Explore skills
Search every indexed skill by name, description, repository or instructions, then narrow the results.
Showing 30361–30390 of 31529 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| to-issueskevinnft/ai-agent-skillsBreak a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| to-prdkevinnft/ai-agent-skillsTurn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| triagekevinnft/ai-agent-skillsTriage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| zoom-outkevinnft/ai-agent-skillsTell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| reviewkevinnft/ai-agent-skillsReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X". | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| writing-beatskevinnft/ai-agent-skillsShape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| writing-fragmentskevinnft/ai-agent-skillsGrilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fragments", "ideate", or "raw material" for writing. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| writing-shapekevinnft/ai-agent-skillsTake a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| git-guardrails-claude-codekevinnft/ai-agent-skillsSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| migrate-to-shoehornkevinnft/ai-agent-skillsMigrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| scaffold-exerciseskevinnft/ai-agent-skillsCreate exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| setup-pre-commitkevinnft/ai-agent-skillsSet up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| edit-articlekevinnft/ai-agent-skillsEdit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| obsidian-vaultkevinnft/ai-agent-skillsSearch, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| cavemankevinnft/ai-agent-skillsUltra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| grill-mekevinnft/ai-agent-skillsInterview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me". | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| handoffkevinnft/ai-agent-skillsCompact the current conversation into a handoff document for another agent to pick up. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| write-a-skillkevinnft/ai-agent-skillsCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| native-mcpkevinnft/ai-agent-skillsMCP client: connect servers, register tools (stdio/HTTP). | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| gif-searchkevinnft/ai-agent-skillsSearch/download GIFs from Tenor via curl + jq. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| heartmulakevinnft/ai-agent-skillsHeartMuLa: Suno-like song generation from lyrics + tags. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| songseekevinnft/ai-agent-skillsAudio spectrograms/features (mel, chroma, MFCC) via CLI. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| spotifykevinnft/ai-agent-skillsSpotify: play, search, queue, manage playlists and devices. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| youtube-contentkevinnft/ai-agent-skillsYouTube transcripts to summaries, threads, blogs. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| crypto-mining-setupkevinnft/ai-agent-skillsSetup and optimize cryptocurrency mining operations — AI-powered mining (soul.md protocol), parallel agent deployment, accumulation strategies, and performance optimization. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| lm-evaluation-harnesskevinnft/ai-agent-skillslm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.). | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| weights-and-biaseskevinnft/ai-agent-skillsW&B: log ML experiments, sweeps, model registry, dashboards. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| huggingface-hubkevinnft/ai-agent-skillsHuggingFace hf CLI: search/download/upload models, datasets. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| llama-cppkevinnft/ai-agent-skillsllama.cpp local GGUF inference + HF Hub model discovery. | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |
| obliteratuskevinnft/ai-agent-skillsOBLITERATUS: abliterate LLM refusals (diff-in-means). | Stars: 15 | Updated | Claude CodeCodex | Unverified | Install |