@lifeaitools/rdc-skills 0.24.11 → 0.24.13

package/skills/status/SKILL.md

@@ -1,99 +1,99 @@
----
-name: rdc: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."
----
-
-> **⚠️ 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.
-
-> 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`).
-
-
-# rdc:status — Project Dashboard
-
-## When to Use
-- Start of any session
-- Project lead asks "what's the status", "where are we", "what's open"
-- Before deciding what to work on next
-
-## Procedure
-
-1. **Open epics:**
-   ```sql
-   SELECT get_open_epics();
-   ```
-
-2. **Work item counts by status:**
-   ```sql
-   SELECT status, count(*) FROM work_items 
-   WHERE status != 'archived' 
-   GROUP BY status ORDER BY status;
-   ```
-
-3. **Items by label/project (top 10 labels):**
-   ```sql
-   SELECT unnest(labels) as label, count(*), 
-          count(*) FILTER (WHERE status = 'done') as done,
-          count(*) FILTER (WHERE status = 'todo') as todo,
-          count(*) FILTER (WHERE status = 'in_progress') as wip
-   FROM work_items 
-   GROUP BY label ORDER BY count DESC LIMIT 10;
-   ```
-
-4. **Recent activity (last 48 hours):**
-   ```sql
-   SELECT title, status, updated_at 
-   FROM work_items 
-   WHERE updated_at > now() - interval '48 hours'
-   ORDER BY updated_at DESC LIMIT 15;
-   ```
-
-5. **Git status:**
-   ```bash
-   git log --oneline -10
-   git status
-   git branch -v
-   ```
-
-6. **Dev server health (PM2):**
-   SSH into the Coolify server and check PM2 process state:
-   ```bash
-   # Note: clauth key name for the SSH key may vary by project. Common names: ssh-key-path, vultr-ssh-key, dev-ssh-key.
-   # Check available keys with: curl -s http://127.0.0.1:52437/list-services
-   SSH_KEY=$(curl -s http://127.0.0.1:52437/v/ssh-key-path)
-   ssh -i "$SSH_KEY" -o StrictHostKeyChecking=no root@64.237.54.189 "pm2 jlist 2>/dev/null"
-   ```
-   Parse the JSON array — for each process note `name`, `pm2_env.status` (online/stopped/errored), and `pm2_env.pm_uptime`.
-   If SSH fails or PM2 returns nothing, note "PM2 unreachable" and continue.
-
-7. **Infrastructure health** (if MCP available):
-   - Get infrastructure overview or diagnose issues
-   - Report any apps with failed builds or down containers
-
-8. **Present as a compact dashboard:**
-   ```
-   ## Open Epics (N)
-   <table>
-   
-   ## Work Items: X done | Y todo | Z in_progress
-   
-   ## Recent (48h)
-   <list>
-   
-   ## Dev Servers (PM2)
-   online: studio canvas lifeai ...   stopped: issho-invest
-   
-   ## Deployments
-   <green/red/yellow status>
-   
-   ## Recommended Next
-   <highest priority unstarted epic>
-   ```
-
-## Rules
-- Keep output concise — this is a glance, not a deep dive
-- Always end with a recommendation for what to work on next
-- After the Recommended Next section, suggest which guide file from `.rdc/guides/` (fallback: `.rdc/guides/`) the recommended work would need
-- Use database MCP for queries (not raw curl)
-- If infrastructure MCP is unavailable, skip deployment status and note it
+---
+name: rdc: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."
+---
+
+> **⚠️ 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.
+
+> 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`).
+
+
+# rdc:status — Project Dashboard
+
+## When to Use
+- Start of any session
+- Project lead asks "what's the status", "where are we", "what's open"
+- Before deciding what to work on next
+
+## Procedure
+
+1. **Open epics:**
+   ```sql
+   SELECT get_open_epics();
+   ```
+
+2. **Work item counts by status:**
+   ```sql
+   SELECT status, count(*) FROM work_items 
+   WHERE status != 'archived' 
+   GROUP BY status ORDER BY status;
+   ```
+
+3. **Items by label/project (top 10 labels):**
+   ```sql
+   SELECT unnest(labels) as label, count(*), 
+          count(*) FILTER (WHERE status = 'done') as done,
+          count(*) FILTER (WHERE status = 'todo') as todo,
+          count(*) FILTER (WHERE status = 'in_progress') as wip
+   FROM work_items 
+   GROUP BY label ORDER BY count DESC LIMIT 10;
+   ```
+
+4. **Recent activity (last 48 hours):**
+   ```sql
+   SELECT title, status, updated_at 
+   FROM work_items 
+   WHERE updated_at > now() - interval '48 hours'
+   ORDER BY updated_at DESC LIMIT 15;
+   ```
+
+5. **Git status:**
+   ```bash
+   git log --oneline -10
+   git status
+   git branch -v
+   ```
+
+6. **Dev server health (PM2):**
+   SSH into the Coolify server and check PM2 process state:
+   ```bash
+   # Note: clauth key name for the SSH key may vary by project. Common names: ssh-key-path, vultr-ssh-key, dev-ssh-key.
+   # Check available keys with: curl -s http://127.0.0.1:52437/list-services
+   SSH_KEY=$(curl -s http://127.0.0.1:52437/v/ssh-key-path)
+   ssh -i "$SSH_KEY" -o StrictHostKeyChecking=no root@64.237.54.189 "pm2 jlist 2>/dev/null"
+   ```
+   Parse the JSON array — for each process note `name`, `pm2_env.status` (online/stopped/errored), and `pm2_env.pm_uptime`.
+   If SSH fails or PM2 returns nothing, note "PM2 unreachable" and continue.
+
+7. **Infrastructure health** (if MCP available):
+   - Get infrastructure overview or diagnose issues
+   - Report any apps with failed builds or down containers
+
+8. **Present as a compact dashboard:**
+   ```
+   ## Open Epics (N)
+   <table>
+   
+   ## Work Items: X done | Y todo | Z in_progress
+   
+   ## Recent (48h)
+   <list>
+   
+   ## Dev Servers (PM2)
+   online: studio canvas lifeai ...   stopped: issho-invest
+   
+   ## Deployments
+   <green/red/yellow status>
+   
+   ## Recommended Next
+   <highest priority unstarted epic>
+   ```
+
+## Rules
+- Keep output concise — this is a glance, not a deep dive
+- Always end with a recommendation for what to work on next
+- After the Recommended Next section, suggest which guide file from `.rdc/guides/` (fallback: `.rdc/guides/`) the recommended work would need
+- Use database MCP for queries (not raw curl)
+- If infrastructure MCP is unavailable, skip deployment status and note it

package/skills/tests/MATRIX.md

@@ -0,0 +1,53 @@
+# RDC Skill Test Suite Matrix
+
+Current coverage: 29 manifests for 29 skill directories.
+
+The manifest layer verifies each skill can be started from a realistic caller prompt in an isolated `RDC_TEST=1` sandbox. The acceptance harness records the engine stream, extracted tool calls, stdout/stderr artifacts, rendered assistant output, failures, lessons learned, and next build optimizations under `.rdc/reports/`.
+
+`rdc:channel-formatter` currently has the strongest content acceptance fixture: it asserts source-grounded social-pack output, forbidden-claim absence, and observable corpus or web-search tool routing. `rdc:watch` adds a focus-safety negative check. The remaining manifests are basic behavioral smoke tests and should gain deeper acceptance assertions as each skill is touched.
+
+| Skill | Manifest | Fixture prompt class | Assertions | Acceptance depth |
+|---|---|---|---|---|
+| `rdc:brochure` | `rdc-brochure.test.json` | HTML-to-PDF brochure fixture | `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:build` | `rdc-build.test.json` | Unattended build from sandbox label | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:channel-formatter` | `rdc-channel-formatter.test.json` | Long article to social content pack | `exit_code`, `stdout_contains` | Output contains, output not contains, tool-call routing |
+| `rdc:co-develop` | `rdc-co-develop.test.json` | Coordination status | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:collab` | `rdc-collab.test.json` | Claude session relay fixture | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:convert` | `rdc-convert.test.json` | Markdown-to-Word conversion fixture | `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:deploy` | `rdc-deploy.test.json` | Deployment diagnosis | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:design` | `rdc-design.test.json` | Studio palette audit | `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:fixit` | `rdc-fixit.test.json` | Tiny sandbox typo fix | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:fs-mcp` | `rdc-fs-mcp.test.json` | File-system bridge read fixture | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:handoff` | `rdc-handoff.test.json` | Stub work handoff | `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:help` | `rdc-help.test.json` | Help menu rendering | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:housekeeping` | `rdc-housekeeping.test.json` | Read-only housekeeping audit | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:lifeai-brochure-author` | `rdc-lifeai-brochure-author.test.json` | JSX compliance review fixture | `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:overnight` | `rdc-overnight.test.json` | Label-based overnight queue drain | `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:plan` | `rdc-plan.test.json` | Health-endpoint planning prompt | `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:preplan` | `rdc-preplan.test.json` | Rate-limiter research prompt | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:prototype` | `rdc-prototype.test.json` | Tiny component prototype prompt | `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:rdc-brochurify` | `rdc-rdc-brochurify.test.json` | Read-only markdown Brochurify fixture | `exit_code`, `stdout_contains` | Sandbox output and no-follow-up negative checks |
+| `rdc:rdc-extract-verifier-rules` | `rdc-rdc-extract-verifier-rules.test.json` | Enhancement-log verifier fixture | `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:release` | `rdc-release.test.json` | Dry-run package release | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:report` | `rdc-report.test.json` | Unattended report generation | `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:review` | `rdc-review.test.json` | Unattended review gate | `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:rpms-filemap` | `rdc-rpms-filemap.test.json` | Canonical location lookup | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:self-test` | `rdc-self-test.test.json` | Strict self-test prompt | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:status` | `rdc-status.test.json` | Read-only status snapshot | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:terminal-config` | `rdc-terminal-config.test.json` | Hidden-window launch policy audit | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+| `rdc:watch` | `rdc-watch.test.json` | Watcher initialization prompt | `exit_code`, `stdout_contains` | Test-mode no-open output, tool-call routing, and focus-event negative checks |
+| `rdc:workitems` | `rdc-workitems.test.json` | Work-item epic listing | `commits_made`, `exit_code`, `stdout_contains` | Basic manifest |
+
+## What The Tests Accomplish
+
+- Verify every installed RDC skill has at least one executable caller-facing prompt.
+- Exercise the `RDC_TEST=1` sandbox contract so build tests do not publish, deploy, or mutate production services.
+- Capture observed engine events and extracted tool calls for periodic inspection.
+- Preserve stdout, stderr, and rendered assistant output as report artifacts.
+- Make content-producing skills eligible for deeper source-fidelity checks through the optional `acceptance` block.
+
+## Next Coverage Upgrades
+
+- Add tool-call assertions to read/research skills (`rdc:preplan`, `rdc:fs-mcp`, `rdc:co-develop`, `rdc:collab`).
+- Add artifact existence checks for output-producing skills (`rdc:brochure`, `rdc:convert`, `rdc:prototype`, `rdc:report`).
+- Add negative safety assertions for skills that open windows, launch terminals, deploy, release, or write commits.

package/skills/tests/README.md

@@ -1,7 +1,10 @@
 # Tier 2 Test Manifests
 
-Each rdc:* skill has a colocated test manifest at `skills/tests/rdc-<name>.test.json`.
-These drive the Tier 2 behavioral runner (`scripts/self-test.mjs --tier2`).
+Each RDC skill directory has a colocated test manifest at `skills/tests/rdc-<name>.test.json`.
+There are currently 29 manifests for 29 skill directories. These drive the Tier 2
+behavioral runner and the build acceptance harness.
+
+See `MATRIX.md` for the current skill-by-skill coverage table.
 
 ## Schema
 
@@ -13,14 +16,23 @@ is the source of truth. Top-level fields:
 - `description` (string) — what this test verifies
 - `fixture` (object) — prompt, precondition files, env vars
 - `assertions` (object) — what to check after the skill runs
+- `acceptance` (object, optional) — assistant output and recorded tool-call assertions
 - `teardown` (object) — cleanup policy
 
+`acceptance` supports:
+
+- `output_contains` — strings that must appear in the rendered assistant output
+- `output_not_contains` — strings that must not appear in the rendered assistant output
+- `tool_calls_include_any` — at least one recorded tool call with a listed name
+- `tool_calls_include_all` — all listed tool-call names must be recorded
+- `tool_calls_argument_matches` — tool-call argument regex matchers for source/corpus/tool routing checks
+
 ## Authoring a manifest
 
 1. Start from an existing manifest in this dir
 2. Set `fixture.env.RDC_TEST = "1"` (required — sandbox contract)
 3. Write assertions tight enough to catch real regressions but not flaky
-4. Run `node scripts/self-test.mjs --tier2 --skill rdc:<name>` to smoke-test
+4. Run `node scripts/acceptance.mjs --skill rdc:<name>` to capture the transcript, tool calls, and lessons learned
 5. Commit manifest + any skill changes together
 
 For content-producing skills, include both positive and negative output checks.

package/skills/tests/rdc-brochure.test.json

@@ -0,0 +1,20 @@
+{
+  "manifest_version": 1,
+  "skill": "rdc:brochure",
+  "description": "Brochure renders a small HTML fixture to a PDF artifact under RDC_TEST without modifying source inputs.",
+  "fixture": {
+    "prompt": "rdc:brochure docs/source/brochure-fixture.html --out .rdc/reports/brochure-fixture.pdf --format Letter",
+    "precondition_files": [
+      {
+        "path": "docs/source/brochure-fixture.html",
+        "content": "<!doctype html><html><head><meta charset=\"utf-8\"><title>Fixture Brochure</title><style>@page{size:Letter;margin:0.75in}body{font-family:serif}h1{color:#234}</style></head><body><h1>Fixture Brochure</h1><p>This is a tiny print-ready brochure fixture for RDC skill acceptance.</p></body></html>"
+      }
+    ],
+    "env": { "RDC_TEST": "1" }
+  },
+  "assertions": {
+    "exit_code": 0,
+    "stdout_contains": ["PDF", "Pages", "Size"]
+  },
+  "teardown": { "reset_branch": true }
+}

package/skills/tests/rdc-co-develop.test.json

@@ -0,0 +1,15 @@
+{
+  "manifest_version": 1,
+  "skill": "rdc:co-develop",
+  "description": "Co-develop status/list path is caller-safe under RDC_TEST and does not send a peer message.",
+  "fixture": {
+    "prompt": "rdc:co-develop status",
+    "env": { "RDC_TEST": "1" }
+  },
+  "assertions": {
+    "exit_code": 0,
+    "commits_made": { "min": 0 },
+    "stdout_contains": ["Verdict"]
+  },
+  "teardown": { "reset_branch": true }
+}

package/skills/tests/rdc-collab.test.json

@@ -0,0 +1,15 @@
+{
+  "manifest_version": 1,
+  "skill": "rdc:collab",
+  "description": "Collab validates the missing/fixture session path without mutating git under RDC_TEST.",
+  "fixture": {
+    "prompt": "rdc:collab --session self-test-fixture",
+    "env": { "RDC_TEST": "1" }
+  },
+  "assertions": {
+    "exit_code": 0,
+    "commits_made": { "min": 0 },
+    "stdout_contains": ["Verdict"]
+  },
+  "teardown": { "reset_branch": true }
+}

package/skills/tests/rdc-convert.test.json

@@ -0,0 +1,20 @@
+{
+  "manifest_version": 1,
+  "skill": "rdc:convert",
+  "description": "Convert exposes the portable build-corpus command reference and recognizes a caller conversion request under RDC_TEST.",
+  "fixture": {
+    "prompt": "rdc:convert help for converting markdown to Word in a sandbox; do not install packages or launch GUI",
+    "precondition_files": [
+      {
+        "path": "docs/source/convert-fixture.md",
+        "content": "# Convert Fixture\n\nThis markdown document proves the caller-facing convert path can accept a source file and report an output artifact.\n"
+      }
+    ],
+    "env": { "RDC_TEST": "1" }
+  },
+  "assertions": {
+    "exit_code": 0,
+    "stdout_contains": ["build-corpus", "Markdown", "Word"]
+  },
+  "teardown": { "reset_branch": true }
+}

package/skills/tests/rdc-fs-mcp.test.json

@@ -0,0 +1,21 @@
+{
+  "manifest_version": 1,
+  "skill": "rdc:fs-mcp",
+  "description": "FS MCP skill explains the local-script versus MCP access boundary for a read-only file task.",
+  "fixture": {
+    "prompt": "rdc:fs-mcp read docs/source/fs-mcp-fixture.md and summarize the access path",
+    "precondition_files": [
+      {
+        "path": "docs/source/fs-mcp-fixture.md",
+        "content": "# FS MCP Fixture\n\nThis fixture exists so the skill can demonstrate a read-only filesystem access handoff.\n"
+      }
+    ],
+    "env": { "RDC_TEST": "1" }
+  },
+  "assertions": {
+    "exit_code": 0,
+    "commits_made": { "min": 0 },
+    "stdout_contains": ["FS MCP", "access path"]
+  },
+  "teardown": { "reset_branch": true }
+}

package/skills/tests/rdc-help.test.json

@@ -0,0 +1,15 @@
+{
+  "manifest_version": 1,
+  "skill": "rdc:help",
+  "description": "Help renders the manifest-driven command reference and decision tree without external writes.",
+  "fixture": {
+    "prompt": "rdc:help",
+    "env": { "RDC_TEST": "1" }
+  },
+  "assertions": {
+    "exit_code": 0,
+    "commits_made": { "min": 0 },
+    "stdout_contains": ["rdc:help", "Decision tree"]
+  },
+  "teardown": { "reset_branch": true }
+}

package/skills/tests/rdc-housekeeping.test.json

@@ -0,0 +1,15 @@
+{
+  "manifest_version": 1,
+  "skill": "rdc:housekeeping",
+  "description": "Housekeeping audit runs read-only checks under RDC_TEST and reports a caller-facing verdict.",
+  "fixture": {
+    "prompt": "rdc:housekeeping",
+    "env": { "RDC_TEST": "1" }
+  },
+  "assertions": {
+    "exit_code": 0,
+    "commits_made": { "min": 0 },
+    "stdout_contains": ["Verdict"]
+  },
+  "teardown": { "reset_branch": true }
+}

package/skills/tests/rdc-lifeai-brochure-author.test.json

@@ -0,0 +1,20 @@
+{
+  "manifest_version": 1,
+  "skill": "rdc:lifeai-brochure-author",
+  "description": "LifeAI brochure author contract rejects raw HTML and returns brochure-kit component guidance.",
+  "fixture": {
+    "prompt": "rdc:lifeai-brochure-author review this JSX fixture for brochure-kit compliance: docs/source/brochure-author-fixture.tsx",
+    "precondition_files": [
+      {
+        "path": "docs/source/brochure-author-fixture.tsx",
+        "content": "export default function Fixture(){ return <div><h1>Raw HTML Fixture</h1><p>This should be rewritten with brochure-kit components.</p></div>; }\n"
+      }
+    ],
+    "env": { "RDC_TEST": "1" }
+  },
+  "assertions": {
+    "exit_code": 0,
+    "stdout_contains": ["brochure-kit", "Raw HTML"]
+  },
+  "teardown": { "reset_branch": true }
+}

package/skills/tests/rdc-rdc-brochurify.test.json

@@ -0,0 +1,23 @@
+{
+  "manifest_version": 1,
+  "skill": "rdc:rdc-brochurify",
+  "description": "Brochurify orchestrator accepts a markdown source fixture and reports sandboxed orchestration state.",
+  "fixture": {
+    "prompt": "rdc:rdc-brochurify docs/source/brochurify-fixture.md --mode read-only --theme editorial-neutral",
+    "precondition_files": [
+      {
+        "path": "docs/source/brochurify-fixture.md",
+        "content": "# Brochurify Fixture\n\nA short source document for a read-only brochure orchestration smoke test.\n"
+      }
+    ],
+    "env": { "RDC_TEST": "1" }
+  },
+  "assertions": {
+    "exit_code": 0,
+    "stdout_contains": ["Brochurify", "Wave 1"]
+  },
+  "acceptance": {
+    "output_not_contains": ["Want me to", "Would you like me to"]
+  },
+  "teardown": { "reset_branch": true }
+}

package/skills/tests/rdc-rdc-extract-verifier-rules.test.json

@@ -0,0 +1,20 @@
+{
+  "manifest_version": 1,
+  "skill": "rdc:rdc-extract-verifier-rules",
+  "description": "Verifier-rule extraction reads a tiny enhancement-log fixture and reports candidate-rule status without opening a PR.",
+  "fixture": {
+    "prompt": "rdc:rdc-extract-verifier-rules --since 2026-01-01 --auto-merge=false docs/source/enhancement-log-fixture.jsonl",
+    "precondition_files": [
+      {
+        "path": "docs/source/enhancement-log-fixture.jsonl",
+        "content": "{\"input_fingerprint\":\"fixture-1\",\"reason\":\"raw div used in brochure JSX\",\"snippet\":\"<div>bad</div>\"}\n{\"input_fingerprint\":\"fixture-1\",\"reason\":\"raw div used in brochure JSX\",\"snippet\":\"<div>bad</div>\"}\n{\"input_fingerprint\":\"fixture-1\",\"reason\":\"raw div used in brochure JSX\",\"snippet\":\"<div>bad</div>\"}\n"
+      }
+    ],
+    "env": { "RDC_TEST": "1" }
+  },
+  "assertions": {
+    "exit_code": 0,
+    "stdout_contains": ["candidate", "FP"]
+  },
+  "teardown": { "reset_branch": true }
+}

package/skills/tests/rdc-rpms-filemap.test.json

@@ -0,0 +1,15 @@
+{
+  "manifest_version": 1,
+  "skill": "rdc:rpms-filemap",
+  "description": "RPMS file map answers a placement question using canonical homes and Rule #1 language.",
+  "fixture": {
+    "prompt": "rdc:rpms-filemap where should a project report and entity context live?",
+    "env": { "RDC_TEST": "1" }
+  },
+  "assertions": {
+    "exit_code": 0,
+    "commits_made": { "min": 0 },
+    "stdout_contains": ["RULE #1", "Canonical"]
+  },
+  "teardown": { "reset_branch": true }
+}

package/skills/tests/rdc-self-test.test.json

@@ -0,0 +1,15 @@
+{
+  "manifest_version": 1,
+  "skill": "rdc:self-test",
+  "description": "Self-test strict mode validates all skill metadata and emits the package validation verdict.",
+  "fixture": {
+    "prompt": "rdc:self-test --strict",
+    "env": { "RDC_TEST": "1" }
+  },
+  "assertions": {
+    "exit_code": 0,
+    "commits_made": { "min": 0 },
+    "stdout_contains": ["PASS", "strict"]
+  },
+  "teardown": { "reset_branch": true }
+}

package/skills/tests/rdc-status.test.json

@@ -1,7 +1,6 @@
 {
   "manifest_version": 1,
   "skill": "rdc:status",
-  "timeout_ms": 180000,
   "description": "Status is read-only: prints kanban + health, makes no commits.",
   "fixture": {
     "prompt": "rdc:status",

package/skills/tests/rdc-terminal-config.test.json

@@ -0,0 +1,15 @@
+{
+  "manifest_version": 1,
+  "skill": "rdc:terminal-config",
+  "description": "Terminal config audits focus-safe launch policy without changing Windows Terminal settings.",
+  "fixture": {
+    "prompt": "rdc:terminal-config audit hidden-window launch policy and do not write settings",
+    "env": { "RDC_TEST": "1" }
+  },
+  "assertions": {
+    "exit_code": 0,
+    "commits_made": { "min": 0 },
+    "stdout_contains": ["hidden-window", "No settings written"]
+  },
+  "teardown": { "reset_branch": true }
+}

package/skills/tests/rdc-watch.test.json

@@ -0,0 +1,24 @@
+{
+  "manifest_version": 1,
+  "skill": "rdc:watch",
+  "description": "Watch initializes or describes the live viewer in RDC_TEST mode without launching a foreground browser.",
+  "fixture": {
+    "prompt": "rdc:watch",
+    "env": { "RDC_TEST": "1" }
+  },
+  "assertions": {
+    "exit_code": 0,
+    "stdout_contains": ["Verdict"]
+  },
+  "acceptance": {
+    "output_contains": ["not opened because RDC_TEST=1"],
+    "output_not_contains": ["SetForegroundWindow", "AppActivate", "BringWindowToTop", "SwitchToThisWindow"],
+    "tool_calls_argument_matches": [
+      {
+        "tools": ["Bash"],
+        "pattern": "watch-init\\.mjs"
+      }
+    ]
+  },
+  "teardown": { "reset_branch": true }
+}