@lifeaitools/rdc-skills 0.35.6 → 0.35.7

package/skills/architecture-reviewer/SKILL.md

@@ -1,16 +1,6 @@
 ---
 name: architecture-reviewer
-description: >-
-  Usage `rdc:architecture-reviewer <path> [--config <file>] [--diff <ref>]` —
-  Clean Architecture boundary/dependency-direction/layer-separation review.
-  Runs TWO mechanical scorers first — `rdc-architecture-score` (layer
-  classification, inward-dependency rule, framework coupling, missing
-  repository/port abstractions, HTTP/DB leaks into Use Cases, circular
-  layer dependencies) and `rdc-solid-score`'s orchestrator/port boundary
-  check — then dispatches judgment-level review for the ONE thing neither
-  can see: whether an abstraction boundary makes architectural SENSE for
-  this domain, not just whether it has the right shape. Call from
-  rdc:review step 8b+, or standalone before merging a new package/module.
+description: rdc:architecture-reviewer (path) - [--diff] — Clean Architecture boundary/dependency-direction/layer-separation review
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/behavior-audit/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: behavior-audit
-description: "Usage `rdc:behavior-audit <report-dir> [--since-days N] [--latest N] [--reprocess]` — produces a bounded, redacted Claude/Codex transcript evidence bundle, incrementally skips completed transcript hashes, and aligns candidate behavior problems to shared truth-governance rules."
+description: rdc:behavior-audit (report-dir) - [--since-days, --latest, --reprocess] — produces a bounded, redacted Claude/Codex transcript evidence bundle, incrementally skips completed transcr...
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/behavior-audit/agents/openai.yaml

@@ -1,4 +1,4 @@
-interface:
-  display_name: "Behavior Audit"
-  short_description: "Audit Claude and Codex behavior against shared rules."
-  default_prompt: "Run a behavior audit for the last seven days and write the evidence bundle to a report directory."
+interface:
+  display_name: "Behavior Audit"
+  short_description: "Audit Claude and Codex behavior against shared rules."
+  default_prompt: "Run a behavior audit for the last seven days and write the evidence bundle to a report directory."

package/skills/brochure/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: brochure
-description: "Usage `rdc:brochure <input> [--out <path>] [--template <name>] [--format Letter|A4]` — Turn a zip, folder, HTML file, URL, or markdown folder into a print-quality PDF brochure via Puppeteer. Auto-detects print-variant HTML, honors @page CSS, falls back to a Studio-token-aware template when no HTML exists."
+description: rdc:brochure (input) - [--out, --template, --format, --margin, --no-print-emulate, --keep-workdir] — Turn a zip, folder, HTML file, URL, or markdown folder into a print-quality PDF brochure via Puppeteer
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/brochurify/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: brochurify
 version: 0.1.0
-description: |
   Orchestrate a Brochurify job from source ingest through delivered PDF, using six parallel-dispatched typed sub-agents and the convergence loop. Use this skill EVERY TIME the user invokes Brochurify directly via "brochurify this", "make a brochure from", "convert this to a brochure PDF", or "rdc:brochurify". Also runs automatically when a job arrives from the broker via monkey_dispatch. The skill enforces D-001 through D-016 from the brochurify DECISIONS-LOG.
 triggers:
   - "rdc:brochurify"
@@ -10,6 +9,7 @@ triggers:
   - "convert to brochure PDF"
   - "generate brochure from"
   - monkey_dispatch payload with skill="brochurify"
+description: rdc:brochurify (source) — |
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/build/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: build
-description: "Usage `rdc:build <epic-id>` — You have a planned epic with tasks ready to execute. Dispatches parallel typed agents, each commits atomically to develop, runs a mandatory per-wave code-review gate (pr-review-toolkit:code-reviewer), closes work items, and runs the validator gate. Call after rdc:plan or when told to build."
+description: rdc:build (epic-id) - [--no-review] — execute a planned epic, then gate and ship to dev
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/channel-formatter/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: channel-formatter
-description: "Usage `rdc:channel-formatter <channel|pack> [content]` — Apply precise, channel-native formatting and content repurposing to any output: LinkedIn, Twitter/X, Slack/Teams, Email (external/internal), Pitch Deck slides, Word/DOCX, PDF Report, Web/Landing Page, and multi-output content packs. Use EVERY TIME the user names an output channel/platform/document type, asks to 'write a post', 'draft an email', 'format this for', 'make this a slide', 'send to LinkedIn', 'write a tweet', 'social media post', 'turn this article into posts', 'make a content pack', 'make a social pack', or 'repurpose this article'. Each channel has its own Unicode strategy, emphasis system, length limits, and structure — never apply generic markdown to channel-specific output. This skill FORMATS, STRUCTURES, and REPURPOSES text only — for actual .docx/.pptx ↔ Markdown FILE conversion (either direction) use `rdc:convert` (build-corpus), not this skill. Self-contained: all channel and pack rules are inlined below (no external reference files)."
+description: "rdc:channel-formatter ([channel], [content]) — Apply precise, channel-native formatting and content repurposing to any output: LinkedIn, Twitter/X, Slack/..."
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/clean-code-analyzer/SKILL.md

@@ -1,11 +1,6 @@
 ---
 name: clean-code-analyzer
-description: >-
-  Usage `rdc:clean-code-analyzer <path> [--project-root <dir>]` — naming,
-  dead code, function-size, and error-handling smells outside SOLID's scope
-  (SOLID governs class/module shape; this governs whether the code inside is
-  readable and honest about what it does). N1/N2/N4/N7/F1/F2/E1/E2/G9 are
-  mechanical AST checks, not LLM judgment — see `scripts/clean-code-score.mjs`.
+description: rdc:check-clean-code (path) - [--diff] — naming, dead code, function-size, and error-handling smells outside SOLID's scope (SOLID governs class/modu...
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/co-develop/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: co-develop
-description: "Usage `rdc:co-develop <ask|reply|inbox|start|resume|status>` — peer-aware Claude/Codex co-development over clauth, with ask --wait as the default delegation pattern."
+description: rdc:co-develop (subcommand) - [--wait] — peer-aware Claude/Codex co-development over clauth, with ask --wait as the default delegation pattern
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/collab/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: collab
-description: "Usage `rdc:collab <collaborator> [inbound] <topic>` — Structured agent-to-agent CONVERSATION with Codex, a local LLM, a Claude agent, or a claude.ai session. Converges on a decision and never writes to the repo — work that needs writing becomes a work item for rdc:build. Run `rdc:collab status <peer>` first — both sides emit probed capability state. Every dispatch carries a response contract."
+description: rdc:collab () - [--session] — run a structured agent-to-agent conversation
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/convert/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: convert
-description: "Usage `rdc:convert <input> [--out <dir>] [--to markdown|word] [--images assets|base64|s3]` — Convert .docx/.pptx/.ppt → Markdown (Word OMML equations as KaTeX TeX, tables, images) or Markdown → Word via the build-corpus CLI from npm `regen.mde`. Portable: runs in any session that can reach npm — Claude Code CLI, Codex, and claude.ai can fetch + run it. Use whenever the user asks to convert an Office document, build a Markdown corpus from .docx/.pptx, turn Markdown into a .docx, or open the report in the regen-mde editor on Windows."
+description: rdc:convert (input) - [--out, --out-same-dir, --to, --images, --equations, --inline-images, --word-template, --move-sources, --config] — Convert .docx/.pptx/.ppt → Markdown (Word OMML equations as KaTeX TeX, tables, images) or Markdown → Word v...
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/deploy/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: deploy
-description: "Usage `rdc:deploy <slug> [promote|diagnose|audit|convert]` — registry-resolved PM2 development deployment and Coolify production promotion through clauth's bearer-authenticated job control plane, with status receipts and mandatory content gates."
+description: rdc:deploy (slug, [action]) - [--fix, --hotfix] — ship to PM2 dev; promote to Coolify production
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/design/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: design
-description: "Usage `rdc:design <topic>` — RDC-owned design work for Studio, Palette Library, and token-aware UI systems. Use for Rampant color work or design-system-first builds owned by the design cell. Not for general UI polish — use impeccable for that."
+description: rdc:design (topic) — design Studio, palette and token-aware UI work
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/edit/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: edit
-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`."
+description: rdc:edit (target) — open the local website editor for a target
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/env/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: env
-description: "Usage `rdc:env [status|install|repair|update]` — Manage the LIFEAI environment harness: check status, install on a fresh box, repair broken services, or pull updates. Reads $LIFEAI_ENV/manifest.json as the source of truth. Use when: 'check the environment', 'install environment', 'repair environment', 'update environment', 'setup env', 'fix env', 'env status', or after a reboot/GPU crash."
+description: "rdc:env ([action]) — Manage the LIFEAI environment harness: check status, install on a fresh box, repair broken services, or pul..."
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/extract-verifier-rules/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: extract-verifier-rules
 version: 0.1.0
-description: |
   Read recent enhancement-log entries, cluster failures by pattern, generate candidate verifier rules, test them against the known-good corpus and the failure corpus, and propose pull requests adding the highest-confidence rules to forbidden-patterns.json. Use this skill on a nightly cadence (3 AM PT), or manually when the user says "extract verifier rules", "promote enhancement log", "what new rules should we add", or after a significant brochure run produced many failures.
 triggers:
   - "rdc:extract-verifier-rules"
@@ -10,6 +9,7 @@ triggers:
   - "what new rules should we add"
   - "verifier corpus update"
   - nightly cron at 3:00 AM PT
+description: rdc:extract-verifier-rules ([enhancement-log]) — |
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/fixit/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: fixit
-description: "Usage `rdc:fixit <description>` — Quick fix under 5 files / 30 min that does not warrant a full plan→build cycle. Creates a minimal work item, makes the change, commits, runs a mandatory code-review pass (pr-review-toolkit:code-reviewer), DELIVERS the change to where it is consumed (publish/deploy/land) and verifies it, then closes. The only sanctioned bypass of rdc:build."
+description: rdc:fixit (description) — make a scoped fix under 5 files and ship it to dev
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/fs-mcp/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: fs-mcp
-description: "Usage `rdc:fs-mcp <task>` — Use the File System MCP bridge for live repo reads, safe writes, cloud-to-local ingest, and GitHub-branch imports into a dirty local monorepo. Use when Claude.ai, Cowork, or CLI agents need fs_read/fs_write/fs_import_git_files guidance."
+description: rdc:fs-mcp (task) — Use the File System MCP bridge for live repo reads, safe writes, cloud-to-local ingest, and GitHub-branch i...
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/handoff/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: handoff
-description: "Usage `rdc:handoff [--from-prototype <id>]` — Convert a finalized plan or prototype into CLI-ready artifacts: writes .rdc/plans/, creates Supabase work items with DoD checklists, registers prototype if present. Bridge between planning session and rdc:build."
+description: rdc:handoff () - [--from-prototype] — turn a plan or prototype into work items and artifacts
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/help/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: help
-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."
+description: rdc:help () — list all MCP skills with usage, requirements and slash form
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/housekeeping/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: housekeeping
-description: "Usage `rdc:housekeeping [--fix]` — Weekly maintenance audit: directory structure verification, PUBLISH.md URL validation, CLAUDE.md freshness, orphan detection, places compliance, and stale version scan. Produces `.rdc/reports/YYYY-MM-DD-housekeeping.md`. With `--fix`, auto-remediate safe issues."
+description: "rdc:housekeeping () - [--fix] — Weekly maintenance audit: directory structure verification, PUBLISH.md URL validation, CLAUDE.md freshness,..."
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/lifeai-brochure-author/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: lifeai-brochure-author
 version: 0.1.0
-description: |
   The mandatory contract for authoring brochure JSX using @lifeai/brochure-kit. Use this skill EVERY TIME any AI engine (Claude, Cursor, Copilot, /design, Cowork, v0) generates JSX intended for the Brochurify pipeline — whether the user says "write a brochure," "make a one-pager," "draft a PDF report," or any equivalent. Also trigger when a file imports from @lifeai/brochure-kit. Failing to read this skill before authoring is a defect.
 
 triggers:
@@ -18,6 +17,7 @@ triggers:
 required_validators:
   - command: pnpm bk-lint
     blocking: true
+description: lifeai-brochure-author (brochure-jsx-task) — |
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/new-model/SKILL.md

@@ -9,13 +9,7 @@ triggers:
   - register model
   - new model for
   - model registration check
-description: >
-  Register a new Reference Model completely — the yes/no gate that prevents half-registered models.
-  A reference model is DEFINED as registered in all four homes: (1) RPMS project_nodes row
-  (node_type=reference_model), (2) apps/vlas route group /models/<slug>, (3) apps/vlas
-  src/data/models/<slug> definitions, (4) global-corpus Drive directory. If ANY of the four is
-  missing, the model does not exist yet — run this skill.
-  Trigger when asked to create, register, or check whether a reference model exists.
+description: rdc:new-model (slug-or-model-brief) — Register a new Reference Model completely — the yes/no gate that prevents half-registered models
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/onramp/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: onramp
-description: "Usage `rdc:onramp <slug> --name \"<Display Name>\"` — Full-pipeline enrollment orchestrator for a new Place Fund project. Runs all 7 phases: enroll → research + document integration → conflict resolution → brand book + imagery → Regen Score gate → site build → deploy dev. Each phase is idempotent and resumable."
+description: rdc:onramp (slug) - [--name, --location, --archetype, --owner, --history, --dry-run] — Full-pipeline enrollment orchestrator for a new Place Fund project
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/overnight/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: overnight
-description: "Usage `rdc:overnight [epic-id|label=<label>]` — Unattended end-to-end: drain the entire work queue autonomously (preplan → plan → build → review → report). Inherits mandatory per-wave code-review (pr-review-toolkit:code-reviewer) from rdc:build and rdc:review. Use when leaving Claude to run unsupervised for an extended session."
+description: rdc:overnight ([scope]) — drain the work queue unattended, end to end
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/package-design/SKILL.md

@@ -1,9 +1,6 @@
 ---
 name: package-design
-description: >-
-  Usage `rdc:package-design <path>` — module boundary and export-surface
-  review: does this package expose the right things, hide the right things,
-  and sit at the right size.
+description: "rdc:check-packages (path) — module boundary and export-surface review: does this package expose the right things, hide the right things..."
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/pattern-advisor/SKILL.md

@@ -1,11 +1,6 @@
 ---
 name: pattern-advisor
-description: >-
-  Usage `rdc:pattern-advisor <path>` — suggests an applicable design pattern
-  for a given code shape. Factory Method/Builder/Singleton/Decorator/
-  Adapter/Facade/Strategy/Observer/Command/Template Method are mechanical
-  AST checks, not LLM judgment — see `scripts/pattern-score.mjs`. Advisory
-  only; never rewrites code itself.
+description: rdc:suggest-patterns (path) — suggests an applicable design pattern for a given code shape
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/pattern-refactoring-guide/SKILL.md

@@ -1,9 +1,6 @@
 ---
 name: pattern-refactoring-guide
-description: >-
-  Usage `rdc:pattern-refactoring-guide <path>` — turns a pattern-advisor
-  recommendation (or a solid-validator/architecture-reviewer finding) into a
-  concrete before/after refactor plan. Produces a plan, does not apply it.
+description: rdc:get-refactoring-plan (finding) — turns a pattern-advisor recommendation (or a solid-validator/architecture-reviewer finding) into a concrete...
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/plan/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: plan
-description: "Usage `rdc:plan <topic>` — No epic exists and you need architecture + task breakdown. Produces design decisions, tradeoffs, and Supabase epics/tasks with DoD checklists that feed rdc:build. Use after rdc:preplan or when given clear architectural direction."
+description: rdc:plan (topic) — produce architecture, decisions and an epic with tasks
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/preplan/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: preplan
-description: "Usage `rdc:preplan <topic>` — Before committing to an architecture, research unknowns first. Codebase scan + web search, no code written, no work items created. Output feeds rdc:plan. Use for open-ended approach questions."
+description: rdc:preplan (topic) — research the unknowns before committing to an architecture
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/prototype/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: prototype
-description: "Usage `rdc:prototype <description>` — Build a JSX/TSX mockup for visual review before implementation. Saves to docs/source/, registers in prototype_registry. Use when asked to mock something up or show what it looks like. Not production code."
+description: rdc:prototype (description) — build a JSX/TSX mockup for visual review
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/refactor/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: refactor
-description: "Usage `rdc:refactor <epic-id|topic> --takeover <reason>` — Governed consolidation and implementation of a cross-cutting refactor. Authorizes an explicit takeover, preserves evidence, re-parents relevant work through the consolidation RPC, isolates every writer, and uses the same review, validator, landing, and delivery gates as rdc:build."
+description: rdc:refactor (epic-id-or-topic) - [--takeover] — Governed consolidation and implementation of a cross-cutting refactor
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/regen-media/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: regen-media
-description: "Usage `rdc:regen-media <generate|edit|upscale|upload> <brief-or-path>` - Primary image-generation and Regen Media asset workflow. Use for image generation, image editing/upscaling, GPT Image/gpt-image-2 requests, Codex built-in image_gen, and uploading finished images to regen-media/R2. The default path is keyless local Codex gpt-image-2 via the built-in image_gen tool; server-side regen-media MCP/API generation is fallback only."
+description: rdc:regen-media (action, brief-or-path) - [--size, --upload] — Primary image-generation and Regen Media asset workflow
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/release/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: release
-description: "Usage `rdc:release <repo> [version|--patch|--minor|--major|--dry-run]` — bump, commit, tag, push, wait for CI/publish, install, and verify a package or project using repo-local release metadata."
+description: rdc:release (repo, [version]) - [--patch, --minor, --major, --dry-run] — bump, tag, publish and verify a package
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/report/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: report
-description: "Usage `rdc:report` — Write the nightly session summary to .rdc/reports/YYYY-MM-DD.md covering completed work, open items, per-project progress, and infra status. Call at session end."
+description: rdc:report () — write the session summary to .rdc/reports/
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/review/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: review
-description: "Usage `rdc:review [--unattended]` — Post-build quality gate: tsc, tests, stale docs, export conflicts, and a mandatory pr-review-toolkit:code-reviewer pass across modified packages. Fixes what it can automatically, escalates the rest. Call after rdc:build and before merging to main."
+description: rdc:review () - [--unattended] — post-build gate over tsc, tests, docs and code review
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/rpms-filemap/SKILL.md

@@ -1,6 +1,5 @@
 ---
 name: rpms-filemap
-description: "Generated RPMS file map — RULE #1, canonical homes, and Context Export pointers served from regen-root manifest."
 slash: "rdc:rpms-filemap"
 category: "tooling"
 usage: "rdc:rpms-filemap"
@@ -11,6 +10,7 @@ triggers:
   - "context export"
   - "where does this file belong"
   - "where should pm artifacts go"
+description: "rdc:rpms-filemap () — Generated RPMS file map — RULE #1, canonical homes, and Context Export pointers served from regen-root mani..."
 ---
 # RPMS File Map
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/self-test/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: self-test
-description: "Usage `rdc:self-test [--strict]` — Validate all rdc:* skills, plugin manifest, and tooling consistency. Use after editing skills, upgrading the plugin, or when a skill behaves unexpectedly."
+description: rdc:self-test () - [--strict] — validate every rdc skill, the manifest and tooling
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/solid-validator/SKILL.md

@@ -1,11 +1,6 @@
 ---
 name: solid-validator
-description: >-
-  Usage `rdc:solid-validator <path> [--diff <ref>] [--config <file>]` — the
-  FORM corner of the form/fit/function model. Deterministic AST scoring of
-  all five SOLID letters (weighted sum, confidence-annotated) plus a separate
-  Clean Architecture boundary check. Real numbers, not LLM judgment — see
-  `scripts/solid-score.mjs` for the mechanism.
+description: rdc:solid-validator (path) - [--diff, --config] — the FORM corner of the form/fit/function model
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/status/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: status
-description: "Usage `rdc:status` — Read-only snapshot of open epics, work items, Coolify health, blockers, and next recommended action. Safe to call anytime. Start here when disoriented or resuming a session."
+description: rdc:status () — snapshot open epics, health, blockers and next action
 ---
 
 > **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`

package/skills/terminal-config/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: terminal-config
-description: "Usage `rdc:terminal-config <task>` — read and safely modify Windows Terminal settings, shell profiles, and agent startup sequencing without relying on machine-specific paths."
+description: rdc:terminal-config (task) — read and safely modify Windows Terminal settings, shell profiles, and agent startup sequencing without rely...
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.

package/skills/testing-strategy/SKILL.md

@@ -1,11 +1,6 @@
 ---
 name: testing-strategy
-description: >-
-  Usage `rdc:testing-strategy <path>` — recommends the right TEST LEVEL and
-  SHAPE for a surface (unit/integration/live tier, assertion vs golden-capture),
-  not a specific test to write. The FUNCTION corner of the form/fit/function
-  model — solid-validator covers FORM, architecture-reviewer covers FIT, this
-  covers whether a surface's behavior is actually provable, and how.
+description: rdc:testing-strategy (path) — recommends the right TEST LEVEL and SHAPE for a surface (unit/integration/live tier, assertion vs golden-ca...
 ---
 
 > If dispatching subagents or running as a subagent: read `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` first (fallback: `.rdc/guides/agent-bootstrap.md`) — this is also where the global rdc-harness-use policy for create/open/build/deploy work lives.