Turns big code changes into a checked, repeatable workflow. Five phases (assess, plan, execute, review, iterate), plus an optional learn phase. Splits work into parallel chunks where it can. Picks the right model for each task. A strong model plans and reviews. A faster model writes code. A small model does pattern checks. Catches the common ways big changes go wrong. The diff drifts from the plan. The implementer makes quiet design calls you never see. Tests pass but pages do not render. Fake data leaks into production. Plans must list every design decision up front. The implementer must say which decisions it made. A lint compares the claim to the actual diff. Work with six or more design decisions auto-routes to the strong model in one pass. A read-only critic runs before full validation. Cheap checks catch the obvious mistakes first. Includes an optimize mode that runs multiple tests in a single experiment using Design of Experiments. You can test six variables at once instead of one. The mode plans the test matrix, runs each combination, and tells you which variable actually moved the number. Bundles a debugger memory and an architecture engine that maps the codebase before each build. Use it for features, refactors, migrations, schema changes, anything that touches more than one file. Skip it for fixes under about 20 lines. Verifies the production deploy after a push (Vercel): polls the deployment to a terminal state and probes changed routes — an auth-gated 401/403 is healthy, only a 5xx or build error fails. An independent commit auditor runs at the git-commit boundary on every commit (manual user, Codex, build-loop, IDE) and gathers its own context from intent, goal, PRD, and constitution — the running session renders one of four verdicts in conversation: yay, nay, suggest correction, look again.
60 skills · 2 commands · 29 agents · hooks
End-to-end UI design and validation — guided builds, visual checks, mockup matching, native scanning
32 skills · 14 commands · 1 agent · hooks
Build-loop extension with Karpathy's autoresearch pattern: constrained scope + mechanical metric + git commit/revert + autonomous iteration for app development optimization.
9 skills · 11 commands · 9 agents · hooks
Standalone supporting plugin for build-loop's debugger bridges — extended capability (cross-project incident memory, additional assessor coverage, coordination across build-loop instances). Build-loop bundles its own debug-loop / debugging-memory / logging-tracer skills + MCP server; install this only when bundled capability isn't enough.
3 skills · 9 commands · 7 agents · 1 MCP server · hooks
Launch synthetic personas to review your app UI/UX, architecture, and code base before you deploy
4 skills · 5 commands · 9 agents
Structured research with central knowledge base, source scoring, and claim verification
4 skills · 13 commands · hooks
Capture screenshots, videos, and polished demo clips — spotlight focus, lower-third captions, and a tagged library — across web, macOS, and iOS
7 skills · 9 commands · 1 agent · 1 MCP server
Map dependencies and analyze blast radius before changing code
6 skills · 4 commands · 4 agents
Local doc-content cache and authoritative API source registry. Caches docs as dated markdown with a 7-day freshness contract and answers from the local cache first, falling back to Context7 only when no source is registered. A staleness detector flags docs past the window. Tracks the publish date of each package's latest version and emits an install-cooldown verdict — third-party releases under 7 days old are flagged, the author's own packages exempt. Curation is done in-session, never by a background daemon.
3 skills · 9 commands · hooks
Auto-save and restore session context across compactions and restarts
1 skill · 6 commands · 1 agent · 1 MCP server · hooks
Migrate Replit apps to web (Vercel) or native (iOS/macOS)
3 skills · 2 commands · 1 agent · 1 MCP server · hooks
Barbara Minto's Pyramid Principle for short-form, long-form, presentations, and audits
6 skills · 1 command
Repo-local coordination surface for parallel coding agents (Claude Code, Codex, Gemini). Records claims, checks write boundaries, routes handoffs, and exposes room state via the rally CLI. Three skills — agent-rally-point (per-session loop), rally-workflows (fan-out + dynamic-workflows protocol), mini-loop (per-task quality gate). Advisory-only hooks auto-fire on SessionStart and PreToolUse to surface room awareness and deconflict before edits; never blocks. Backend is the rally Rust CLI; install via `cargo install --path crates/rally-cli` from the repo. Self-gates outside rally repos so it is safe to keep installed everywhere.
4 skills · 1 command · hooks
Classify, diagnose, rewrite, and score prompts by model tier and deployment
1 skill · 4 commands
Extract blog and news content from any website
1 skill · 4 commands
Visual mockup review with component-level ratings
1 skill · 2 commands · hooks
[Deprecated — use spectra] Dev asset capture for blog and website content
1 skill · 2 commands · 1 MCP server
Design and evaluate agentic harnesses with playbooks and an architecture catalog
1 skill
Local plugin version tracker — scan source dirs, detect drift across marketplace/registry, keep everything in sync. Personal tool, not published.
1 skill