bigpowers 1.0.0 → 1.1.0

package/CHANGELOG.md

@@ -1,3 +1,17 @@
+# [1.1.0](https://github.com/danielvm-git/bigpowers/compare/v1.0.0...v1.1.0) (2026-05-31)
+
+
+### Bug Fixes
+
+* **ci:** pass NODE_AUTH_TOKEN for setup-node npmrc auth ([03d58ee](https://github.com/danielvm-git/bigpowers/commit/03d58ee1c9a6b4f7c6c34f822f98363e1493f93e))
+
+
+### Features
+
+* **skills:** add and update a large number of skills ([a51d802](https://github.com/danielvm-git/bigpowers/commit/a51d802ccb1ebcd327e6ff7ef9d7e1471d62ca8e))
+* **skills:** add Project README artifact type to write-document ([43f9f84](https://github.com/danielvm-git/bigpowers/commit/43f9f8473f221374ba8bfe326f8bf604cc213d7e))
+* **workflow:** add solo git profile with land-branch.sh ([1840cd0](https://github.com/danielvm-git/bigpowers/commit/1840cd0011fc522825b72bb10a3f8d16886d902e))
+
 # 1.0.0 (2026-05-23)
 
 

package/CLAUDE.md

@@ -4,21 +4,23 @@ Read CONVENTIONS.md before any GitHub or git operation.
 
 ## Project
 
-bigpowers — 44 agent skills for spec-driven, test-first software development by solo developers.
+bigpowers — 58 agent skills for spec-driven, test-first software development by solo developers.
 Stack: Markdown / Bash (documentation-based; skills integrate with Claude Code, Cursor, Gemini CLI)
 
 ## Commands
 
-| Action | Command |
-|--------|---------|
-| Run    | `bash scripts/sync-skills.sh` |
-| Test   | N/A (documentation project) |
-| Build  | `bash scripts/install.sh` |
-| Lint   | `bash scripts/sync-skills.sh` (validates SKILL.md syntax) |
+| Action  | Command |
+|---------|---------|
+| Install | `npx bigpowers` or `npm install -g bigpowers` |
+| Run     | `bash scripts/sync-skills.sh` |
+| Test    | N/A (documentation project) |
+| Build   | `bash scripts/install.sh` (from source) |
+| Lint    | `bash scripts/sync-skills.sh` (validates SKILL.md syntax) |
+| Compliance | `npm run compliance` |
 
 ## Architecture
 
-Collection of 44 verb-noun skills, each with a SKILL.md source file and supporting documentation. The sync-skills.sh script auto-generates artifacts for Cursor (.cursor/rules) and Gemini CLI (.gemini/extensions/bigpowers/) from SKILL.md sources. All planning and spec output goes to specs/ at the project root.
+Collection of 58 verb-noun skills, each with a SKILL.md source file and supporting documentation. Includes Verify phase (verify-work, run-evals) and optional stack profiles in profiles/. The sync-skills.sh script auto-generates artifacts for Cursor (.cursor/rules) and Gemini CLI (.gemini/extensions/bigpowers/) from SKILL.md sources. All planning and spec output goes to specs/ at the project root.
 
 ## Conventions
 

package/CONVENTIONS.md

@@ -17,7 +17,9 @@ All changes to this repository MUST follow the [Conventional Commits 1.0.0](http
 ## GitHub & Git Operations
 
 - No direct work on `main` or `master`. Every task MUST start with a feature branch or worktree via `kickoff-branch`.
-- Use `gh pr create` not `git push` + manual PR
+- **Integrate (team default):** Use `gh pr create` and `gh pr merge --squash` via `release-branch` (team-pr mode). Prefer `gh` over ad-hoc `git push` + manual PR UI.
+- **Integrate (solo profile):** When `profiles/solo-git.md` or `specs/WORKFLOW-solo-git.md` is active, ship with `bash scripts/land-branch.sh <branch> "<conventional message>"` after `release-branch` gates — local squash to `main`, then push. PR is optional (remote CI / branch protection only).
+- `git push origin <feature-branch>` is allowed for backup or CI; never push directly to `main`/`master` except via `land-branch.sh` (`GIT_BIGPOWERS_LAND=1`).
 - Use `gh repo clone` not `git clone` for GitHub repos
 - Use `gh run view` / `gh run watch` for CI status
 - Verify auth with `gh auth status` before operations
@@ -50,10 +52,11 @@ Every skill that produces written output writes to `specs/` at the project root:
 | Scope definition | `specs/SCOPE.md` |
 | Task breakdown | `specs/TASKS.md` |
 | Implementation plan | `specs/PLAN.md` (or `specs/PLAN-<feature>.md`) |
+| Project README | `README.md` (project root) |
 | Refactor plan | `specs/REFACTOR.md` |
 | Spike learnings | `specs/SPIKE-<name>.md` |
-| Bug investigation | `specs/DIAGNOSIS.md` |
-| QA session log | `specs/BUG-LOG.md` |
+| Bug investigation | `specs/bugs/BUG-*.md` |
+| QA session log | `specs/bugs/BUG-LOG.md` |
 
 ## Code Style
 
@@ -72,6 +75,8 @@ Every skill that produces written output writes to `specs/` at the project root:
 - Prefer exceptions over error codes: throw/raise an exception rather than returning a numeric or boolean error sentinel.
 - Remove dead code (G9/F4): unused functions, unreachable branches, and stale imports must be deleted — not commented out.
 - Boy Scout Rule: leave every file you touch at least as clean as you found it. Fix the first broken window you see.
+- **Law of Demeter:** A method should call only its immediate collaborators — not `a.getB().getC().doX()`. Chain violations need explicit justification in code review.
+- **Verification mandate:** Every story in `specs/RELEASE-PLAN.md` must include a `## Verification Script`. No story is done until `verify-work` confirms it (or user explicitly waives with documented reason in STATE.md).
 - Exception messages must include the offending value, expected shape, and an actionable remediation hint for the agent.
 - SOLID beyond SRP: favor interfaces over concrete types (DIP) when injecting dependencies.
 

package/GEMINI.md

@@ -6,21 +6,22 @@ Read CONVENTIONS.md before any GitHub or git operation.
 
 ## Project
 
-bigpowers — 44 agent skills for spec-driven, test-first software development by solo developers.
+bigpowers — 58 agent skills for spec-driven, test-first software development by solo developers.
 Stack: Markdown / Bash (documentation-based; skills integrate with Claude Code, Cursor, Gemini CLI)
 
 ## Commands
 
-| Action | Command |
-|--------|---------|
-| Run    | `bash scripts/sync-skills.sh` |
-| Test   | N/A (documentation project) |
-| Build  | `bash scripts/install.sh` |
-| Lint   | `bash scripts/sync-skills.sh` (validates SKILL.md syntax) |
+| Action  | Command |
+|---------|---------|
+| Install | `npx bigpowers` or `npm install -g bigpowers` |
+| Run     | `bash scripts/sync-skills.sh` |
+| Test    | N/A (documentation project) |
+| Build   | `bash scripts/install.sh` (from source) |
+| Lint    | `bash scripts/sync-skills.sh` (validates SKILL.md syntax) |
 
 ## Architecture
 
-Collection of 44 verb-noun skills, each with a SKILL.md source file and supporting documentation. The sync-skills.sh script auto-generates artifacts for Cursor (.cursor/rules) and Gemini CLI (.gemini/extensions/bigpowers/) from SKILL.md sources. All planning and spec output goes to specs/ at the project root.
+Collection of 58 verb-noun skills, each with a SKILL.md source file and supporting documentation. Includes Verify phase and profiles/. The sync-skills.sh script auto-generates artifacts for Cursor (.cursor/rules) and Gemini CLI (.gemini/extensions/bigpowers/) from SKILL.md sources. All planning and spec output goes to specs/ at the project root.
 
 ## Conventions
 

package/README.md

@@ -1,25 +1,39 @@
 # bigpowers — Best-in-Class Agentic Skills
 
 ![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)
-![Version](https://img.shields.io/badge/version-1.14.0-blue.svg)
-![Skills](https://img.shields.io/badge/skills-44+-brightgreen.svg)
+![npm version](https://img.shields.io/npm/v/bigpowers.svg)
+![Skills](https://img.shields.io/badge/skills-58-brightgreen.svg)
 
-**44+ agent skills for high-integrity, spec-driven, test-first software development by solo developers.**
+**58 agent skills for high-integrity, spec-driven, test-first software development by solo developers.**
 
 `bigpowers` provides a prescriptive, vertical-slice methodology for building software with AI agents (Claude Code, Gemini CLI, Cursor). It bridges the gap between raw LLM capabilities and professional engineering standards.
 
+Published on npm: [bigpowers@1.0.0](https://www.npmjs.com/package/bigpowers)
+
 ---
 
 ## 🚀 Quick Start
 
+### npm (recommended)
+
 ```bash
-# 1. Clone the repository
-git clone https://github.com/danielvm-git/bigpowers.git && cd bigpowers
+# One-shot setup — downloads, syncs artifacts, and links skills to your tools
+npx bigpowers
 
-# 2. Install globally (links to Claude, Gemini, and Cursor)
-bash scripts/install.sh
+# Or install globally and run the setup command anytime
+npm install -g bigpowers
+bigpowers
+```
+
+Both commands sync skill artifacts and link them to Claude Code, Gemini CLI, and Cursor (see [Prerequisites](#-prerequisites)).
 
-# 3. Sync artifacts
+### From source (contributors)
+
+```bash
+git clone https://github.com/danielvm-git/bigpowers.git && cd bigpowers
+npm install          # runs postinstall: sync + link
+# or manually:
+bash scripts/install.sh
 npm run sync
 ```
 
@@ -28,7 +42,7 @@ npm run sync
 ## 🛠 Prerequisites
 
 - **Bash**: Required for all scripts.
-- **Node.js**: Required for `npm` commands.
+- **Node.js**: v14+ (required for npm/npx).
 - **jq**: (Highly Recommended) Used for robust configuration of tool settings.
 - **AI Tools**: One or more of:
   - [Claude Code](https://claude.ai/code)
@@ -40,36 +54,58 @@ npm run sync
 ## 🔄 Maintenance (Update & Uninstall)
 
 ### Update
-To get the latest skills and performance improvements:
+
+**npm install:**
+
+```bash
+npm update -g bigpowers
+bigpowers    # re-sync and refresh symlinks
+```
+
+**git clone:**
+
 ```bash
 git pull
 npm run sync
 ```
-*Note: Since the installation uses symlinks, syncing automatically updates the tools.*
+
+*Install uses symlinks — re-running setup refreshes links without duplicating files.*
 
 ### Uninstall
-To remove all managed symlinks and configuration hooks:
+
+**npm install:**
+
+```bash
+bash "$(npm root -g)/bigpowers/scripts/install.sh" --uninstall
+npm uninstall -g bigpowers
+```
+
+**git clone:**
+
 ```bash
 bash scripts/install.sh --uninstall
 ```
 
 ### Reinstall
-If you need a fresh start:
+
 ```bash
-bash scripts/install.sh --uninstall && bash scripts/install.sh
+npx bigpowers
+# or, if installed globally:
+bigpowers
 ```
 
 ---
 
 ## 🏗 The BMAD Lifecycle
 
-Every task in `bigpowers` follows a prescriptive 5-phase arc to ensure integrity:
+Every task in `bigpowers` follows a prescriptive lifecycle (see `SKILL-INDEX.md`):
 
-1.  **Discover**: Investigate context, map unknowns, and survey requirements.
-2.  **Elaborate**: Formalize specs and lock design decisions (ADRs).
-3.  **Plan**: Write a verifiable, Karpathy-style implementation roadmap.
-4.  **Build**: Execute via TDD, vertical slices, and small commits.
-5.  **Sustain**: Audit quality, verify compliance, and release.
+1.  **Discover**: survey-context, research-first, elaborate-spec.
+2.  **Elaborate / Plan**: scope-work, plan-work, slice-tasks.
+3.  **Build**: develop-tdd, execute-plan.
+4.  **Verify**: verify-work, run-evals — prove it works before review.
+5.  **Review / Release**: audit-code, request-review, release-branch.
+6.  **Sustain**: stocktake-skills, evolve-skill (benchmark-gated).
 
 ---
 
@@ -93,7 +129,7 @@ Every task in `bigpowers` follows a prescriptive 5-phase arc to ensure integrity
 - `scripts/`: Installation, syncing, and compliance tools.
 - `specs/`: The "Brain" of your project — all planning and decisions live here.
 - `docs/references/`: Theoretical foundations (Uncle Bob, Ousterhout, Karpathy, etc.).
-- `[skill-name]/`: Source files for each of the 44+ skills.
+- `[skill-name]/`: Source files for each of the 58 skills.
 
 ---
 

package/RELEASE.md

@@ -1,5 +1,7 @@
 # Release & Publishing Guide
 
+Package: [bigpowers on npm](https://www.npmjs.com/package/bigpowers)
+
 ## Quick Start
 
 ### 1. Setup (one-time)
@@ -68,6 +70,8 @@ See `.github/CONVENTIONAL-COMMITS.md` for full format.
 
 ## Manual Release (Local)
 
+For full semantic-release (GitHub + npm + changelog):
+
 ```bash
 export GITHUB_TOKEN=$(gh auth token)
 export NPM_TOKEN=[from npmjs.org]
@@ -75,6 +79,12 @@ export NPM_TOKEN=[from npmjs.org]
 npm run release
 ```
 
+To publish the current `package.json` version to npm only:
+
+```bash
+npm publish
+```
+
 ## Version History
 
 All releases in:

package/SKILL-INDEX.md

@@ -2,88 +2,97 @@
 
 **Purpose:** One canonical reference for all bigpowers skills. Referenced by README.md, RELEASE-PLAN.md, and CONVENTIONS.md. Updated per-release.
 
-**Last updated:** 2026-05-20 (v2.1.0 — reconciled orphan/ghost skills; 44 active, 6 planned)
+**Last updated:** 2026-05-25 (v3.0.0 — consolidation release; 58 active, 0 planned, Verify phase)
 
 ---
 
 ## Quick Navigation by BMAD Phase
 
-| Phase | Active | Planned | Skills |
-|---|---|---|---|
-| **Bootstrap** | 1 | — | using-bigpowers |
-| **Orchestrate** | 1 | — | orchestrate-project |
-| **Discover** | 3 | — | survey-context, elaborate-spec, map-codebase |
-| **Elaborate** | 5 | 1 | model-domain, define-language, grill-me, deepen-architecture, design-interface · _(grill-with-docs 📋)_ |
-| **Plan** | 6 | 2 | assess-impact, change-request, define-success, plan-work, plan-refactor, plan-release · _(scope-work 📋, slice-tasks 📋)_ |
-| **Spike** | 1 | — | spike-prototype |
-| **Initiate** | 4 | — | kickoff-branch, guard-git, hook-commits, seed-conventions |
-| **Build** | 5 | — | develop-tdd, enforce-first, delegate-task, dispatch-agents, execute-plan |
-| **Harden** | 1 | — | wire-observability |
-| **Bug** | 2 | 1 | investigate-bug, validate-fix · _(diagnose-root 📋)_ |
-| **Review** | 4 | — | audit-code, request-review, respond-review, trace-requirement |
-| **Integrate** | 2 | — | commit-message, release-branch |
-| **Sustain** | 2 | — | inspect-quality, organize-workspace |
-| **Utility** | 7 | 2 | terse-mode, craft-skill, edit-document, session-state, migrate-spec, visual-dashboard, write-document · _(setup-environment 📋, reset-baseline 📋)_ |
-| **TOTAL** | **44** | **6** | |
+| Phase | Active | Skills |
+|---|---|---|
+| **Bootstrap** | 1 | using-bigpowers |
+| **Orchestrate** | 1 | orchestrate-project |
+| **Discover** | 4 | survey-context, research-first, elaborate-spec, map-codebase |
+| **Elaborate** | 6 | model-domain, define-language, grill-me, grill-with-docs, deepen-architecture, design-interface |
+| **Plan** | 8 | assess-impact, change-request, scope-work, slice-tasks, define-success, plan-work, plan-refactor, plan-release |
+| **Spike** | 1 | spike-prototype |
+| **Initiate** | 4 | kickoff-branch, guard-git, hook-commits, seed-conventions |
+| **Build** | 5 | develop-tdd, enforce-first, delegate-task, dispatch-agents, execute-plan |
+| **Harden** | 1 | wire-observability |
+| **Verify** | 2 | verify-work, run-evals |
+| **Bug** | 3 | investigate-bug, diagnose-root, validate-fix |
+| **Review** | 4 | audit-code, request-review, respond-review, trace-requirement |
+| **Integrate** | 2 | commit-message, release-branch |
+| **Sustain** | 4 | inspect-quality, organize-workspace, stocktake-skills, evolve-skill |
+| **Utility** | 12 | terse-mode, craft-skill, edit-document, session-state, migrate-spec, visual-dashboard, write-document, setup-environment, reset-baseline, search-skills, compose-workflow, simulate-agents |
+| **TOTAL** | **58** | |
 
 ---
 
 ## Full Reference Table
 
-| # | Phase | Skill | Intent | Artefact Output | Status | Source |
-|---|---|---|---|---|---|---|
-| 1 | Bootstrap | `using-bigpowers` | Lifecycle intro; where to start | (dialogue) | ✅ Active | original |
-| 2 | Orchestrate | `orchestrate-project` | Meta-skill enforcing 6-phase core loop (Standard / Fast-Track / Ad-Hoc modes) | (orchestration) | ✅ Active | original v2.0.0 |
-| 3 | Discover | `survey-context` | Per-task context map; suggests next skill | (dialogue, update STATE.md) | ✅ Active | mattpocock/skills (zoom-out) |
-| 4 | Discover | `elaborate-spec` | Dialogue to refine rough idea into spec | (dialogue) | ✅ Active | superpowers/brainstorming |
-| 5 | Discover | `map-codebase` | High-fidelity codebase survey; stack, architecture, gray areas | CODEBASE-MAP.md | ✅ Active | original |
-| 6 | Elaborate | `model-domain` | Interactive domain model; updates CONTEXT.md | CONTEXT.md, adr/ | ✅ Active | mattpocock/skills (domain-model) |
-| 7 | Elaborate | `define-language` | Extract ubiquitous language glossary | UBIQUITOUS_LANGUAGE.md | ✅ Active | mattpocock/skills (ubiquitous-language) |
-| 8 | Elaborate | `grill-me` | Stress-test design by grilling assumptions (Design mode + Docs mode) | (dialogue, refine design) | ✅ Active | mattpocock/skills (grill-me) |
-| 9 | Elaborate | `grill-with-docs` | Grill assumptions grounded in real library docs | (dialogue, refine design) | 📋 Planned | mattpocock/skills (grill-with-docs) |
-| 10 | Elaborate | `deepen-architecture` | Surface architecture deepening opportunities (Ousterhout deep modules) | (dialogue, update CONTEXT.md) | ✅ Active | mattpocock/skills (improve-codebase-architecture) |
-| 11 | Elaborate | `design-interface` | Generate multiple radically different interface designs via parallel subagents | INTERFACE-OPTIONS.md | ✅ Active | original |
-| 12 | Plan | `assess-impact` | Analyze blast radius of a proposed change before any code is written | IMPACT.md | ✅ Active | original |
-| 13 | Plan | `change-request` | Add a new requirement or reorder epics by WSJF against RELEASE-PLAN.md | (updated RELEASE-PLAN.md) | ✅ Active | original |
-| 14 | Plan | `scope-work` | Define what's in/out → SCOPE.md | SCOPE.md | 📋 Planned | mattpocock/skills (to-prd, adapted: local-first) |
-| 15 | Plan | `slice-tasks` | Break work into vertical slices → TASKS.md | TASKS.md | 📋 Planned | mattpocock/skills (to-issues, adapted: local-first) |
-| 16 | Plan | `define-success` | Convert imperative task to step → verify pairs | (dialogue, feed to plan-work) | ✅ Active | Karpathy principle |
-| 17 | Plan | `plan-work` | Write detailed plan with verify steps | PLAN.md | ✅ Active | superpowers/writing-plans + Karpathy verify-template |
-| 18 | Plan | `plan-refactor` | Plan a refactor via interview | REFACTOR.md | ✅ Active | mattpocock/skills (request-refactor-plan, adapted) |
-| 19 | Plan | `plan-release` | Convert elaborated specs into a release plan with Gherkin acceptance criteria | RELEASE-PLAN.md | ✅ Active | original |
-| 20 | Spike | `spike-prototype` | Throw-away spike for unknown problem spaces | SPIKE-<name>.md | ✅ Active | mattpocock/skills (prototype) |
-| 21 | Initiate | `kickoff-branch` | Create worktree + branch + verify test baseline | (git state) | ✅ Active | superpowers/using-git-worktrees |
-| 22 | Initiate | `guard-git` | Block dangerous git commands via pre-command hooks | (git state) | ✅ Active | mattpocock/skills (git-guardrails) |
-| 23 | Initiate | `hook-commits` | Install pre-commit: lint, format, typecheck, test | (git state) | ✅ Active | mattpocock/skills (setup-pre-commit) |
-| 24 | Initiate | `seed-conventions` | Generate CLAUDE.md + CONVENTIONS.md + specs/ scaffold | CLAUDE.md, CONVENTIONS.md, specs/ | ✅ Active | Akita "writing CLAUDE.md is a skill" |
-| 25 | Build | `develop-tdd` | Red → green → refactor TDD loop | src/ (code) | ✅ Active | superpowers/tdd + mattpocock/tdd (override) |
-| 26 | Build | `enforce-first` | F.I.R.S.T test-quality rubric (Fast, Independent, Repeatable, Self-Validating, Timely) | (checklist) | ✅ Active | Clean Code Ch.9 + Akita |
-| 27 | Build | `delegate-task` | One subagent, one task, sequential + two-stage review | (code + review) | ✅ Active | superpowers/subagent-driven-development |
-| 28 | Build | `dispatch-agents` | Multiple subagents in parallel on independent tasks | (code + review) | ✅ Active | superpowers/dispatching-parallel-agents |
-| 29 | Build | `execute-plan` | Batch execute plan tasks sequentially with checkpoints | src/ (code per task) | ✅ Active | superpowers/executing-plans |
-| 30 | Harden | `wire-observability` | Add structured JSON logging + idempotent setup + observability commands | CLAUDE.md (commands), src/ (logging) | ✅ Active | Akita "structured logging + idempotent setup" |
-| 31 | Bug | `investigate-bug` | Investigate a bug → DIAGNOSIS.md | DIAGNOSIS.md | ✅ Active | mattpocock/skills (triage-issue, adapted: local-first) |
-| 32 | Bug | `diagnose-root` | 4-phase root cause (reproduce → isolate → hypothesize → verify) | (dialogue, update DIAGNOSIS.md) | 📋 Planned | superpowers/systematic-debugging |
-| 33 | Bug | `validate-fix` | Prove fix works: re-run suite, typecheck, lint | (dialogue, verify) | ✅ Active | superpowers/verification-before-completion |
-| 34 | Review | `audit-code` | Self-review: CONVENTIONS.md compliance, SOLID, no `any`, test coverage | (checklist, pass/fail) | ✅ Active | superpowers/requesting-code-review + Clean Code |
-| 35 | Review | `request-review` | Dispatch fresh reviewer agent (clean context, no shared state) | review-report (structured) | ✅ Active | original |
-| 36 | Review | `respond-review` | Act on reviewer feedback: categorize (must/should), apply, verify | src/ (updated) | ✅ Active | superpowers/receiving-code-review |
-| 37 | Review | `trace-requirement` | Link story IDs from RELEASE-PLAN.md to implementing code and tests | TRACEABILITY.md | ✅ Active | original |
-| 38 | Integrate | `commit-message` | Draft Conventional Commits + semver prediction | (git message) | ✅ Active | mattpocock/skills (prepare-semantic-commit) |
-| 39 | Integrate | `release-branch` | Merge/PR/keep/discard decision + worktree cleanup | (git PR created) | ✅ Active | superpowers/finishing-a-development-branch |
-| 40 | Sustain | `inspect-quality` | Run structured QA session → BUG-LOG.md | BUG-LOG.md | ✅ Active | mattpocock/skills (qa, adapted: local-first) |
-| 41 | Sustain | `organize-workspace` | Classify, show, confirm, then clean workspace | (filesystem state) | ✅ Active | mattpocock/skills (clean-my-room) |
-| 42 | Utility | `terse-mode` | Fallback: ultra-terse output when context critically long | (prompt override) | ✅ Active | mattpocock/skills (caveman); fallback-only |
-| 43 | Utility | `craft-skill` | Build a new bigpowers skill with proper structure | skills/<name>/SKILL.md | ✅ Active | superpowers/writing-skills + mattpocock/write-a-skill |
-| 44 | Utility | `edit-document` | Edit and restructure a document in specs/ | specs/<name>.md | ✅ Active | mattpocock/skills (edit-article) |
-| 45 | Utility | `session-state` | Track implementation decisions and progress in specs/STATE.md | STATE.md | ✅ Active | original |
-| 46 | Utility | `migrate-spec` | Detect GSD/spec-kit/BMAD artifacts and transform to bigpowers specs/ format | specs/ (migrated artifacts) | ✅ Active | original v2.1.0 |
-| 47 | Utility | `visual-dashboard` | Browser-based dashboard: architecture, plans, and UI mockups | (browser view) | ✅ Active | original |
-| 48 | Utility | `write-document` | Write and sync high-integrity technical documents (BMAD methodology) | specs/<name>.md | ✅ Active | original |
-| 49 | Utility | `setup-environment` | Pre-install deps, configure tools before work | (.env, installed packages) | 📋 Planned | autoresearch experiment |
-| 50 | Utility | `reset-baseline` | Restore project to known state between runs | (clean working tree) | 📋 Planned | autoresearch experiment |
-
-**Total: 50 rows — 44 ✅ Active, 6 📋 Planned.**
+| # | Phase | Skill | Intent | Artefact Output | Status |
+|---|---|---|---|---|---|
+| 1 | Bootstrap | `using-bigpowers` | Lifecycle intro; where to start | (dialogue) | ✅ Active |
+| 2 | Orchestrate | `orchestrate-project` | Meta-skill enforcing 6-phase core loop | (orchestration) | ✅ Active |
+| 3 | Discover | `survey-context` | Per-task context map; suggests next skill | STATE.md update | ✅ Active |
+| 4 | Discover | `research-first` | Look-before-build; prior art search | Prior Art in spec | ✅ Active |
+| 5 | Discover | `elaborate-spec` | Dialogue to refine rough idea into spec | (dialogue) | ✅ Active |
+| 6 | Discover | `map-codebase` | High-fidelity codebase survey | CONTEXT.md | ✅ Active |
+| 7 | Elaborate | `model-domain` | Interactive domain model | CONTEXT.md, adr/ | ✅ Active |
+| 8 | Elaborate | `define-language` | Extract ubiquitous language glossary | UBIQUITOUS_LANGUAGE.md | ✅ Active |
+| 9 | Elaborate | `grill-me` | Stress-test design (Design + Docs modes) | (dialogue) | ✅ Active |
+| 10 | Elaborate | `grill-with-docs` | Grill assumptions grounded in real library docs | (dialogue) | ✅ Active |
+| 11 | Elaborate | `deepen-architecture` | Architecture deepening (Ousterhout deep modules) | CONTEXT.md | ✅ Active |
+| 12 | Elaborate | `design-interface` | Multiple interface designs via parallel subagents | INTERFACE-OPTIONS.md | ✅ Active |
+| 13 | Plan | `assess-impact` | Blast radius before code | IMPACT.md | ✅ Active |
+| 14 | Plan | `change-request` | Add requirement or WSJF reorder | RELEASE-PLAN.md | ✅ Active |
+| 15 | Plan | `scope-work` | Define in/out boundaries | SCOPE.md | ✅ Active |
+| 16 | Plan | `slice-tasks` | Vertical slices | TASKS.md | ✅ Active |
+| 17 | Plan | `define-success` | Step → verify pairs | (dialogue) | ✅ Active |
+| 18 | Plan | `plan-work` | Detailed plan with verify steps | RELEASE-PLAN.md | ✅ Active |
+| 19 | Plan | `plan-refactor` | Refactor plan via interview | REFACTOR.md | ✅ Active |
+| 20 | Plan | `plan-release` | Release plan with Gherkin criteria | RELEASE-PLAN.md | ✅ Active |
+| 21 | Spike | `spike-prototype` | Throw-away spike | SPIKE-&lt;name&gt;.md | ✅ Active |
+| 22 | Initiate | `kickoff-branch` | Worktree + branch + test baseline | (git state) | ✅ Active |
+| 23 | Initiate | `guard-git` | Block dangerous git commands | (git state) | ✅ Active |
+| 24 | Initiate | `hook-commits` | Pre-commit hooks | (git state) | ✅ Active |
+| 25 | Initiate | `seed-conventions` | CLAUDE.md + CONVENTIONS.md + specs/ | CLAUDE.md, CONVENTIONS.md | ✅ Active |
+| 26 | Build | `develop-tdd` | Red → green → refactor TDD | src/ | ✅ Active |
+| 27 | Build | `enforce-first` | F.I.R.S.T test-quality rubric | (checklist) | ✅ Active |
+| 28 | Build | `delegate-task` | One subagent, sequential + review | (code) | ✅ Active |
+| 29 | Build | `dispatch-agents` | Parallel subagents on independent tasks | (code) | ✅ Active |
+| 30 | Build | `execute-plan` | Batch execute plan with checkpoints | src/ | ✅ Active |
+| 31 | Harden | `wire-observability` | Structured logging + observability | src/, CLAUDE.md | ✅ Active |
+| 32 | Verify | `verify-work` | Multi-phase UAT; loop on gaps | (dialogue) | ✅ Active |
+| 33 | Verify | `run-evals` | EDD capability + regression evals | EVALS-&lt;feature&gt;.md | ✅ Active |
+| 34 | Bug | `investigate-bug` | Investigate bug → diagnosis | bugs/BUG-*.md | ✅ Active |
+| 35 | Bug | `diagnose-root` | 4-phase root cause analysis | bugs/BUG-*.md | ✅ Active |
+| 36 | Bug | `validate-fix` | Prove fix works | (verify) | ✅ Active |
+| 37 | Review | `audit-code` | Self-review checklist | (checklist) | ✅ Active |
+| 38 | Review | `request-review` | Fresh reviewer agent | review-report | ✅ Active |
+| 39 | Review | `respond-review` | Act on reviewer feedback | src/ | ✅ Active |
+| 40 | Review | `trace-requirement` | Story ID → code/tests | TRACEABILITY.md | ✅ Active |
+| 41 | Integrate | `commit-message` | Conventional Commits + semver | (git message) | ✅ Active |
+| 42 | Integrate | `release-branch` | Merge/PR decision + cleanup | (git PR) | ✅ Active |
+| 43 | Sustain | `inspect-quality` | Structured QA session | BUG-LOG.md | ✅ Active |
+| 44 | Sustain | `organize-workspace` | Safe workspace cleanup | (filesystem) | ✅ Active |
+| 45 | Sustain | `stocktake-skills` | Batch audit of skill catalog | specs/ audit report | ✅ Active |
+| 46 | Sustain | `evolve-skill` | Benchmark-gated skill evolution | ADR, STATE.md | ✅ Active |
+| 47 | Utility | `terse-mode` | Ultra-terse output (fallback) | (prompt) | ✅ Active |
+| 48 | Utility | `craft-skill` | Build new bigpowers skill | skills/&lt;name&gt;/SKILL.md | ✅ Active |
+| 49 | Utility | `edit-document` | Edit documents in specs/ | specs/&lt;name&gt;.md | ✅ Active |
+| 50 | Utility | `session-state` | Track decisions in STATE.md | STATE.md | ✅ Active |
+| 51 | Utility | `migrate-spec` | Migrate foreign spec formats | specs/ | ✅ Active |
+| 52 | Utility | `visual-dashboard` | Browser dashboard | .bigpowers/dashboard/ | ✅ Active |
+| 53 | Utility | `write-document` | BMAD technical documents | specs/&lt;name&gt;.md | ✅ Active |
+| 54 | Utility | `setup-environment` | Pre-install deps before work | (.env, packages) | ✅ Active |
+| 55 | Utility | `reset-baseline` | Restore clean known state | (clean tree) | ✅ Active |
+| 56 | Utility | `search-skills` | Natural language → right skill | SKILL-SEARCH-INDEX.md | ✅ Active |
+| 57 | Utility | `compose-workflow` | Chain skills into workflow recipe | WORKFLOW-&lt;name&gt;.md | ✅ Active |
+| 58 | Utility | `simulate-agents` | Mock User + Auditor simulation | SIMULATION-&lt;feature&gt;.md | ✅ Active |
+
+**Total: 58 ✅ Active, 0 📋 Planned.**
 
 ---
 
@@ -91,13 +100,13 @@
 
 ```
 [First time]
-using-bigpowers → orchestrate-project (choose Standard / Fast-Track / Ad-Hoc)
+using-bigpowers → orchestrate-project (Standard / Fast-Track / Ad-Hoc)
                          ↓
-survey-context → elaborate-spec → map-codebase
+survey-context → research-first → elaborate-spec → map-codebase
                          ↓
-     model-domain / define-language / grill-me / design-interface / deepen-architecture
+  model-domain / define-language / grill-me / grill-with-docs / design-interface / deepen-architecture
                          ↓
-  assess-impact → change-request → define-success → plan-work / plan-refactor / plan-release
+  scope-work → assess-impact → change-request → define-success → slice-tasks → plan-work / plan-refactor / plan-release
                          ↓
     kickoff-branch → guard-git / hook-commits / seed-conventions
                          ↓
@@ -107,16 +116,19 @@ survey-context → elaborate-spec → map-codebase
                          ↓
         wire-observability (production-readiness gate, any phase)
                          ↓
-    investigate-bug → validate-fix
+              ★ VERIFY ★  run-evals → verify-work  (prove it works)
+                         ↓
+    investigate-bug → diagnose-root → validate-fix
                          ↓
       audit-code → request-review → respond-review → trace-requirement
                          ↓
       commit-message → release-branch
                          ↓
-        inspect-quality → organize-workspace (ongoing)
+   inspect-quality → organize-workspace → stocktake-skills → evolve-skill
 
 Transversal utilities (any phase):
-  terse-mode, craft-skill, edit-document, session-state, migrate-spec, visual-dashboard, write-document
+  terse-mode, craft-skill, edit-document, session-state, migrate-spec, visual-dashboard,
+  write-document, setup-environment, reset-baseline, search-skills, compose-workflow, simulate-agents
 ```
 
 ---
@@ -125,22 +137,20 @@ Transversal utilities (any phase):
 
 | Icon | Meaning |
 |---|---|
-| ✅ Active | Implemented — SKILL.md exists, skill is usable |
-| 📋 Planned | Designed or referenced, not yet implemented (no directory) |
+| ✅ Active | SKILL.md exists and is usable |
+| 📋 Planned | Designed but not yet implemented |
 | 🔄 Refactoring | Active but under revision |
 | ⚠️ Deprecated | Will be removed in a future release |
 
 ## Naming Convention Notes
 
-All skills follow `verb-noun` kebab-case (ADR-0001). Two documented exceptions:
-- `terse-mode` — adjective-noun; retained for clarity (the verb form `enable-terse` is confusing)
-- `visual-dashboard` — adjective-noun; retained for clarity (`view-dashboard` implies read-only)
+All skills follow `verb-noun` kebab-case (ADR-0001). Documented exceptions:
+- `terse-mode` — adjective-noun; retained for clarity
+- `visual-dashboard` — adjective-noun; retained for clarity
 
 ## How to Update
 
-1. Every new skill: add a row here before the skill is published.
-2. Every rename: update the Skill column; add a note in the Added column.
-3. Every phase change: update the Phase column.
-4. After any change: bump the "Last updated" date and run `bash scripts/sync-skills.sh`.
+1. Every new skill: add a row here before publishing.
+2. After any change: bump "Last updated" and run `bash scripts/sync-skills.sh`.
 
 → verify: `find . -maxdepth 2 -name "SKILL.md" | grep -v ".git\|.cursor\|.gemini" | wc -l`

package/assess-impact/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: assess-impact
+model: sonnet
 description: Analyze the blast radius of a proposed change before any code is written. Maps dependents, affected stories, and test coverage. Produces specs/IMPACT.md. Use before plan-work on any non-trivial change, when touching a shared module, or when the user asks "what does this break?".
 ---
 

package/audit-code/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: audit-code
+model: haiku
 description: Self-review checklist for the coding agent to run before dispatching a reviewer. Checks CONVENTIONS.md compliance, Boy Scout Rule, test coverage, types, and SOLID. Produces a pass/fail checklist. Use before request-review, before committing, or when user asks for a code quality check.
 ---
 
@@ -11,6 +12,23 @@ Run this self-review before asking anyone else to look at the code. The goal is
 
 ## Checklist
 
+### Supply Chain & Security
+
+- [ ] slopcheck run for new dependencies; packages tagged in plan-work: `[OK]`, `[SUS]`, or `[SLOP]`
+- [ ] No `[SLOP]` packages without documented human approval
+- [ ] No secrets in diff (`sk-`, `ghp_`, `AKIA`, `.env` values) — see `guard-git` patterns
+- [ ] OWASP Top 10 spot-check: injection, broken auth, sensitive data exposure, misconfiguration (see `docs/references/security-threats.md`)
+
+### Provenance & Metadata
+
+- [ ] New plan artefacts include `type:` and `context:` metadata
+- [ ] Implementation steps reference ADR or commit SHA where decisions were made
+
+### Law of Demeter
+
+- [ ] No method chains through unrelated objects (e.g. `a.getB().getC().doX()`)
+- [ ] Collaborators talk to immediate neighbors only; law violations need explicit justification
+
 ### CONVENTIONS.md Compliance
 
 - [ ] All output files are in `specs/` (no docs written to project root)

package/change-request/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: change-request
+model: sonnet
 description: Add a new requirement or reorder epics by WSJF value engineering against specs/RELEASE-PLAN.md. Two modes: Add (intake a new requirement mid-flight) and Reorder (re-score and re-sort all epics/stories). Use when a new requirement arrives mid-release, or when the plan needs prioritization.
 ---
 

package/commit-message/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: commit-message
+model: haiku
 description: Reviews working-tree changes, then drafts a Conventional Commits title/body and states the semantic-release version bump a single such commit would imply. Also notes which defensive-code categories were touched. Use when the user wants to commit recent work, prepare a Conventional Commits message, or asks for semantic-release / semver-consistent messaging before git commit.
 ---
 

package/compose-workflow/REFERENCE.md

@@ -0,0 +1,13 @@
+# Workflow template
+
+```markdown
+# WORKFLOW: <name>
+
+**Trigger:** Use when ...
+
+| Step | Skill | Output | verify |
+|------|-------|--------|--------|
+| 1 | survey-context | STATE.md | ... |
+| 2 | research-first | Prior Art | ... |
+| 3 | plan-work | RELEASE-PLAN.md | ... |
+```