Discover and install skills to enhance your AI agent's capabilities.
| Name | Contains | Score |
|---|---|---|
langfuse/langfuse Use Langfuse's disposable per-PR previews at pr-N.preview.langfuse.com (synthetic data only). Use for preview access, failed deployments, test-data seeding, kubectl debugging, or waking sleeping previews. | Skills | |
ahgraber/skills Use when writing, rewriting, or auditing Python docstrings that a documentation site is generated from, or when docstrings are long, narrate the code, or leave a reader of the generated reference unable to find their way. Triggers - "audit the docstrings", "docstring slop", "docstrings as documentation", "the API reference reads badly", "rewrite these docstrings". | Skills | |
ahgraber/skills Use when completing and archiving a change after all tasks are done and specs are synced. Triggers: "archive the change", "complete this change", "close out the change", "finish the change", "archive". | Skills | |
fkukuck/fabro Apply this Rust style guide when writing, reviewing, refactoring, or configuring Rust code for this project. Covers Rust 2024/MSRV, library vs application conventions, public API design, errors, panics, ownership and cloning, async/Tokio/concurrency, tracing, rustfmt/Clippy, testing with nextest, and unsafe/macro policy. Also use when setting up new Rust projects, investigating Rust performance, verifying library releases, or reviewing Rust code changes. | Skills | |
IgorVaryvoda/image-optimization-skill Expert guidance on video optimization for web performance. Use when adding, auditing, or improving video on websites - hero/background videos, product demo videos, autoplay loops, GIF-to-video conversion, HLS/adaptive streaming, video posters and thumbnails, lazy loading video, YouTube/Vimeo embed performance, video Core Web Vitals (LCP/CLS/INP), video SEO/schema, or Sirv video hosting and streaming. Covers MP4/WebM/HLS delivery, H.264/VP9/AV1 codec choice, preload strategies, muted autoplay rules, facades for third-party players, and video-to-spin workflows. | Skills | |
ChromeDevTools/chrome-devtools-mcp Uses Chrome DevTools MCP for inspecting, debugging, and testing cookies, session state, authentication issues, and cookie consent compliance. Use when diagnosing 401/403 errors, authentication redirects, session expiration, Cookie/Set-Cookie header issues, cookie banner consent conformance, or third-party cookie/SameSite/Partitioned cookie warnings. | Skills | |
wanshuiyin/Auto-claude-code-research-in-sleep Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese tutorial on a specific ML topic. | Skills | |
wanshuiyin/Auto-claude-code-research-in-sleep Workflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas. Use when user says "robotics idea discovery", "机器人找idea", "embodied AI idea", "机器人方向探索", "sim2real 选题", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning. | Skills | |
FlorianBruniaux/claude-code-ultimate-guide Audit Claude Code instruction rules in .claude/rules/ and ~/.claude/rules/: frontmatter, paths glob validity against real files, symlink load status, and day-to-day usefulness, then update rules with the user. Use for first-time rules setup, rules that apply too often or never, or periodic rules hygiene. Not for Codex .rules command-approval files. | Skills | |
bangle-io/bangle-io Operate recurring Bangle.io agent follow-ups after a thread has already started. Use when the user asks to continue, check status, decide what is next, push, create or update a PR, poll CI, rebase, merge, release, run Playwright/manual UX checks, spawn or aggregate code-review subagents, run thermonuclear review, address review findings, make a plan, add a project task, or asks "we good?", "pushed?", "PR?", "did you test?", "what should I test?", or similar follow-up prompts in the Bangle repo. | Skills | |
silverstein/minutes Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought. | Skills | |
NVIDIA-NeMo/Nemotron Reference desk for NVIDIA Nemotron 3.5 Lightning (30B-A3B), a hybrid Mamba-Transformer MoE with MTP built from Nano 3 Base by distillation from Super 3 Base, single-stage text SFT, RLVR, MTP boosting, and W4A16 NVFP4 quantization. Use when the user asks facts about Lightning 3.5 rather than building a pipeline. | Skills | |
v0.19.1 Herdr team coordination policy for AI coding agents Contains: herdr-foreman Coordinate Herdr workers in parallel and recover stalled sessions. Use to assign work, collect coordination metrics/evidence, summarize a measurement snapshot, inspect workflow readiness, retrieve saved attention, retrieve working memory, retrieve retrospectives, check task cost, inspect GitHub evidence, quarantine contradictory context evidence, or release verified task changes. herdr-observer Start, recover or stop an independent Herdr factory observer; analyze its pending evidence, inspect collection health, and produce private weekly reports or urgent alerts about delivery throughput, coordination overhead, idle capacity, subscription balance, model/effort suitability and other improvement opportunities. Use for Herdr observer wake prompts or requests to start, restart or stop the observer, inspect observer status, analyze factory efficiency, prepare its weekly report or investigate an observer alert. Never gates delivery. herdr-optimizer Optimize an assigned Herdr developer task: simplify logic, refactor duplication, remove dead code and redundant dependencies, and eliminate avoidable work. Use when a verified Herdr worker's developer brief asks it to simplify, refactor or clean up its named code area, or continue its assigned optimizer objective. herdr-standup Collect Herdr standup evidence, check worker readiness, account for missing reports, render a daily status table and relay blockers without interrupting workers. Use when the user asks for a Herdr standup, team status update, daily check-in, worker progress report or what each worker is doing. Live inspection requires the verified foreman; ordinary work skips this skill. | SkillsRules | |
NVIDIA/skills Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene captions, grounded referring expressions, and (optionally) verified expressions via VLM distillation. Use when the user wants to generate referring-expression annotations from images with KITTI labels, build region descriptions, produce grouped grounding phrases tied to bboxes, run a double-check verification pass on grounding expressions, auto-label traffic / scene images for referring datasets, or run the image_referring_expression pipeline. Triggers include 'referring expression', 'region description', 'KITTI labels', 'spatial relationship annotation', 'auto-label image referring expression', 'image_referring_expression'. | Skills | |
NVIDIA/skills cuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API. | Skills | |
NVIDIA/skills Use this skill for MolMIM, NVIDIA's BioNeMo NIM microservice for small-molecule latent-space generation and optimization. Invoke for MolMIM, molecular embeddings, hidden states, latent decoding, sampling around a seed SMILES, CMA-ES guided molecule generation, QED or plogP optimization, hosted NVIDIA API calls, or local Docker deployment. | Skills | |
TanStack/ai Sweep open (or listed) PRs with up to 100 parallel agents: security-scan outside contributors, rebase onto main when behind (push --force-with-lease), approve pending first-time-contributor CI when relevant, optionally rebase in-house PRs, and report who should review. Supports full, changed-only, behind-only, and conflict-only scopes for cheap daily runs. Use when the user runs /pr-sweep (or /pr-inbound-sweep), or asks to "sweep PRs", "sweep inbound PRs", "security-check outside PRs", "rebase outsider PRs", "rebase our PRs", "approve waiting CI on PRs", "daily PR sweep", or "prep external PRs for review". | Skills | |
TanStack/ai Use when writing a pull request title or body, when about to run gh pr create, when about to git push on a branch that already has an open PR, or when the user says /pr-description, "write the PR description", or "update the PR title". Don't use for commit messages, changelogs, or review comments. | Skills | |
TanStack/ai Use when writing a pull request title or body, when about to run gh pr create, when about to git push on a branch that already has an open PR, or when the user says /pr-description, "write the PR description", or "update the PR title". Don't use for commit messages, changelogs, or review comments. | Skills | |
vercel/next.js Benchmark React or Next.js changes on Vercel Sandbox VMs with paired A/B statistics: react PR/commit vs base, or Next.js PR/commit vs base, measured end-to-end through the bench/render-pipeline app (rps, latency, p95; TTFB, RSS and document/Flight bytes when the Next side captures them) and, for React changes, through the react repo's flight-ssr-bench fixture (Node AND Edge web-streams paths, Fizz and Flight+Fizz). Use whenever the user asks to bench, perf test, or A/B a React PR, a react-server-dom / Flight / vendored React change, or a Next.js PR ("is this PR faster", "does this regress RSC?", "measure the perf impact of <commit>"), even if they don't say "benchmark" — any request to quantify a server-side performance difference between two revisions belongs here. Runs remotely (laptop-free), applies correctness gates before measuring, and reports boot-level confidence intervals. | Skills |
Can't find what you're looking for? Evaluate a missing skill.