prizmkit 1.1.130 → 1.1.131

package/bundled/skills/_metadata.json

@@ -1,29 +1,36 @@
 {
-  "version": "1.1.130",
+  "version": "1.1.131",
   "skills": {
     "prizmkit": {
-      "description": "Full-lifecycle dev toolkit. Covers spec-driven development, Prizm context docs, code quality, debugging, deployment, and knowledge management.",
+      "description": "Framework introduction and navigation for the formal single-requirement lifecycle, project initialization, Prizm docs, and independent deployment.",
+      "tier": "foundation",
+      "category": "prizmkit-skill",
+      "hasAssets": false,
+      "hasScripts": false
+    },
+    "prizmkit-workflow": {
+      "description": "Composite L1 workflow for one explicitly requested formal requirement: plan → implement → code-review → test → retrospective → committer, with stable artifact identity and deterministic repair routing.",
       "tier": "foundation",
       "category": "prizmkit-skill",
       "hasAssets": false,
       "hasScripts": false
     },
     "prizmkit-init": {
-      "description": "Project takeover and bootstrap. Scans any project, generates Prizm docs, configures hooks.",
+      "description": "Recommended one-time project initialization. Scans greenfield or brownfield projects, generates Prizm docs and a project brief, and provides soft-prerequisite context for formal requirements.",
       "tier": "foundation",
       "category": "prizmkit-skill",
       "hasAssets": false,
       "hasScripts": false
     },
     "prizmkit-plan": {
-      "description": "Specify and plan tasks: natural language → spec.md → plan.md with architecture and executable tasks.",
+      "description": "Formal requirement lifecycle entry: natural language → reviewed spec.md and plan.md with stable artifact identity and workflow-state handoff.",
       "tier": "1",
       "category": "prizmkit-skill",
       "hasAssets": true,
       "hasScripts": false
     },
     "prizmkit-implement": {
-      "description": "Execute implementation following plan.md Tasks section with TDD approach.",
+      "description": "Execute a reviewed formal requirement plan, preserve artifact identity, and route implementation repairs to the correct review or test gate.",
       "tier": "1",
       "category": "prizmkit-skill",
       "hasAssets": false,
@@ -37,14 +44,14 @@
       "hasScripts": true
     },
     "prizmkit-committer": {
-      "description": "Pure git commit workflow with safety checks. Does NOT modify .prizmkit/prizm-docs/.",
+      "description": "Final formal-requirement commit gate: verifies all prior stages, confirms interactive commits or performs authorized L4-headless local commits, and never pushes automatically.",
       "tier": "1",
       "category": "prizmkit-skill",
       "hasAssets": false,
       "hasScripts": false
     },
     "prizmkit-retrospective": {
-      "description": "Sole .prizmkit/prizm-docs/ maintainer. Structural sync + TRAPS/RULES/DECISIONS injection to architecture index. Run after code review passes, before committing.",
+      "description": "Mandatory formal-requirement retrospective: updates durable Prizm docs or records NO_DOC_CHANGE with machine-verifiable result before commit.",
       "tier": "1",
       "category": "prizmkit-skill",
       "hasAssets": true,
@@ -58,21 +65,21 @@
       "hasScripts": false
     },
     "prizmkit-deploy": {
-      "description": "Universal deployment gateway: auto-discovers project type and target, routes to SSH automation (PM2 + Nginx + blue/green), guided cloud/Docker deployment, or documentation fallback. Also operates existing deployments (status/logs/restart/rollback).",
+      "description": "Universal deployment and operations entry point, independent of the six-stage formal requirement lifecycle.",
       "tier": "1",
       "category": "prizmkit-skill",
       "hasAssets": false,
       "hasScripts": false
     },
     "prizmkit-test": {
-      "description": "Auditable project-native test evidence with request-driven execution, runner-generated receipts, differential proof, replay, and deterministic validation.",
+      "description": "Mandatory post-review auditable test evidence with TEST_PASS/TEST_FAIL/TEST_BLOCKED verdicts, repair-scope routing, differential proof, replay, and deterministic validation.",
       "tier": "1",
       "category": "prizmkit-skill",
       "hasAssets": true,
       "hasScripts": true
     },
     "feature-workflow": {
-      "description": "One-stop entry point for feature development. Orchestrates feature-planner → feature-pipeline-launcher → background execution. Handles multi-feature batch development from a single request.",
+      "description": "Thin feature scenario router. Clarifies whether the request needs direct single-requirement guidance, app planning, feature planning, or command construction from an existing feature list.",
       "tier": "companion",
       "category": "orchestration-skill",
       "subcategory": "workflows",
@@ -80,7 +87,7 @@
       "hasScripts": false
     },
     "refactor-workflow": {
-      "description": "One-stop entry point for code refactoring. Orchestrates refactor-planner → refactor-pipeline-launcher → execution.",
+      "description": "Thin behavior-preserving refactor scenario router. Clarifies direct guidance, refactor planning, existing-list command construction, or feature rerouting when behavior must change.",
       "tier": "companion",
       "category": "orchestration-skill",
       "subcategory": "workflows",
@@ -88,23 +95,23 @@
       "hasScripts": false
     },
     "bug-planner": {
-      "description": "Interactive bug planning that produces bug-fix-list.json. Supports stack traces, user reports, failed tests, log patterns, monitoring alerts.",
+      "description": "Plan, append, validate, and summarize bug-fix-list.json from user reports, stack traces, failed tests, logs, and monitoring alerts.",
       "tier": "companion",
       "category": "orchestration-skill",
       "subcategory": "pipelines",
-      "hasAssets": false,
-      "hasScripts": false
+      "hasAssets": true,
+      "hasScripts": true
     },
     "app-planner": {
-      "description": "Plan a new application from scratch — vision, tech stack, feature decomposition, and validated feature-list.json.",
+      "description": "Capture application vision, tech stack, project conventions, infrastructure decisions, development rules, architecture decisions, and project-brief.md without generating feature-list.json.",
       "tier": "companion",
       "category": "orchestration-skill",
       "subcategory": "pipelines",
-      "hasAssets": true,
-      "hasScripts": true
+      "hasAssets": false,
+      "hasScripts": false
     },
     "feature-planner": {
-      "description": "Interactive planning for new apps and incremental features; outputs validated feature-list.json for dev-pipeline.",
+      "description": "Plan, append, reprioritize, split, validate, and summarize features for an existing project; outputs validated feature-list.json.",
       "tier": "companion",
       "category": "orchestration-skill",
       "subcategory": "pipelines",
@@ -112,7 +119,7 @@
       "hasScripts": true
     },
     "feature-pipeline-launcher": {
-      "description": "Launch and manage the dev-pipeline from within an AI CLI session. Start pipeline in background, monitor logs, check status, stop pipeline.",
+      "description": "Build feature pipeline start, status, logs, stop, and safe retry commands from a validated feature-list.json without executing them.",
       "tier": "companion",
       "category": "orchestration-skill",
       "subcategory": "pipelines",
@@ -120,7 +127,7 @@
       "hasScripts": false
     },
     "bugfix-pipeline-launcher": {
-      "description": "Launch and manage the bugfix pipeline from within a CLI session.",
+      "description": "Build bugfix pipeline start, status, logs, stop, and safe retry commands from a validated bug-fix-list.json without executing them.",
       "tier": "companion",
       "category": "orchestration-skill",
       "subcategory": "pipelines",
@@ -136,7 +143,7 @@
       "hasScripts": true
     },
     "refactor-pipeline-launcher": {
-      "description": "Launch and manage the refactor pipeline from within an AI CLI session.",
+      "description": "Build refactor pipeline prerequisite, start, status, logs, stop, and safe retry commands from a validated refactor-list.json without executing them.",
       "tier": "companion",
       "category": "orchestration-skill",
       "subcategory": "pipelines",
@@ -144,7 +151,7 @@
       "hasScripts": false
     },
     "bug-fix-workflow": {
-      "description": "Interactive single-bug fix in current session. Guides triage → reproduce → fix → review → commit without background pipeline.",
+      "description": "Thin bug scenario router. Performs lightweight diagnosis only to choose direct guidance, bug planning, or command construction from an existing bug list.",
       "tier": "companion",
       "category": "orchestration-skill",
       "subcategory": "workflows",
@@ -152,7 +159,7 @@
       "hasScripts": false
     },
     "recovery-workflow": {
-      "description": "Recover and resume interrupted feature pipeline sessions. Detects partial work from failed or interrupted sessions and resumes from the correct phase.",
+      "description": "Detect whether interrupted work belongs to a direct requirement or autonomous pipeline, select the authoritative owner, and hand off without merging state machines.",
       "tier": "companion",
       "category": "orchestration-skill",
       "subcategory": "workflows",
@@ -165,6 +172,7 @@
       "description": "All skills: full spec-driven cycle + orchestration + planning + recovery",
       "skills": [
         "prizmkit",
+        "prizmkit-workflow",
         "prizmkit-init",
         "prizmkit-prizm-docs",
         "prizmkit-plan",
@@ -188,16 +196,45 @@
       ]
     },
     "minimal": {
-      "description": "Minimal closed-loop workflow: full spec-driven cycle with .prizmkit/prizm-docs/ architecture sync and code review",
+      "description": "Minimal single-requirement lifecycle: composite workflow plus all six formal stages and Prizm documentation sync",
+      "skills": [
+        "prizmkit",
+        "prizmkit-workflow",
+        "prizmkit-init",
+        "prizmkit-prizm-docs",
+        "prizmkit-plan",
+        "prizmkit-implement",
+        "prizmkit-code-review",
+        "prizmkit-test",
+        "prizmkit-retrospective",
+        "prizmkit-committer"
+      ]
+    },
+    "recommended": {
+      "description": "Recommended single-requirement lifecycle with optional scenario orchestration; base lifecycle is always complete",
       "skills": [
         "prizmkit",
+        "prizmkit-workflow",
         "prizmkit-init",
         "prizmkit-prizm-docs",
         "prizmkit-plan",
         "prizmkit-implement",
         "prizmkit-code-review",
+        "prizmkit-test",
+        "prizmkit-retrospective",
         "prizmkit-committer",
-        "prizmkit-retrospective"
+        "feature-workflow",
+        "refactor-workflow",
+        "bug-fix-workflow",
+        "recovery-workflow",
+        "app-planner",
+        "feature-planner",
+        "bug-planner",
+        "refactor-planner",
+        "feature-pipeline-launcher",
+        "bugfix-pipeline-launcher",
+        "refactor-pipeline-launcher",
+        "prizmkit-deploy"
       ]
     }
   },

package/bundled/skills/app-planner/SKILL.md

@@ -12,7 +12,7 @@ Plan an application from idea to actionable project context through interactive
 - Architecture decision capture
 - Project brief accumulation (`.prizmkit/plans/project-brief.md`)
 
-This skill captures **project-level context only**: vision, tech stack, conventions, architecture decisions, and project brief. It does not do feature decomposition. (See **Scope Boundary** for the authoritative output rules.)
+This skill captures **project-level planning context only**: vision, tech stack, conventions, architecture decisions, and project brief. It defines a new application or completes missing app-level context; it does not decompose features, implement source code, or start execution. (See **Scope Boundary** for the authoritative output rules.)
 
 For adding features to an **existing** project that already has a project brief, use `feature-planner` directly.
 
@@ -27,7 +27,7 @@ If you believe the task is better suited for a different workflow, you MUST:
 
 ## Scope Boundary (Hard Rule)
 
-**This skill is PLANNING ONLY.** You must NEVER:
+**This skill is PLANNING ONLY.** It creates or updates only the application-planning artifacts listed below. It must never implement source code or prepare, configure, launch, or monitor an implementation pipeline. You must NEVER:
 - Create, modify, or delete source code files (*.js, *.ts, *.py, *.go, *.html, *.css, etc.)
 - Create project scaffolding, directories, or boilerplate (exception: `.prizmkit/rules/` and `.prizmkit/prizm-docs/` directories may be created for dev rules and root.prizm output)
 - Run build/install/test commands (npm init, pip install, etc.)
@@ -52,8 +52,9 @@ If you believe the task is better suited for a different workflow, you MUST:
 **After planning is complete**, you MUST:
 1. Present the summary of captured project-level context (vision, conventions, architecture decisions, project brief)
 2. List the artifacts produced and suggest possible next steps (e.g., `feature-planner`, `prizmkit-plan`, etc.) — but do NOT auto-invoke any of them
-3. **NEVER auto-execute** the pipeline, feature-planner, or any implementation step
+3. **NEVER auto-execute** a pipeline, launcher, composite workflow, or any implementation step
 4. **NEVER generate `feature-list.json`** — that is exclusively `feature-planner`'s responsibility
+5. Return the completed planning context to the caller. Direct implementation and planned pipeline execution are separate next steps; this planner is not an execution intermediary
 
 ## When to Use