Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
48,622 skills from 2,355 repositories · updated 10 hours ago
6,268 skills
- python-fastapi-ops0xDarkMatter/claude-modsFastAPI web framework patterns. Triggers on: fastapi, api endpoint, dependency injection, pydantic model, openapi, swagger, starlette, async api, rest api, uvicorn.EngineeringNo warnings★ 80↓ —
- release-cutBlackBeltTechnology/pi-agent-dashboardCut a new pi-agent-dashboard release: promote `## [Unreleased]` in CHANGELOG.md, bump every workspace package.json per SemVer, commit, tag `v<version>`, and push — triggering the Release workflow that publishes every non-private workspace, builds the Electron artifacts, and creates a GitHub Release. Use on "cut a release", "release vX.Y.Z", "publish a new version", "tag a release".EngineeringReview first★ 339↓ —
- code-reviewNewkyy-logs/code-review-skill写完代码、提交前或合并 PR 时使用；用户说“帮我 review”“提交前检查一下”“看看这次改动”“PR review”，或要求严格审查/合入门禁时也使用。EngineeringNo warnings★ 101↓ —
- sympyKalarisLabs/research-agent-skillsUse when you need exact symbolic math in Python — algebra, calculus, equation solving, symbolic linear algebra, or code generation via lambdify/LaTeX. Prefer NumPy or SciPy when floating-point approximations are sufficient.EngineeringNo warnings★ 84↓ —
- python-async-ops0xDarkMatter/claude-modsPython asyncio patterns for concurrent programming. Triggers on: asyncio, async, await, coroutine, gather, semaphore, TaskGroup, event loop, aiohttp, concurrent.EngineeringNo warnings★ 80↓ —
- waypoint-bioKalarisLabs/research-agent-skillsUse when working with Outpost Bio's open microbiome foundation models - the Waypoint checkpoints (Waypoint-6m, Waypoint-45m, Waypoint-170m), the Atlas pretraining corpus, the Compass eight-task benchmark, or the `waypoint` CLI from the `waypoint-bio` package. Covers embedding microbiome samples, fine-tuning on taxonomic abundance data, benchmarking a checkpoint on Compass, pretraining a GPT-2 model on taxonomic abundance profiles, and converting MetaPhlAn, Kraken2, QIIME 2, or MGnify abundance tables into waypoint format.EngineeringNo warnings★ 84↓ —
- show-me-your-workadriannoes/awesome-agentic-aiKeep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.EngineeringNo warnings★ 92↓ —
- wechat-topic-hunteradsorgcn/WorkBuddyFind WeChat official account (公众号) topics with real demand and supply data: read the repository's daily cross-platform hot list for free (what every platform is talking about today), then check read/share numbers on WeChat through the wxrank API with the user's own key. Use when the user says 选题/对标/看榜/爆文榜/今天写什么/内容清单/选方向/哪些文章读得多/找对标号/查阅读. Quotes the cost before every paid call. Never copies content.EngineeringNo warnings★ 113↓ —
- threejs-sceneNewMoh4696/open-3d-skillsBuilds real-time 3D websites in three.js from code alone, with no model files. Covers buildings and landmarks, vehicles, machines, landscapes and product studies made of procedural geometry (profile sweeps, lathes, instancing), canvas textures, shader patches, a physically based sky and sun, soft shadows, ambient occlusion and bloom, light presets, camera vantages and flights, quality tiers, and a starter that runs at 60 fps. Use when someone asks for a 3D website, a three.js scene, a WebGL hero, an interactive 3D model of a real place or object, a "3D version" of something, or when an existing three.js page looks flat, plasticky, aliased, washed out or slow.EngineeringNo warnings★ 75↓ —
- grpo-rl-trainingKalarisLabs/research-agent-skillsGuides GRPO (Group Relative Policy Optimization) fine-tuning of language models with the TRL library, including GRPOTrainer configuration, composing multiple reward functions (correctness, format, length, style), dataset prep in chat format, Unsloth setup, LoRA merging, and monitoring reward, reward_std and KL. Use when training a model to follow a strict output format such as XML or JSON. Use when teaching verifiable tasks like math or code with objective correctness rewards. Use when improving chain-of-thought reasoning with custom reward functions. Use when debugging flat rewards, mode collapse, or OOM in GRPO runs. Do not use for plain supervised fine-tuning (use SFT) or when high-quality preference pairs exist (use DPO or PPO).EngineeringNo warnings★ 84↓ —
- stable-baselines3KalarisLabs/research-agent-skillsProduction-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.EngineeringNo warnings★ 84↓ —
- alterlab-pubmedAlterLab-IEU/AlterLab-Academic-SkillsProvide direct REST API access to PubMed via the NCBI E-utilities API, supporting advanced Boolean/MeSH queries, batch processing, and citation management. Use when searching biomedical literature by MeSH terms, retrieving abstracts or PMIDs in bulk, or scripting custom PubMed queries over raw HTTP/REST — for Python workflows prefer biopython (Bio.Entrez) instead, use this for direct REST work or custom API implementations. Part of the AlterLab Academic Skills suite.EngineeringNo warnings★ 82↓ —
- dead-code-eliminatorArabelaTso/Skills-4-SEIdentify and analyze unused or redundant code including unused functions/methods, unused variables/imports, unreachable code, and redundant conditions. Use when cleaning up codebases, improving maintainability, reducing technical debt, or conducting code quality audits. Analyzes Python code using AST analysis and produces markdown reports listing dead code locations with line numbers, severity ratings, and recommendations. Triggers when users ask to find dead code, remove unused code, identify unused imports, find unreachable code, or clean up redundant logic.EngineeringNo warnings★ 260↓ —
- labarchive-integrationKalarisLabs/research-agent-skillsSecurely integrate with the official LabArchives ELN REST-like API and Inventory API v1. Use for regional endpoint selection, signed-request construction, user authorization and UID flows, local LA container validation, and verified LabArchives integration workflows.EngineeringNo warnings★ 84↓ —
- light-idea-critiqueLight0305/Light-skillsLight 科研主线第 4 步·审 idea：以**顶会审稿人标准严审** idea，**撞车/无创新 fatal flaw 一票否决**(critical 门)， 逼出真能发表的 idea。何时用：用户问"这 idea 行不行/够不够新/能不能发""帮我严审/挑刺/找致命问题" / idea 定稿前把关 / 收到 idea-generation 的候选要审 / 怀疑撞车(被人做过)。触发词：审 idea / 评审 / 严审 / 挑刺 / 这 idea 行不行 / 够不够新 / 创新性 / 撞车 / 被做过了吗 / 致命问题 / 能投顶会吗 / 拒稿风险 / critique my idea / review this idea / is this novel / fatal flaw / 一票否决。核心纪律：**撞车/无创新的 critical 一票否决在本技能**(不被其他高维度平均救回)； **硬性反谄媚**(不被作者反复反驳顺从放行弱 idea)；撞车判定**target/background 可追溯分解**非"感觉像"；judge 不靠裸 自评(用可计算否决闸门 + 密度先验 + pairwise)。**消费上游 idea-generation 的撞车 findings + facet 槽位**。EngineeringNo warnings★ 842↓ —
- light-experiment-codingLight0305/Light-skillsLight 科研主线 stage 6：把冻结的 question/estimand、experiment matrix、pre-registration 与 data lineage 落成最小可运行、测试先行、无泄漏、可复现且能交给 result-analysis 的实验代码。用于实现或复现训练/预处理/评测， 设计 gold/property/metamorphic 测试，控制 Python/NumPy/框架/CUDA/DataLoader 随机性，审查 train/test 或 CV fit 穿越，记录 config/code/environment/input hashes、stdout/stderr、raw metrics、patient/entity predictions 与 failure artifacts，以及运行 stage-6 checkpoint。数据泄漏或不可复现是 critical；静态扫描和同 seed 两次一致都不证明跨硬件 绝对复现。EngineeringNo warnings★ 842↓ —
- light-review-rebuttalLight0305/Light-skillsBuild auditable peer-review revision and author-response packages for Light stage 13. Use after receiving reviewer comments, a decision or meta-review; when drafting a rebuttal or response letter; when triaging major/minor revisions; when simulating a pre-submission review; or when a rejection may require a user-chosen 13→3 novelty, 13→5 experiment, or 13→8 writing back-edge. Consumes the selected venue/context and real PDF facts, preserves reviewer wording, atomizes issues, binds claims/evidence/actions/provenance, separates PLANNED from DONE, checks current venue limits without borrowing another venue's rules, and emits the stage-13 gate without changing venue, manuscript, evidence, citations, figures, PDF, or passport automatically.EngineeringNo warnings★ 842↓ —
- systematic-review-prismaKalarisLabs/research-agent-skillsPlan, run and report systematic reviews and meta-analyses to PRISMA 2020 standards. Use when writing a review protocol (PROSPERO/OSF), building reproducible database search strings (PubMed, Embase, Scopus, Web of Science), deduplicating exports, organizing title/abstract and full-text screening, assessing risk of bias, drawing the PRISMA flow diagram, or completing the PRISMA 2020 checklist. Includes a dedup tool and a checked PRISMA diagram generator.EngineeringNo warnings★ 84↓ —
- hail-webhooksNewhookdeck/webhook-skillsReceive and verify Hail webhooks. Use when setting up Hail email, SMS and voice webhook handlers, debugging X-Hail-Signature verification, or handling events such as email.received, email.delivered, email.bounced, email.opened, email.clicked, sms.received, sms.delivered, and call.completed.EngineeringNo warnings★ 97↓ —
- velt-webhooksNewhookdeck/webhook-skillsReceive and verify Velt webhooks (Advanced V2, Enterprise, signed with Standard Webhooks). Use when setting up Velt webhook handlers, debugging webhook-signature verification, or handling events like comment_annotation.add, comment.add, huddle.join, crdt.update_data, recorder.done, and execution.completed.EngineeringNo warnings★ 97↓ —
- commit-and-pushjmagly/aiwgCreate a well-formatted git commit and push to remote repositoryEngineeringReview first★ 227↓ —
- sajn-webhooksNewhookdeck/webhook-skillsReceive and verify sajn (sajn.se) e-signature webhooks. Use when setting up a sajn webhook endpoint, getting the whsec_ signing secret, debugging webhook-id / webhook-timestamp / webhook-signature (Standard Webhooks) verification, or handling events like document.completed, document.fully_signed, document.party.signed, document.party.delivery_failed, document.rejected and identity_check.verified.EngineeringNo warnings★ 97↓ —
- commitPaulRBerg/agent-skillsCommit staged or intended changes: compose a Conventional Prefix or Natural Language message, then use ai-commit — with --all, --staged, --close, --finding, or --push. Also squash a branch into one commit with --squash.EngineeringNo warnings★ 104↓ —
- copy-transcript-pathPaulRBerg/agent-skillsCopy the active Claude Code or Codex CLI chat transcript path to the macOS clipboard.EngineeringNo warnings★ 104↓ —