@lifeaitools/rdc-skills 0.24.23 → 0.24.24

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "rdc",
-  "version": "0.24.23",
+  "version": "0.24.24",
   "description": "RDC typed-agent dispatch skill suite for Claude Code — plan, build, review, overnight unattended builds with work-item tracking and TDD enforcement.",
   "author": {
     "name": "LIFEAI",

package/README.md

@@ -13,7 +13,10 @@ From any Claude Code session:
 /plugin install rdc-skills
 ```
 
-All user-invocable skills become available as slash commands. Agent playbooks in `guides/agents/` are dispatched internally by `rdc:build` and are not user-invocable.
+The full catalog is available through the MCP as 29 skills. Eighteen common
+workflows also ship as `/rdc:*` command shorthands. Agent playbooks in
+`guides/agents/` are dispatched internally by `rdc:build` and are not
+user-invocable.
 
 ### Option B — Directory plugin (LIFEAI dev machines)
 
@@ -162,39 +165,47 @@ Throughout the skills, the following substitutions have been made to make them p
 
 ## Skills Overview
 
-29 skills organized into 6 categories:
+29 MCP skills organized into 8 manifest categories. Eighteen of these also have
+`/rdc:*` command shorthands for Claude Code/plugin callers.
 
-### Orchestration Skills (workflow drivers)
-- rdc:build, rdc:plan, rdc:preplan, rdc:review, rdc:overnight, rdc:fixit, rdc:status, rdc:report
+Use `rdc_skill_list` for the authoritative live catalog, including names,
+visible slash forms, requirements, triggers, and usage.
+
+### Planning
+- rdc:preplan, rdc:plan, rdc:handoff
 
 ### Agent Guides (dispatched by rdc:build, not user-invocable)
 Located in `guides/agents/` — plain markdown playbooks spawned as sub-agents:
 - frontend, backend, data, design, infrastructure, content, cs2, viz, setup, verify
 
-### Bridge Skills (Planning → CLI)
-- rdc:handoff, rdc:prototype, rdc:workitems
+### Build
+- rdc:build, rdc:design, rdc:prototype, rdc:overnight, rdc:review
 
-### Utility Skills
-- rdc:collab
-- rdc:co-develop — peer-aware Claude/Codex co-development over clauth
-- rdc:fs-mcp — File System MCP bridge guidance for live repo reads/writes
-- rdc:terminal-config — Windows Terminal and hidden-launch policy audit
-- rdc:watch — session-log viewer initialization for attended sessions
-- rdc:channel-formatter — channel-native formatting and content repurposing for LinkedIn, Twitter/X, Slack/Teams, email, decks, Word/PDF structure, web copy, and content packs
+### Deploy
+- rdc:deploy
 
-### Design Skills
-- rdc:design — RDC/Studio design, tokens, palettes, themes, and Rampa CLI-assisted color systems
+### Release
+- rdc:release
 
-### Document and Brochure Skills
-- rdc:convert — Office/Markdown conversion via build-corpus
+### Dev Loop
+- rdc:fixit, rdc:collab, rdc:co-develop
+
+### Reporting
+- rdc:help, rdc:housekeeping, rdc:report, rdc:status, rdc:watch
+
+### Tooling
+- rdc:channel-formatter — channel-native formatting and content repurposing for LinkedIn, Twitter/X, Slack/Teams, email, decks, Word/PDF structure, web copy, and content packs
 - rdc:brochure — HTML/folder/zip/URL/Markdown to print-quality PDF
-- rdc:brochurify — six-wave Brochurify orchestration contract
-- lifeai-brochure-author — brochure JSX authoring contract for @lifeai/brochure-kit
-- rdc:extract-verifier-rules — verifier-rule candidates from enhancement logs
-- rpms-filemap — canonical RPMS file-map lookup
+- rdc:brochurify — Brochurify orchestration for polished PDF jobs
+- lifeai-brochure-author — JSX authoring contract for Brochurify inputs
+- rdc:convert — Office/Markdown conversion via build-corpus
+- rdc:fs-mcp — File System MCP bridge guidance for live repo reads/writes
+- rdc:extract-verifier-rules — verifier-rule extraction from enhancement logs
+- rdc:rpms-filemap — generated RPMS file-map guidance
+- rdc:workitems — manual work item CRUD
 
-### Reference
-- rdc:help, rdc:self-test
+### Infra
+- rdc:self-test, rdc:terminal-config
 
 ## Channel Formatting and Content Packs
 

package/commands/help.md

@@ -1,15 +1,15 @@
 ---
 name: rdc:help
 description: >-
-  Usage `rdc:help` or `rdc` — manifest-driven menu of all rdc:* skills with
+  Usage `rdc:help` or `rdc` — manifest-driven menu of all MCP skills with
   argument syntax, requirements, decision hints, and direct MCP/curl access.
 ---
 
 > **Output contract:** Checklist/table output only. No raw MCP/JSON/log dumps.
 
-# rdc:help — Manifest-Driven Command Reference
+# rdc:help — Manifest-Driven Skill Reference
 
-Print a concise command reference from the plugin manifest, then stop. Do not
+Print a concise skill reference from the plugin manifest, then stop. Do not
 ask which command to run unless the user explicitly asks for a recommendation.
 
 ## Source Of Truth

package/git-sha.json

@@ -1,3 +1,3 @@
 {
-  "sha": "118a743f830c5a240c3c3bc46f45adfcaed9d1e2"
+  "sha": "337ec305ad032632e314baec4d0d7ddcccca6b8c"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lifeaitools/rdc-skills",
-  "version": "0.24.23",
+  "version": "0.24.24",
   "description": "RDC typed-agent dispatch skill suite for Claude Code - plan, build, review, overnight builds",
   "keywords": [
     "claude-code",

package/skills/help/SKILL.md

@@ -1,12 +1,12 @@
 ---
 name: rdc:help
-description: "Usage `rdc:help` — Show all rdc:* skills with usage, requirements, 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."
+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."
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
 > Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
 
-# rdc:help — Command Reference (manifest-driven)
+# rdc:help — Skill Reference (manifest-driven)
 
 > **⚠️ HARD OUTPUT RULE:** Read the plugin manifest, render the table, exit.
 > No preamble. No follow-up question. No summary.

package/tests/help-surface.test.mjs

@@ -31,6 +31,13 @@ for (const [name, text] of Object.entries(docs)) {
   assert.doesNotMatch(text, /https:\/\/rdc-skills\.dev\.regendevcorp\.com\/mcp/, `${name} must not point callers at dev MCP`);
 }
 
+assert.match(docs.readme, /29 MCP skills organized into 8 manifest categories/, 'README should use manifest category count');
+assert.match(docs.readme, /Eighteen[\s\S]*\/rdc:\*` command shorthands/i, 'README should distinguish slash-command shorthands from full MCP skills');
+assert.match(docs.readme, /Use `rdc_skill_list` for the authoritative live catalog/, 'README should point callers to live MCP catalog');
+assert.doesNotMatch(docs.readme, /All user-invocable skills become available as slash commands/, 'README must not imply all MCP skills are slash commands');
+assert.doesNotMatch(docs.readme, /29 skills organized into 6 categories/, 'README must not carry stale category count');
+assert.match(docs.commandHelp, /menu of all MCP skills/, 'command help should refer to MCP skill catalog');
+assert.match(docs.skillHelp, /Show all MCP skills/, 'skill help should refer to MCP skill catalog');
 assert.match(docs.skillHelp, /manifest-driven/i, 'skill help should be manifest-driven');
 assert.match(docs.commandHelp, /manifest-driven/i, 'command help should be manifest-driven');
 assert.doesNotMatch(docs.commandHelp, /Print the full usage menu below verbatim/, 'command help must not use stale static menu wording');