Defines how the agent should interpret and act on blocking warnings from the comment-checker hook that runs after file edits.
A routing skill that points first-time users to NanoClaw's single end-to-end install script.
A one-line skill that asks Claude to re-explain anything technical as the who, what, where, why, and when in plain English.
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.
Plans assessments, policy mappings, and staged rollouts when migrating from Zscaler ZIA/ZPA, Palo Alto, or legacy VPN/SWG stacks to Cloudflare One.
Reference skill for uploading media from URLs or local paths to BulkPublish and batch-creating posts across social platforms.
Generates and audits accessible alt text for figures in R package (pkgdown) sites and Quarto documents by reading the plotting code and surrounding prose.
A role skill for math modeling contests that analyzes the problem, selects models and algorithms, and produces exactly two deliverables: a problem analysis report and a terminology table.
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 prioritized ruleset that makes Claude write minimal new code that blends seamlessly into your existing codebase.
For every reviewer question thread on a PR, it recovers the original implementation reasoning and drafts a plain-text answer.
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.
Turns Claude into an orchestrator on explicit /director invocation: it defines, divides, decides and reviews while lower-tier agents do the actual work.
Turns an app URL into a validated Homebrew Cask and walks you all the way to a submitted pull request.