  125. package/skills/fixit/SKILL.md +165 -165
  126. package/skills/fs-mcp/SKILL.md +148 -148
  127. package/skills/handoff/SKILL.md +236 -200
  128. package/skills/help/SKILL.md +143 -143
  129. package/skills/housekeeping/SKILL.md +219 -160
  130. package/skills/lifeai-brochure-author/SKILL.md +340 -340
  131. package/skills/overnight/SKILL.md +251 -251
  132. package/skills/plan/SKILL.md +345 -345
  133. package/skills/preplan/SKILL.md +90 -90
  134. package/skills/prototype/SKILL.md +150 -150
  135. package/skills/rdc-brochurify/SKILL.md +245 -245
  136. package/skills/rdc-extract-verifier-rules/SKILL.md +191 -191
  137. package/skills/release/SKILL.md +140 -140
  138. package/skills/report/SKILL.md +100 -100
  139. package/skills/review/SKILL.md +152 -152
  140. package/skills/rpms-filemap/SKILL.cloud.md +111 -111
  141. package/skills/rpms-filemap/SKILL.md +111 -111
  142. package/skills/self-test/SKILL.md +132 -132
  143. package/skills/status/SKILL.md +99 -99
  144. package/skills/terminal-config/SKILL.md +62 -62
  145. package/skills/tests/MATRIX.md +54 -54
  146. package/skills/tests/README.md +47 -47
  147. package/skills/tests/rdc-brochure.test.json +34 -34
  148. package/skills/tests/rdc-build.test.json +36 -36
  149. package/skills/tests/rdc-channel-formatter.test.json +45 -45
  150. package/skills/tests/rdc-co-develop.test.json +29 -29
  151. package/skills/tests/rdc-collab.test.json +29 -29
  152. package/skills/tests/rdc-convert.test.json +35 -35
  153. package/skills/tests/rdc-deploy.test.json +30 -30
  154. package/skills/tests/rdc-design.test.json +27 -27
  155. package/skills/tests/rdc-edit.test.json +29 -29
  156. package/skills/tests/rdc-fixit.test.json +36 -36
  157. package/skills/tests/rdc-fs-mcp.test.json +36 -36
  158. package/skills/tests/rdc-handoff.test.json +28 -28
  159. package/skills/tests/rdc-help.test.json +29 -29
  160. package/skills/tests/rdc-housekeeping.test.json +32 -28
  161. package/skills/tests/rdc-lifeai-brochure-author.test.json +35 -35
  162. package/skills/tests/rdc-overnight.test.json +37 -37
  163. package/skills/tests/rdc-plan.test.json +27 -27
  164. package/skills/tests/rdc-preplan.test.json +31 -31
  165. package/skills/tests/rdc-prototype.test.json +28 -28
  166. package/skills/tests/rdc-rdc-brochurify.test.json +23 -23
  167. package/skills/tests/rdc-rdc-extract-verifier-rules.test.json +34 -34
  168. package/skills/tests/rdc-release.test.json +29 -29
  169. package/skills/tests/rdc-report.test.json +28 -28
  170. package/skills/tests/rdc-review.test.json +29 -29
  171. package/skills/tests/rdc-rpms-filemap.test.json +28 -28
  172. package/skills/tests/rdc-self-test.test.json +24 -24
  173. package/skills/tests/rdc-status.test.json +29 -29
  174. package/skills/tests/rdc-terminal-config.test.json +29 -29
  175. package/skills/tests/rdc-watch.test.json +24 -24
  176. package/skills/tests/rdc-workitems.test.json +27 -27
  177. package/skills/watch/SKILL.md +97 -97
  178. package/skills/workitems/SKILL.md +151 -151
  179. package/tests/acceptance.test.mjs +59 -59
  180. package/tests/channel-formatter.contract.test.mjs +251 -251
  181. package/tests/curl-surface.test.mjs +289 -289
  182. package/tests/harness-gates.test.mjs +325 -325
  183. package/tests/help-surface.test.mjs +61 -61
  184. package/tests/housekeeping-lessons-triage.test.mjs +49 -0
  185. package/tests/install-rdc-skills.test.mjs +49 -49
  186. package/tests/lessons-pipeline-contract.test.mjs +26 -0
  187. package/tests/manifest-contract-fields.test.mjs +78 -78
  188. package/tests/mcp.test.mjs +271 -271
  189. package/tests/rdc-brochure.test.mjs +125 -0
  190. package/tests/release-contract.test.mjs +16 -0
  191. package/tests/require-work-item-on-commit.test.mjs +162 -162
  192. package/tests/run-evidence-gate.test.mjs +82 -82
  193. package/tests/skill-test-matrix.test.mjs +66 -66
  194. package/tests/validate-skills.js +27 -27
  195. package/tests/work-item-exit-gate-l2.test.mjs +368 -368
  196. package/tests/work-item-exit-gate-l3.test.mjs +197 -197
@@ -1,143 +1,143 @@
1
- ---
2
- name: rdc:help
3
- description: "Usage `rdc:help` — Show all MCP skills with usage, requirements, slash forms, and codeflow status. Reads `.claude-plugin/plugin.json` skills_meta (single source of truth). Call when unsure which skill to use or what args it takes."
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
-
9
- # rdc:help — Skill Reference (manifest-driven)
10
-
11
- > **⚠️ HARD OUTPUT RULE:** Read the plugin manifest, render the table, exit.
12
- > No preamble. No follow-up question. No summary.
13
-
14
- ## Procedure
15
-
16
- 1. Resolve the plugin manifest path. Try in order, take the first that exists:
17
- - `{PLUGIN_ROOT}/.claude-plugin/plugin.json` ← preferred when running from the published plugin
18
- - `C:/Dev/rdc-skills/.claude-plugin/plugin.json` ← source-checkout fallback
19
- - `~/.claude/plugins/cache/rdc-skills/rdc-skills/latest/.claude-plugin/plugin.json` ← installed cache
20
- 2. Read it. Parse JSON. Read `skills_meta`. Accept either the current object map shape (`skills_meta.<name>`) or an older array shape (`skills_meta[]`); normalize to entries before rendering.
21
- 3. Group entries by `category` in this order: `planning, build, deploy, release, dev-loop, reporting, tooling, infra`.
22
- 4. For each entry render one row: `{slash} — {usage} — needs: {requires.join(',')} — cf: {codeflow_required ? 'yes' : 'no'}`.
23
- 5. Print a Decision Tree at the end that maps natural-language phrases to skills, derived from each entry's `triggers[]`.
24
- 6. Print the Direct MCP / curl Access block exactly as shown in the required output format. Do not summarize, compress, relabel, or omit the curl examples. This block is the public direct-caller contract for MCP/API/curl users.
25
- 7. Hard rules section at the bottom (see below — verbatim).
26
-
27
- ## Required output format
28
-
29
- ```
30
- RDC SKILLS — manifest: .claude-plugin/plugin.json @ v{version}
31
-
32
- ## planning
33
- /rdc:preplan <topic> needs: codeflow cf: yes
34
- /rdc:plan <topic> needs: supabase,clauth,codeflow,work-items-rpc cf: yes
35
- /rdc:handoff [--from-prototype <id>] needs: supabase,clauth,codeflow,work-items-rpc,git cf: yes
36
-
37
- ## build
38
- /rdc:build <epic-id> needs: supabase,clauth,codeflow,agent-dispatch,work-items-rpc,git cf: yes
39
- /rdc:design <topic> needs: supabase,clauth,codeflow,git cf: yes
40
- /rdc:prototype <desc> needs: supabase,clauth,codeflow cf: yes
41
- /rdc:overnight [scope] needs: supabase,clauth,codeflow,agent-dispatch,work-items-rpc,git cf: yes
42
- /rdc:review [--unattended] needs: supabase,clauth,codeflow,agent-dispatch,git cf: yes
43
-
44
- ## deploy
45
- /rdc:deploy <slug> [new|diagnose|audit] [--fix] needs: clauth,coolify,pm2,supabase,codeflow cf: yes
46
-
47
- ## release
48
- /rdc:release <repo> [version|--patch|--minor|--major|--dry-run] needs: clauth,git,npm,coolify cf: no
49
- ⚠ Production promotion requires explicit user go-ahead.
50
-
51
- ## dev-loop
52
- /rdc:fixit <description> needs: supabase,clauth,codeflow,agent-dispatch,work-items-rpc,git cf: yes
53
- constraint: < 5 files AND < 30 min — otherwise use /rdc:plan
54
- /rdc:collab --session <id> needs: clauth,git cf: yes
55
- /rdc:co-develop <ask|reply|inbox|start|resume|status> needs: clauth cf: no
56
-
57
- ## reporting
58
- /rdc:status needs: supabase,clauth cf: no
59
- /rdc:report needs: supabase,clauth,codeflow cf: yes
60
- /rdc:watch needs: (none) cf: no
61
- /rdc:help needs: (none) cf: no
62
-
63
- ## tooling
64
- /rdc:workitems [add|done|status|list|query] needs: supabase,clauth,work-items-rpc cf: no
65
- /rdc:fs-mcp <task> needs: clauth cf: no
66
-
67
- ## infra
68
- /rdc:self-test [--strict] needs: clauth cf: no
69
- /rdc:terminal-config <task> needs: git cf: no
70
-
71
- ## Decision tree (derived from skills_meta[].triggers)
72
-
73
- "research before planning" / "what should we use" → /rdc:preplan
74
- "plan this" / "architecture" / "epic breakdown" → /rdc:plan
75
- "build the epic" / "execute the plan" / "go" → /rdc:build
76
- "let claude run" / "overnight" / "drain queue" → /rdc:overnight
77
- "quick fix" / "typo" / "<5 files" → /rdc:fixit
78
- "code review" / "audit" / "tsc check" → /rdc:review
79
- "session report" / "summarize" → /rdc:report
80
- "where are we" / "snapshot" → /rdc:status
81
- "deploy to dev" / "audit watch paths" → /rdc:deploy
82
- "promote" / "push to prod" / "ship" → /rdc:release
83
- "convert prototype" / "finalize plan" → /rdc:handoff
84
- "mock it up" / "show me" → /rdc:prototype
85
- "add work item" / "list epics" → /rdc:workitems
86
- "ask codex" / "peer-aware" → /rdc:co-develop
87
- "claude.ai relay" / "collab session" → /rdc:collab
88
- "palette" / "studio design" / "tokens" → /rdc:design
89
-
90
- ## Direct MCP / curl Access
91
-
92
- MCP endpoint: https://rdc-skills.regendevcorp.com/mcp
93
- Health: curl -s https://rdc-skills.regendevcorp.com/health
94
- Header: Accept: application/json, text/event-stream
95
- Tools: rdc_skill_list, rdc_skill_search, rdc_skill_get
96
- Variants: cli for Claude Code/Codex/local terminal; cloud for claude.ai
97
- Response: SSE `data:` line contains the JSON-RPC envelope; tool text is result.content[0].text
98
- Catalog: rdc_skill_list returns aliases, args, requires, produces, follows, leads_to, output_contract, codeflow_required, and variants
99
-
100
- Extract the JSON-RPC envelope:
101
- curl -s -X POST https://rdc-skills.regendevcorp.com/mcp \
102
- -H 'Content-Type: application/json' \
103
- -H 'Accept: application/json, text/event-stream' \
104
- -d '{"jsonrpc":"2.0","id":0,"method":"tools/list"}' \
105
- | sed -n 's/^data: //p'
106
-
107
- List skills:
108
- curl -s -X POST https://rdc-skills.regendevcorp.com/mcp \
109
- -H 'Content-Type: application/json' \
110
- -H 'Accept: application/json, text/event-stream' \
111
- -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"rdc_skill_list","arguments":{}}}'
112
-
113
- Search by intent:
114
- curl -s -X POST https://rdc-skills.regendevcorp.com/mcp \
115
- -H 'Content-Type: application/json' \
116
- -H 'Accept: application/json, text/event-stream' \
117
- -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"rdc_skill_search","arguments":{"query":"turn this article into social posts"}}}'
118
-
119
- Fetch a skill:
120
- curl -s -X POST https://rdc-skills.regendevcorp.com/mcp \
121
- -H 'Content-Type: application/json' \
122
- -H 'Accept: application/json, text/event-stream' \
123
- -d '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"rdc_skill_get","arguments":{"name":"rdc:build","variant":"cli"}}}'
124
-
125
- Fetch a structured skill payload:
126
- curl -s -X POST https://rdc-skills.regendevcorp.com/mcp \
127
- -H 'Content-Type: application/json' \
128
- -H 'Accept: application/json, text/event-stream' \
129
- -d '{"jsonrpc":"2.0","id":4,"method":"tools/call","params":{"name":"rdc_skill_get","arguments":{"name":"rdc:build","variant":"cli","format":"json"}}}'
130
-
131
- REQUIRED EXACT TOKEN: "format":"json"
132
-
133
- ## Hard rules
134
-
135
- - `cf: yes` skills MUST consult CodeFlow before acting. Hooks fail-closed on unreachable CodeFlow for these.
136
- - NEVER `pnpm build` at monorepo level — single scoped builds only.
137
- - NEVER commit to `main` without explicit approval. Default branch is `develop`.
138
- - NEVER overlap agents on the same files.
139
- - ALWAYS update work items in real time via RPCs (see `.claude/rules/work-items-rpc.md`).
140
- - ALWAYS credentials via clauth daemon: `curl -s http://127.0.0.1:52437/v/<service>` (plain text).
141
- ```
142
-
143
- > If the manifest file is unreachable, fall back to the static table above (the manifest values it was generated from). Tell the user the fallback was used so they know to investigate.
1
+ ---
2
+ name: rdc:help
3
+ description: "Usage `rdc:help` — Show all MCP skills with usage, requirements, slash forms, and codeflow status. Reads `.claude-plugin/plugin.json` skills_meta (single source of truth). Call when unsure which skill to use or what args it takes."
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
+
9
+ # rdc:help — Skill Reference (manifest-driven)
10
+
11
+ > **⚠️ HARD OUTPUT RULE:** Read the plugin manifest, render the table, exit.
12
+ > No preamble. No follow-up question. No summary.
13
+
14
+ ## Procedure
15
+
16
+ 1. Resolve the plugin manifest path. Try in order, take the first that exists:
17
+ - `{PLUGIN_ROOT}/.claude-plugin/plugin.json` ← preferred when running from the published plugin
18
+ - `C:/Dev/rdc-skills/.claude-plugin/plugin.json` ← source-checkout fallback
19
+ - `~/.claude/plugins/cache/rdc-skills/rdc-skills/latest/.claude-plugin/plugin.json` ← installed cache
20
+ 2. Read it. Parse JSON. Read `skills_meta`. Accept either the current object map shape (`skills_meta.<name>`) or an older array shape (`skills_meta[]`); normalize to entries before rendering.
21
+ 3. Group entries by `category` in this order: `planning, build, deploy, release, dev-loop, reporting, tooling, infra`.
22
+ 4. For each entry render one row: `{slash} — {usage} — needs: {requires.join(',')} — cf: {codeflow_required ? 'yes' : 'no'}`.
23
+ 5. Print a Decision Tree at the end that maps natural-language phrases to skills, derived from each entry's `triggers[]`.
24
+ 6. Print the Direct MCP / curl Access block exactly as shown in the required output format. Do not summarize, compress, relabel, or omit the curl examples. This block is the public direct-caller contract for MCP/API/curl users.
25
+ 7. Hard rules section at the bottom (see below — verbatim).
26
+
27
+ ## Required output format
28
+
29
+ ```
30
+ RDC SKILLS — manifest: .claude-plugin/plugin.json @ v{version}
31
+
32
+ ## planning
33
+ /rdc:preplan <topic> needs: codeflow cf: yes
34
+ /rdc:plan <topic> needs: supabase,clauth,codeflow,work-items-rpc cf: yes
35
+ /rdc:handoff [--from-prototype <id>] needs: supabase,clauth,codeflow,work-items-rpc,git cf: yes
36
+
37
+ ## build
38
+ /rdc:build <epic-id> needs: supabase,clauth,codeflow,agent-dispatch,work-items-rpc,git cf: yes
39
+ /rdc:design <topic> needs: supabase,clauth,codeflow,git cf: yes
40
+ /rdc:prototype <desc> needs: supabase,clauth,codeflow cf: yes
41
+ /rdc:overnight [scope] needs: supabase,clauth,codeflow,agent-dispatch,work-items-rpc,git cf: yes
42
+ /rdc:review [--unattended] needs: supabase,clauth,codeflow,agent-dispatch,git cf: yes
43
+
44
+ ## deploy
45
+ /rdc:deploy <slug> [new|diagnose|audit] [--fix] needs: clauth,coolify,pm2,supabase,codeflow cf: yes
46
+
47
+ ## release
48
+ /rdc:release <repo> [version|--patch|--minor|--major|--dry-run] needs: clauth,git,npm,coolify cf: no
49
+ ⚠ Production promotion requires explicit user go-ahead.
50
+
51
+ ## dev-loop
52
+ /rdc:fixit <description> needs: supabase,clauth,codeflow,agent-dispatch,work-items-rpc,git cf: yes
53
+ constraint: < 5 files AND < 30 min — otherwise use /rdc:plan
54
+ /rdc:collab --session <id> needs: clauth,git cf: yes
55
+ /rdc:co-develop <ask|reply|inbox|start|resume|status> needs: clauth cf: no
56
+
57
+ ## reporting
58
+ /rdc:status needs: supabase,clauth cf: no
59
+ /rdc:report needs: supabase,clauth,codeflow cf: yes
60
+ /rdc:watch needs: (none) cf: no
61
+ /rdc:help needs: (none) cf: no
62
+
63
+ ## tooling
64
+ /rdc:workitems [add|done|status|list|query] needs: supabase,clauth,work-items-rpc cf: no
65
+ /rdc:fs-mcp <task> needs: clauth cf: no
66
+
67
+ ## infra
68
+ /rdc:self-test [--strict] needs: clauth cf: no
69
+ /rdc:terminal-config <task> needs: git cf: no
70
+
71
+ ## Decision tree (derived from skills_meta[].triggers)
72
+
73
+ "research before planning" / "what should we use" → /rdc:preplan
74
+ "plan this" / "architecture" / "epic breakdown" → /rdc:plan
75
+ "build the epic" / "execute the plan" / "go" → /rdc:build
76
+ "let claude run" / "overnight" / "drain queue" → /rdc:overnight
77
+ "quick fix" / "typo" / "<5 files" → /rdc:fixit
78
+ "code review" / "audit" / "tsc check" → /rdc:review
79
+ "session report" / "summarize" → /rdc:report
80
+ "where are we" / "snapshot" → /rdc:status
81
+ "deploy to dev" / "audit watch paths" → /rdc:deploy
82
+ "promote" / "push to prod" / "ship" → /rdc:release
83
+ "convert prototype" / "finalize plan" → /rdc:handoff
84
+ "mock it up" / "show me" → /rdc:prototype
85
+ "add work item" / "list epics" → /rdc:workitems
86
+ "ask codex" / "peer-aware" → /rdc:co-develop
87
+ "claude.ai relay" / "collab session" → /rdc:collab
88
+ "palette" / "studio design" / "tokens" → /rdc:design
89
+
90
+ ## Direct MCP / curl Access
91
+
92
+ MCP endpoint: https://rdc-skills.regendevcorp.com/mcp
93
+ Health: curl -s https://rdc-skills.regendevcorp.com/health
94
+ Header: Accept: application/json, text/event-stream
95
+ Tools: rdc_skill_list, rdc_skill_search, rdc_skill_get
96
+ Variants: cli for Claude Code/Codex/local terminal; cloud for claude.ai
97
+ Response: SSE `data:` line contains the JSON-RPC envelope; tool text is result.content[0].text
98
+ Catalog: rdc_skill_list returns aliases, args, requires, produces, follows, leads_to, output_contract, codeflow_required, and variants
99
+
100
+ Extract the JSON-RPC envelope:
101
+ curl -s -X POST https://rdc-skills.regendevcorp.com/mcp \
102
+ -H 'Content-Type: application/json' \
103
+ -H 'Accept: application/json, text/event-stream' \
104
+ -d '{"jsonrpc":"2.0","id":0,"method":"tools/list"}' \
105
+ | sed -n 's/^data: //p'
106
+
107
+ List skills:
108
+ curl -s -X POST https://rdc-skills.regendevcorp.com/mcp \
109
+ -H 'Content-Type: application/json' \
110
+ -H 'Accept: application/json, text/event-stream' \
111
+ -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"rdc_skill_list","arguments":{}}}'
112
+
113
+ Search by intent:
114
+ curl -s -X POST https://rdc-skills.regendevcorp.com/mcp \
115
+ -H 'Content-Type: application/json' \
116
+ -H 'Accept: application/json, text/event-stream' \
117
+ -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"rdc_skill_search","arguments":{"query":"turn this article into social posts"}}}'
118
+
119
+ Fetch a skill:
120
+ curl -s -X POST https://rdc-skills.regendevcorp.com/mcp \
121
+ -H 'Content-Type: application/json' \
122
+ -H 'Accept: application/json, text/event-stream' \
123
+ -d '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"rdc_skill_get","arguments":{"name":"rdc:build","variant":"cli"}}}'
124
+
125
+ Fetch a structured skill payload:
126
+ curl -s -X POST https://rdc-skills.regendevcorp.com/mcp \
127
+ -H 'Content-Type: application/json' \
128
+ -H 'Accept: application/json, text/event-stream' \
129
+ -d '{"jsonrpc":"2.0","id":4,"method":"tools/call","params":{"name":"rdc_skill_get","arguments":{"name":"rdc:build","variant":"cli","format":"json"}}}'
130
+
131
+ REQUIRED EXACT TOKEN: "format":"json"
132
+
133
+ ## Hard rules
134
+
135
+ - `cf: yes` skills MUST consult CodeFlow before acting. Hooks fail-closed on unreachable CodeFlow for these.
136
+ - NEVER `pnpm build` at monorepo level — single scoped builds only.
137
+ - NEVER commit to `main` without explicit approval. Default branch is `develop`.
138
+ - NEVER overlap agents on the same files.
139
+ - ALWAYS update work items in real time via RPCs (see `.claude/rules/work-items-rpc.md`).
140
+ - ALWAYS credentials via clauth daemon: `curl -s http://127.0.0.1:52437/v/<service>` (plain text).
141
+ ```
142
+
143
+ > If the manifest file is unreachable, fall back to the static table above (the manifest values it was generated from). Tell the user the fallback was used so they know to investigate.