Documentation menu
reference

Fifty-nine skills,
all in main context.

Reference for the skills. A skill runs in main context with the whole conversation visible, which is what lets it decide anything. The baseline ships one subagent, and everything else that might have been one is a skill instead.

skills
59
categories
15
subagents
1

Categories

If these counts and the real total ever drift apart, audit-baseline fails the build. There are 15 categories, assigned by hand rather than derived from disk. That is why they live beside the deriver, and why this section can give you counts without a per-skill grouping.

artifact

4

phases

10

workers

5

specHelpers

5

orchestration

3

memory

1

navigation

1

phaseHelpers

1

generators

4

sharedGlobals

10

audit

1

altTracks

2

maintenance

4

sprint

5

roadmap

3

The roster

59 baseline-owned skills, in alphabetical order. Each summary is excerpted from the first sentence of the skill's own description. It is never reworded, because a skill prompt is a contract and editing it from a template would quietly change how the skill behaves in a session (the roster derives from the files themselves).

archive

move the slug's workflow artifacts (intake, scout, research, spec, approvals, swarm state, security reports, rendered diagrams) to…

audit-baseline

Drift check between the baseline implementation on disk and the claims in `docs/init/seed.md` + cross-references in CLAUDE.md, README.md, and the…

brainstorm

PM-mode brainstorm helper. Captures the requirement via Socratic dialogue before any entry phase (`/intake`, `/spec`, `/tdd`) drafts its artifact.

brd

Draft a Business Requirements Document (BRD) for cross-functional or stakeholder-heavy work that needs more structure than an intake.

chore

documentation edits, governance count bumps, vendored-skill content updates, configuration tweaks, formatting, typo fixes, dependency bumps where no…

claude-automation-recommender

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers).

code-browser

The primary tool for code-navigation questions in ANY language (frontend or backend) — walk the structural graph from an entry point (page, route,…

code-structure

MANDATORY skill for ALL code generation.

commit

Commit Preparation and Execution. Stages and commits the work.

commit-planner

Split a dirty working tree into single-concern Conventional Commits.

companion

EXPERIMENTAL. Join or leave an org-team coordination channel as a session peer.

copywriting

When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages,…

design-ui

Orchestrates `impeccable` for every design task inside a workflow phase.

document

orchestrator for documentation work. Surveys the diff, routes any page on a documentation surface through `technical-writer`, standalone technical…

documentation

Write and maintain technical documentation.

gitignore

Generate or repair a project's .gitignore.

harness

End-to-end workflow orchestrator. Walks the 11-phase pipeline, invoking each phase skill in order inside an internal loop, yielding at consent gates…

humanizer

Remove signs of AI-generated writing from text.

impeccable

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract,…

implement

Write the production code that makes a pre-decided set of failing tests pass, within an explicit write_set, following an explicit behavior contract.

intake

Draft a Workflow Phase 1 intake document capturing a new request — the problem, the desired outcome, constraints, and testable acceptance criteria.

integrate

Integration and Verification. Runs the full test suite, stamps the binding verdict at .claude/state/last_test_result, optionally runs a cross-engine…

memory-sync

Review the auto-extracted candidates in `.claude/memory/_pending.md` and commit keepers to the canonical memory files (`landmarks.md`,…

org-dispatch

a flat pod of up to four peer Claude Code sessions claims lane-tagged slices of an approved spec over the baseline MCP channel and implements them…

power

hosts the two behaviours that distinguish the `power` workflow track from spec-entry.

prose

documentation body, intake problem statements, spec context, RCA summaries, marketing copy, README sections, PR descriptions.

rca

Draft a Root Cause Analysis for an incident, outage, or repeated test failure.

reader-level

Bring documentation prose down to a high-school reading level without losing precision.

research

Research and Solution Exploration. Surfaces 2–4 candidate solution approaches with concrete tradeoffs, grounded in current library docs (fetched…

retrospective

Cycle-end retrospective converting recurring judgment failures into durable enforcement.

roadmap

Read-only view of the execution roadmap.

roadmap-planner

Derive an execution roadmap from a project's vision/spec docs by first principles, then diff that fresh derivation against the existing roadmap to…

roadmap-sync

sync the project's execution roadmap (project.json → roadmap.path, default docs/roadmap-execution-plan.md) to the just-landed work.

scenario

Write executable failing tests from a recipe handed to you by the main context.

scout

Codebase Scouting and Constraint Discovery.

security

OWASP-aligned security review of pending code changes.

simplify

Mechanical cleanup pass over the branch diff, followed by a `code-structure` review pass and a `verify` re-stamp.

spec

Draft a Workflow Phase 4 technical spec from an intake (and optionally a BRD + scout + research memo).

spec-diagram-review

Cross-consistency review of a drafted spec's diagrams.

spec-lint

Preflight a spec draft without saving. Runs the same checks as the write-boundary hooks — PlantUML syntax, required diagram presence, AC-to-sequence…

spec-render

Extract every PlantUML block from docs/specs/<slug>.md and render each to SVG under docs/specs/_rendered/<slug>/, with an index.md listing them in…

spec-rollout-enforceability-review

Oracle-bound spec-review check that every structured Rollout prerequisite binds to an enforcement-type acceptance criterion.

spec-sync

Bootstrap the central system spec at `docs/system/` for a repository that has never had one.

spec-traceability-review

every spec AC must trace to a resolvable upstream AC in the intake (and BRD if present), and no upstream AC is silently dropped.

sprint-oracle

a mechanical, exit-code-driven check that every feature in a sprint manifest is provably complete across three dimensions (a done-record reference,…

sprint-plan

Decompose an MVP vision into a sprint manifest — a prioritized feature list where every feature carries explicit done-criteria (a done-record…

sprint-planner

Propose the next dependency-ready sprint from the ALREADY-DECOMPOSED roadmap — standup's active sibling.

standup

Read-only release + backlog recap. Reports the last release, commits-since-tag classified by conventional-commit type with the semver bump they…

swarm-dispatch

Execute a swarm plan wave by wave with filesystem isolation via git worktrees.

swarm-plan

Decompose an approved spec into a dependency-ordered swarm plan — one task per component, each with an explicit write_set.

system-reconcile

Report the health of the central system spec at `docs/system/` across seven checks — coverage gaps, stale elements, dangling anchors, duplicate…

tdd

TDD coordinator. Decides the scenario recipe and the implementation contract in main context, writes them to a state file, seeds per-worker tasks…

technical-tutorials

When the user wants to create step-by-step technical tutorials, quickstarts, or code walkthroughs.

technical-writer

Standard operating procedure for producing a documentation page end to end — gather source material, classify, draft against the measured corpus…

technical-writing

Write technical documentation that matches the measured profile of professionally-written docs.

triage

pick the workflow entry phase (intake / spec / tdd / chore) and record the workflow statefile that the Track Guard reads.

upgrade-project

Reconcile baseline-versioned files that the `create-baseline upgrade` CLI staged for LLM-assisted semantic merge.

verify

Contract document for the binding test verdict file at .claude/state/last_test_result.

whatsnew

On-demand "what's new" generator. Main context (which knows the impending change) writes keepachangelog-style entries to a fragment file at…

Ownership

A skill is baseline-owned when its SKILL.md frontmatter says owner: baseline. Every other skill on disk belongs to the project. Leaving the line out is the default on purpose, so a repository that already carries skills of its own can install the overlay without anyone annotating a single file (an explicit owner: user is permitted, never required).

To keep a maintainer's working skills out of the package, the build ships a skill only when it claims baseline ownership. Ownership decides one further thing. audit-baseline hash-checks the baseline-owned paths and nothing else, which leaves your own skills outside the audit.

Sub-skill contracts

Five skills call another skill as part of their job, and four of those calls are mandatory. Where a skill declares none, its work is mechanical enough not to need one.

scenario

Calls code-structure.

implement

Calls code-structure. Also checks current docs for any third-party API.

design-ui

Calls impeccable to do the design. Writes no product code itself.

prose

Always calls humanizer. Also calls one register skill, picked by whoever ran it.

verify

Mechanical. Declares no sub-skill.

last updated 2026-08-20 edit on GitHub →