@lifeaitools/rdc-skills 0.8.7

package/README.md

@@ -0,0 +1,188 @@
+# RDC Skills Library — Generic Version
+
+This directory contains a generic, project-agnostic version of the RDC (Research, Design, Code) skill suite. All skills have been extracted from a reference implementation and genericized for use in any monorepo project.
+
+## Install
+
+### Option A — Plugin marketplace (recommended for new installs)
+
+From any Claude Code session:
+
+```
+/plugin marketplace add LIFEAI/rdc-skills
+/plugin install rdc-skills
+```
+
+All 17 user-invocable skills become available as slash commands. Agent playbooks in `guides/agents/` are dispatched internally by `rdc:build` and are not user-invocable.
+
+### Option B — Directory plugin (LIFEAI dev machines)
+
+If you have the source repo locally, point the plugin directly at the directory in `~/.claude/settings.json`. Skills load live from disk — no install step needed, changes take effect on next session start:
+
+```json
+"extraKnownMarketplaces": {
+  "rdc-skills": {
+    "source": { "source": "directory", "path": "C:\\Dev\\rdc-skills" }
+  }
+},
+"enabledPlugins": {
+  "rdc-skills@rdc-skills": true
+}
+```
+
+### ⚠️ DO NOT mix install methods — duplicates will occur
+
+If `rdc-skills@rdc-skills` is enabled in your plugin settings AND you have manually installed files at `~/.claude/skills/user/rdc-*.md`, every skill loads twice (or more if stale plugin cache versions exist). Symptoms: each skill appears 2–3× in the skill list.
+
+**Fix:**
+```bash
+# Remove manual install
+rm ~/.claude/skills/user/rdc-*.md
+
+# Remove stale plugin cache (keep only the current version)
+rm -rf ~/.claude/plugins/cache/rdc-skills/rdc-skills/0.7.*
+```
+
+Use **one method only**: plugin (Option A or B) OR manual install — never both.
+
+### Legacy install scripts (deprecated since v0.6.0)
+
+`scripts/install.sh` and `scripts/install.ps1` copy files into `~/.claude/skills/user/`. These exist only for environments that cannot use the plugin system. Running them alongside the plugin creates duplicates. Do not use them if you have the plugin installed.
+
+## Path Variables
+
+Throughout the skills, the following substitutions have been made to make them portable:
+
+| Original | Generic | Your Project |
+|----------|---------|--------------|
+| `/full/path/to/monorepo/` | `{PROJECT_ROOT}/` | Your monorepo root |
+| `docs/guides/agent-bootstrap.md` | `{PROJECT_ROOT}/docs/guides/agent-bootstrap.md` | Your agent guide |
+| `develop` branch | `{development-branch}` | Your development branch |
+| `main` branch | `{production-branch}` | Your production branch |
+| Specific apps | `your-app-name` | Your app names |
+
+## Skills Overview
+
+23 skills organized into 5 categories:
+
+### Orchestration Skills (workflow drivers)
+- rdc:build, rdc:plan, rdc:preplan, rdc:review, rdc:overnight, rdc:fixit, rdc:status, rdc:report
+
+### 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
+
+### Utility Skills
+- rdc:collab
+
+### Reference
+- rdc:help
+
+## Key Features
+
+### TDD Enforcement (Built In)
+
+- `rdc:build` includes mandatory post-wave test gate via vitest
+- `rdc:review` reports test coverage delta
+- All agents write tests FIRST: red → implement → green
+- Packages with implementation but 0 new tests are flagged
+
+### Core Rules (Non-Negotiable)
+
+1. NEVER run `pnpm build` — crashes the system. Use `npx tsc --noEmit` + vitest only
+2. NEVER let agents overlap on the same files
+3. ALWAYS create work items BEFORE starting work
+4. ALWAYS read guide files before agent dispatch
+5. ALWAYS update work items in real time
+6. Tests FIRST, then implementation — red → green
+7. Push after every logical block
+
+## How to Adapt for Your Project
+
+1. Replace path variables in all skills:
+   - `{PROJECT_ROOT}` → your monorepo root
+   - `{development-branch}` → your dev branch
+   - `{production-branch}` → your production branch
+
+2. Create project guides in `{PROJECT_ROOT}/docs/guides/`:
+   - agent-bootstrap.md, frontend.md, backend.md, data.md, design.md, infrastructure.md, content.md
+
+3. Set up database (Supabase or equivalent):
+   - work_items table
+   - RPC functions: get_open_epics, insert_work_item, update_work_item_status, get_work_items_by_epic, bump_epic_version
+   - prototype_registry table
+   - design_context table
+
+4. Update database references from `work_items` to your actual table names
+
+5. Configure credential daemon or update `http://127.0.0.1:52437` references
+
+## File Structure
+
+```
+skills/
+  build/SKILL.md       (dispatch agents in waves — mandatory validator gate)
+  plan/SKILL.md        (create architecture + tasks)
+  preplan/SKILL.md     (research before planning)
+  review/SKILL.md      (quality gate: tests, types, docs)
+  overnight/SKILL.md   (unattended multi-epic supervisor)
+  fixit/SKILL.md       (quick-fix bypass)
+  status/SKILL.md      (project dashboard)
+  report/SKILL.md      (nightly report)
+  collab/SKILL.md      (bidirectional claude.ai ↔ Claude Code relay)
+  handoff/SKILL.md     (planning → work items)
+  prototype/SKILL.md   (build JSX prototype)
+  workitems/SKILL.md   (work item management)
+  help/SKILL.md        (skill index — shows current version)
+  deploy/SKILL.md      (Coolify ops: deploy, new, diagnose, audit)
+  release/SKILL.md     (atomic package/app release)
+  self-test/SKILL.md   (skill suite health check)
+  watch/SKILL.md       (session log watcher)
+
+guides/agents/         (agent-only playbooks — dispatched by rdc:build, not user-invocable)
+  frontend.md          (React, UI, Tailwind)
+  backend.md           (API routes, database, auth)
+  data.md              (migrations, schema, RPC)
+  design.md            (brand, tokens, design)
+  infrastructure.md    (deployment, CI/CD, DNS)
+  content.md           (copy, messaging, tone)
+  cs2.md               (paradigm-level work)
+  viz.md               (visualizations, charts, SVG)
+  setup.md             (project scan + .rdc/config.json generation)
+  verify.md            (evidence-before-claims verification gate — tsc + vitest + HTTP)
+
+scripts/
+  install.sh           (legacy only — do not use with plugin install)
+  install.ps1          (legacy only — do not use with plugin install)
+```
+
+## Check installed version
+
+```bash
+# See version in rdc:help skill
+head -4 ~/.claude/skills/user/rdc-help.md   # if using manual install
+
+# Or check source directly
+python3 -c "import json; print(json.load(open('package.json'))['version'])"
+
+# Or invoke the skill
+/rdc:help
+```
+
+Current version: **v0.8.0**
+
+## Quick Start
+
+1. Copy this directory to your project
+2. Update `{PROJECT_ROOT}` paths in all skills
+3. Create the required project guides and database tables
+4. Invoke skills via your agent framework:
+   - `/rdc:build <epic-id>` — dispatch agents
+   - `/rdc:overnight` — unattended multi-epic build
+   - `/rdc:review` — quality gate
+   - etc.
+
+All skills follow the same patterns: check before acting, update work items in real time, push often, test first.

package/README.sandbox.md

@@ -0,0 +1,3 @@
+# Sandbox
+
+Hello world

package/assets/watcher/viewer.html

@@ -0,0 +1,164 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="utf-8" />
+<title>rdc:watch — session log</title>
+<style>
+  :root {
+    --bg: #0b0f0b;
+    --fg: #c8f0c8;
+    --dim: #6a7a6a;
+    --bar: #111a11;
+    --bar-stall: #3a2f00;
+    --dispatch: #6aa9ff;
+    --commit: #58d06a;
+    --test: #e6c84a;
+    --error: #ff6060;
+    --note: #8a8a8a;
+    --banner: #ffffff;
+  }
+  * { box-sizing: border-box; }
+  html, body { margin: 0; padding: 0; height: 100%; background: var(--bg); color: var(--fg); font-family: ui-monospace, "Cascadia Mono", Menlo, Consolas, monospace; font-size: 13px; }
+  body { display: flex; flex-direction: column; }
+  header {
+    background: var(--bar);
+    border-bottom: 1px solid #1d2a1d;
+    padding: 8px 14px;
+    display: flex;
+    gap: 18px;
+    flex-wrap: wrap;
+    font-size: 12px;
+    color: var(--dim);
+  }
+  header.stalled { background: var(--bar-stall); color: #ffe08a; }
+  header b { color: var(--fg); font-weight: 600; }
+  header.stalled b { color: #ffe08a; }
+  #log {
+    flex: 1;
+    overflow-y: auto;
+    padding: 10px 14px 40px;
+    white-space: pre-wrap;
+    word-break: break-word;
+  }
+  .line { padding: 1px 0; line-height: 1.45; }
+  .ts { color: var(--dim); margin-right: 8px; }
+  .kind {
+    display: inline-block;
+    min-width: 70px;
+    margin-right: 8px;
+    text-transform: uppercase;
+    font-size: 11px;
+    letter-spacing: 0.05em;
+  }
+  .dispatch .kind, .dispatch .msg { color: var(--dispatch); }
+  .commit   .kind, .commit   .msg { color: var(--commit); }
+  .test     .kind, .test     .msg { color: var(--test); }
+  .error    .kind, .error    .msg { color: var(--error); }
+  .note     .kind, .note     .msg { color: var(--note); }
+  .banner   .kind, .banner   .msg { color: var(--banner); font-weight: 700; }
+</style>
+</head>
+<body>
+<header id="bar">
+  <div>session <b id="sid">—</b></div>
+  <div>started <b id="started">—</b></div>
+  <div>events <b id="count">0</b></div>
+  <div>updated <b id="updated">—</b></div>
+  <div id="status"></div>
+</header>
+<div id="log"></div>
+<script>
+(function () {
+  const LOG_URL = "./current.log";
+  const POLL_MS = 2000;
+  const logEl = document.getElementById("log");
+  const bar = document.getElementById("bar");
+  const sidEl = document.getElementById("sid");
+  const startedEl = document.getElementById("started");
+  const countEl = document.getElementById("count");
+  const updatedEl = document.getElementById("updated");
+  const statusEl = document.getElementById("status");
+
+  let lastLen = 0;
+  let count = 0;
+  let sessionSet = false;
+
+  const LINE_RE = /^\[([^\]]+)\]\s*\[([^\]]+)\]\s*(.*)$/;
+  const KINDS = new Set(["dispatch", "commit", "test", "error", "note", "banner"]);
+
+  function isAtBottom() {
+    return logEl.scrollHeight - logEl.scrollTop - logEl.clientHeight < 40;
+  }
+
+  function renderLine(raw) {
+    const m = raw.match(LINE_RE);
+    let ts = "", kind = "note", msg = raw;
+    if (m) {
+      ts = m[1];
+      kind = KINDS.has(m[2].toLowerCase()) ? m[2].toLowerCase() : "note";
+      msg = m[3];
+    }
+    const div = document.createElement("div");
+    div.className = "line " + kind;
+    const tsSpan = document.createElement("span");
+    tsSpan.className = "ts";
+    tsSpan.textContent = ts;
+    const kSpan = document.createElement("span");
+    kSpan.className = "kind";
+    kSpan.textContent = kind;
+    const mSpan = document.createElement("span");
+    mSpan.className = "msg";
+    mSpan.textContent = msg;
+    div.appendChild(tsSpan);
+    div.appendChild(kSpan);
+    div.appendChild(mSpan);
+    logEl.appendChild(div);
+
+    if (kind === "banner" && !sessionSet) {
+      const idMatch = msg.match(/Session started:\s*(\S+)/);
+      if (idMatch) sidEl.textContent = idMatch[1];
+      if (ts) startedEl.textContent = ts;
+      sessionSet = true;
+    }
+    count += 1;
+  }
+
+  async function poll() {
+    try {
+      const res = await fetch(LOG_URL + "?t=" + Date.now(), { cache: "no-store" });
+      if (!res.ok) throw new Error("http " + res.status);
+      const text = await res.text();
+      if (text.length < lastLen) {
+        // File shrank — reset (new session).
+        logEl.innerHTML = "";
+        lastLen = 0;
+        count = 0;
+        sessionSet = false;
+      }
+      if (text.length > lastLen) {
+        const stick = isAtBottom();
+        const chunk = text.slice(lastLen);
+        lastLen = text.length;
+        const lines = chunk.split(/\r?\n/);
+        for (const line of lines) {
+          if (line.trim().length === 0) continue;
+          renderLine(line);
+        }
+        countEl.textContent = String(count);
+        updatedEl.textContent = new Date().toLocaleTimeString();
+        if (stick) logEl.scrollTop = logEl.scrollHeight;
+      }
+      bar.classList.remove("stalled");
+      statusEl.textContent = "";
+    } catch (e) {
+      bar.classList.add("stalled");
+      statusEl.textContent = "stalled — retrying";
+    }
+  }
+
+  poll();
+  setInterval(poll, POLL_MS);
+})();
+</script>
+</body>
+</html>

package/commands/build.md

@@ -0,0 +1,183 @@
+---
+name: rdc:build
+description: >-
+  Usage `rdc:build <epic-id|topic> [--unattended]` — dispatch typed agents from an epic, commit, push, update work items. The build engine. Use after rdc:plan or when the project lead says "build it".
+---
+
+> **⚠️ OUTPUT CONTRACT (READ FIRST):** `guides/output-contract.md`
+> Checklist-only output. No tool-call narration. No raw MCP/JSON/log dumps.
+> One checklist upfront, updated in place, shown again at end with a 1-line verdict.
+
+> **Sandbox contract:** This skill honors `RDC_TEST=1` per `guides/agent-bootstrap.md` § RDC_TEST Sandbox Contract. Destructive external calls short-circuit under the flag.
+
+
+# rdc:build — Typed Agent Dispatch Engine
+
+## When to Use
+- Plan is approved and ready to execute
+- Project lead says "build it", "go", "execute", "do not stop"
+- An epic exists with child tasks ready for implementation
+- Called by `rdc:overnight` as part of the automated build loop
+
+## Arguments
+- `rdc:build <epic-id>` — build from a specific Supabase epic
+- `rdc:build <topic>` — find the epic by label/title match
+- `rdc:build` (no args) — show open epics and ask which to build (interactive only)
+- `rdc:build <epic-id> --unattended` — silent mode for overnight builds
+
+## Agent Types & Guide Files
+
+Every dispatched agent MUST read two files before starting — in this order:
+1. `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` — credentials, git rules, completion report format
+   (fallback: `{PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md` if `.rdc/` does not exist)
+2. `{PROJECT_ROOT}/.rdc/guides/<type>.md` — role-specific guide
+   (fallback: `{PROJECT_ROOT}/.rdc/guides/<type>.md`)
+
+Include both lines in every agent prompt:
+```
+"Read {PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md first (fallback: .rdc/guides/agent-bootstrap.md), then {PROJECT_ROOT}/.rdc/guides/<type>.md (fallback: .rdc/guides/<type>.md) before starting."
+```
+
+| Agent Type | Guide File | When to dispatch |
+|-----------|-----------|-----------------|
+| `frontend` | `.rdc/guides/frontend.md` | React components, pages, UI, Tailwind, animation |
+| `backend` | `.rdc/guides/backend.md` | API routes, server components, database queries, auth |
+| `data` | `.rdc/guides/data.md` | Migrations, schema changes, RPC functions |
+| `design` | `.rdc/guides/design.md` | Visual design, brand palettes, OG images, token work |
+| `infra` | `.rdc/guides/infrastructure.md` | CI/CD, deployment, DNS, SSL |
+| `content` | `.rdc/guides/content.md` | Marketing copy, messaging, tone |
+| `cs2` | `.rdc/guides/cs2.md` | CS 2.0 paradigm work (generic) |
+| `hail` | `.rdc/guides/cs2.md` + `packages/hail/CLAUDE.md` | Grammar, DSL compiler, evolution |
+| `pal` | `.rdc/guides/cs2.md` + `packages/pal/CLAUDE.md` | Sessions, moment windows, graph memory |
+| `bpmn` | `.rdc/guides/cs2.md` + `docs/systems/<domain>/flowable-bpmn-architecture.md` | BPMN flows, governance |
+| `virtue` | `.rdc/guides/cs2.md` + `packages/virtue-engine/CLAUDE.md` | Virtue weights, coherence, certification |
+| `viz` | `.rdc/guides/frontend.md` + `.rdc/guides/design.md` | Custom viz components, charts, diagrams |
+
+### How to classify a task → agent type
+
+Read the task title and description, then:
+- Mentions React, component, page, UI, Tailwind → `frontend`
+- Mentions API route, server, database query, auth → `backend`
+- Mentions migration, schema, table, RPC → `data`
+- Mentions brand, palette, typography, OG image → `design`
+- Mentions deploy, infrastructure, CI, DNS → `infra`
+- Mentions copy, messaging, email template → `content`
+- Mentions grammar, DSL, compiler → `hail`
+- Mentions session, moment, memory graph → `pal`
+- Mentions BPMN, flow, governance → `bpmn`
+- Mentions virtue, coherence, certification → `virtue`
+- Mentions visualization, chart, diagram, SVG → `viz`
+- Multiple types? Dispatch multiple agents, each with its guide.
+
+## Procedure
+
+1. **Load the epic:**
+   ```sql
+   SELECT get_work_items_by_epic('<epic-id>', 'todo');
+   ```
+   - Interactive (no args): show open epics, ask which to build
+   - Unattended (no tasks found): escalate via advisor tool
+
+2. **CHECK FOR EXISTING WORK (mandatory — never skip):**
+   ```sql
+   -- Check if prototypes exist from earlier sessions
+   SELECT name, component, source_path, status, notes
+   FROM prototype_registry
+   WHERE status IN ('prototype', 'converting')
+   ORDER BY created_at DESC;
+
+   -- Check for design decisions on this topic
+   SELECT topic, context_type, summary, source
+   FROM design_context
+   WHERE topic ILIKE '%<epic-topic>%'
+   ORDER BY created_at DESC;
+   ```
+   **If a prototype exists: ADAPT IT. Do not build from scratch.**
+   Tell the agent: "Read <source_path> first and convert it to the production contract."
+   
+   **If design decisions exist: follow them.** Include the summary in the agent prompt.
+
+3. **Load the plan** (if exists): check `.rdc/plans/` for matching topic (fallback: `.rdc/plans/`).
+
+4. **Read CLAUDE.md files** for all affected packages.
+
+5. **Classify each task** → assign agent type from the table above.
+
+6. **Group tasks into waves** — parallelize tasks with no file overlap:
+   - Wave 1: independent tasks (different packages/files)
+   - Wave 2: tasks that depend on Wave 1 outputs
+   - Wave 3: integration tasks
+
+7. **For each wave — dispatch typed agents in parallel:**
+   - Set work item to `in_progress` before dispatching
+   - Each agent prompt MUST include:
+     - `"Read {PROJECT_ROOT}/.rdc/guides/agent-bootstrap.md first (fallback: .rdc/guides/agent-bootstrap.md), then {PROJECT_ROOT}/.rdc/guides/<type>.md (fallback: .rdc/guides/<type>.md) before starting."`
+     - Specific files to create/modify
+     - Exact deliverables and commit message
+     - `"NEVER run pnpm build/test. NEVER modify files outside your scope."`
+   - Use `run_in_background: true` for parallel execution
+   - NEVER let agents overlap on the same files
+
+8. **Post-wave test gate (mandatory):**
+   After all agents in a wave complete, before marking tasks done:
+   ```bash
+   # For each package modified in this wave:
+   cd packages/<name> && npx vitest run 2>&1 | tail -20
+   ```
+   - All tests must pass before proceeding to next wave
+   - If tests fail: fix before marking the wave done
+   - NEVER use `pnpm build` or `pnpm turbo test` — vitest only per package
+   - New code must have tests: if a modified package shows 0 new test files, flag it
+
+9. **As agents complete:**
+   - Verify commit landed on the development branch
+   - Push to origin *(skip if `$RDC_TEST=1` — echo `[RDC_TEST] skipping git push` instead)*
+   - Set work item to `done` with notes
+   - Continue to next wave
+
+   **If an agent fails:**
+   - Interactive: diagnose before retrying
+   - Unattended: retry once; on second failure escalate via advisor
+     ```
+     BUILD_STATUS: { wave, tasks_done, tasks_failed, commits, escalated: true }
+     ```
+
+10. **Final verification gate (mandatory — before marking epic done):**
+    Dispatch the verify agent (see `guides/agents/verify.md`) across every package/app touched in this build.
+    The Iron Law: **NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE.**
+    - Run `npx vitest run --dir <pkg>` fresh for each touched package
+    - Run `npx tsc --noEmit --project <pkg>/tsconfig.json` for each
+    - Read the full output — zero failures, zero type errors
+    - If any step fails: fix and re-run the entire gate. Do not skip.
+    - NEVER `pnpm build` / `pnpm test` / `pnpm -r` (crashes machine)
+
+11. **After verification passes:**
+    - Push all commits:
+      ```bash
+      if [ "$RDC_TEST" != "1" ]; then
+        git push origin {development-branch}
+      else
+        echo "[RDC_TEST] skipping git push origin {development-branch}"
+      fi
+      ```
+    - Update epic version: `bump_epic_version()`
+    - Report summary with verification evidence quoted
+
+## Agent TDD Requirements
+
+When dispatching agents, include in every prompt:
+```
+TDD REQUIREMENT: Write tests FIRST for new functions/modules.
+Run: npx vitest run packages/<name> to verify red → implement → verify green.
+NEVER run pnpm build or pnpm turbo. Use npx vitest run only.
+```
+
+## Rules
+- Branch: development branch only (auto-commit, no confirmation needed)
+- NEVER let two agents edit the same file
+- NEVER run `pnpm build` (crashes system) — code only
+- Every agent reads its guide file — no exceptions
+- Update Supabase work items IN REAL TIME — not batch at end
+- Push after each wave, not just at the end
+- Unattended: NEVER pause — continue automatically
+- Unattended: max 2 retries per task before escalating to advisor