Dev & Coding

Reviews changed Java code straight from your git worktree and writes a severity-graded review.md with concrete fixes.

An evidence-driven skill that researches and recommends the architecture, tech stack, and build sequence for your software project.

Runs a read-only, parallel audit of git, PRs, CI, releases, plan docs and logs, presents a grouped checklist, and fixes only what you explicitly confirm.

Audits a SKILL.md and fixes the phrasing that makes agents skip instructions: cuts rationale prose, hardens soft language, and adds STOP: gates.

Converts GitHub Actions or Bamboo pipelines into TeamCity YAML and walks you through the manual steps until builds go green.

Lets Claude drive the `teamcity` CLI to investigate build failures and manage jobs, queues, agents and pipelines.

Enforces the edit → eval → lint → test → commit workflow for skills, agents, hooks and the eval framework inside the claude-elixir-phoenix repo.

An opinionated ruleset that scaffolds Expo React Native apps with onboarding, a RevenueCat paywall, AdMob banners and i18n.

A hands-on reference for wiring up axe-core, auditing against WCAG 2.2 AA, and writing keyboard, screen reader and ARIA tests.

Teaches Claude production-grade Convex patterns: function organization, arg/return validators, index-based queries, ConvexError handling, and OCC-safe mutations.

Creates an OpenSpec change and generates proposal, design and tasks artifacts in a single step.

Describe what you want to build and this skill scaffolds an OpenSpec change plus proposal, design and tasks documents in one pass.

A step-by-step release runbook that syncs the version across every manifest, builds, tags, publishes a GitHub release, regenerates the changelog, and notifies Discord.

A layered troubleshooting playbook that uses the mcptoon CLI to find and fix broken MCP servers.

Runs a local Python runtime to handle bulk file operations and return only summaries, cutting token use by 90%+.

For every reviewer question thread on a PR, it recovers the original implementation reasoning and drafts a plain-text answer.

A tuning playbook for AgentDB vector databases: quantization, HNSW parameters, caching, batching and pruning.

A reference skill that teaches Claude Code plugin directory layout, plugin.json manifest fields, and component auto-discovery rules.

A hands-on reference for building Claude Code slash commands — frontmatter, dynamic arguments, file references, and plugin patterns.

A meta-skill that walks you through designing, writing, and validating Claude Code skills with a 6-step process and checklists.