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.
A reference skill that teaches Claude Code plugin directory layout, plugin.json manifest fields, and component auto-discovery rules.
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.
Defines how the agent should interpret and act on blocking warnings from the comment-checker hook that runs after file edits.
Delegate code review, research, and debugging to Google's Antigravity CLI (agy) as an independent second agent.
Reviews changed Java code straight from your git worktree and writes a severity-graded review.md with concrete fixes.
An 8-phase, approval-gated pair programming workflow: understand requirements, write a spec, implement in vertical slices, review, then keep spec and code in sync.
Guides wiring third-party auth providers' JWTs into InsForge RLS and adding OKX x402 onchain pay-per-use billing.
A workflow skill that delegates repo exploration and bounded implementation to Google Antigravity CLI (agy) while the driver keeps approval, diff review, and verification.
Turns an app URL into a validated Homebrew Cask and walks you all the way to a submitted pull request.
For every reviewer question thread on a PR, it recovers the original implementation reasoning and drafts a plain-text answer.
Turns feature requests into detailed, sequential implementation plans with file-level tasks and dependencies.
A skill that guides Claude to copy, move, and extract functions or classes between files with line-level precision.
A read-only skill that reports file metadata and statistics — size, modification time, line counts, function/class counts — without touching your files.
Spawns three parallel subagents to produce diverse solutions, then scores them and returns the best with trade-offs.
Proven architecture patterns for robot software — behavior trees, FSMs, HALs, safety systems — with working code examples.
A repo-specific playbook that guides Claude through the correct PR path, validation commands, and review gate for JSONbored/awesome-claude.
A static-analysis skill that uses abstract interpretation to summarize execution paths, variable ranges, and loop invariants without running the code.
Generates consistent, standards-compliant Claude Code sub-agent files from a short role description.