Dev & Coding

An engineering skill for scaffolding and registering Paperclip agent adapters that satisfy the server, UI, and CLI surfaces at once.

Fans out one background agent per open issue/PR to produce evidence-backed, permalink-cited triage reports in /tmp — with zero writes to GitHub.

A setup skill that walks through installing claude-mem on Grok Bot via local worker, host-login observer, or remote cmem.ai.

Case-by-case QA of opencode itself — CLI, HTTP server, plugin hooks/events over SSE, tmux TUI smoke, and read-only session DB investigation.

Splits a task into atomic PRs, builds each in its own git worktree, and loops through CI and bot review gates until merged.

Judges slow, flaky, redundant or brittle tests by the real failure they protect, and trims feedback cost to the smallest verification that covers the risk.

Runs a three-layer, parallel multi-agent review of all unpublished changes before an npm publish and returns a SAFE/CAUTION/RISKY/BLOCK verdict plus a version-bump recommendation.

An evidence-driven skill for finding and safely removing accidental complexity — dead code, duplicate state, redundant layers — within an authorized scope.

An interactive, resumable eight-phase journey that measures, untangles, and speeds up a working-but-slow codebase while logging every decision in docs/.

A Clean Code review skill that scores your code 0-10 on naming, function size, error handling and tests, then lists the exact fixes to reach 10/10.

Turns half-baked ideas into a structured, stress-tested concept brief using multi-turn clarifying questions and seven parallel critique lenses.

Audits every design doc or README against the actual codebase and writes a dated, differences-only drift report.

A hands-on guide for validating web accessibility with VoiceOver, NVDA, JAWS, and TalkBack.

A playbook for splitting a large feature across multiple implementer agents using file ownership, interface contracts, and integration patterns.

A read-only analysis skill that inspects and summarizes codebases, checks service health, and supports decisions via ADR consultation, weighted scoring, and multi-persona critique.

Answers questions about your codebase by selectively grepping a pre-built knowledge graph instead of loading it all.

Turns your project's knowledge graph into a complete onboarding document covering architecture, file map, and complexity hotspots.

Official skill that walks you through researching, implementing, testing, and evaluating high-quality MCP (Model Context Protocol) servers in TypeScript or Python.

Convenes each git worktree and PR as its own agent in a shared markdown room, then drives rounds until one consolidation plan emerges.

Maps a codebase into feature-grouped Mermaid flowcharts, hunts duplicated concerns with file:line evidence, and proposes the simplest unified architecture before a refactor.