AI Software Factory — end-to-end pipeline from approved ticket to deployed test environment. Chains readiness gate → develop (factory mode) → PR → CI deploy. Reduces human touchpoints from 5+ to 2.
Fetch library/framework documentation via context7 or web search and persist it to the knowledge base. Automatically invoked when documentation is needed for implementation tasks.
On-demand precise impact analysis for a symbol or file before changing it. Spawns impact-analyzer to grep callers, classify the cascade (direct/indirect/test-only), and produce a confidence-scored report. Different from .claude/state/architecture.md (broad map) — this is the focused per-symbol drill-down.
Build or refresh a vector index of the codebase at .claude/state/codebase.db for semantic search via /search. Opt-in for large codebases (>50k LOC); small projects get sufficient awareness from .claude/state/architecture.md + Grep.
Plan → code → review → re-code feedback loop with persistent state across iterations. Spawns the review-coordinator, tracks findings across pushes, dedupes against prior iterations, and respects user "won't fix" decisions.
AI-powered merge conflict resolution. Reads both features' story docs to understand intent, resolves conflicts per file type, validates merged result. Works for any codebase.
Create mock definitions for external APIs and services. Generates contract files, test fixtures, mock servers, and integration wrappers so AI can safely develop and test against external dependencies without hitting real services.
Invoke the planner-coordinator on a story or task — spawns planning specialists in parallel (requirements-clarifier, scope-decomposer, risk-assessor, test-strategy-planner, plus architect/api-designer/database-architect when relevant) and produces .claude/state/plan- .md.
Ticket refinement and gap analysis - analyzes existing tickets, identifies gaps, scans codebase, and generates refined documentation. Use when improving existing tickets or doing a quick gap check.
Semantic search across the indexed codebase. Returns top-K matching chunks with file:line + similarity score. Requires /index to have been run first. Useful for "where do we handle X?" questions that grep can't answer because there's no exact-string match.
First-time onboarding — orchestrates project-setup-detector and project-setup-applier across a confirm checkpoint. Distinct from /improve (ongoing evolution); /setup owns the first-run shape decisions.
Update work item tracker with story documentation (solution components, how-to-test, manual steps). Use after developing or refining a ticket to push docs back to the tracker.
Validate built code against project standards and conventions. Checks coding standards, test quality, naming, formatting, and configuration. Use after implementation to catch issues before committing.
★not rated 2 1mo agoA34 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: