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.
46,099 skills from 2,198 repositories · updated 10 minutes ago
9,541 skills
- frappe-syntax-hooks-eventsImpertio-Studio/Frappe_Claude_Skill_PackageUse when implementing document lifecycle hooks via doc_events in hooks.py, understanding event execution order, or extending/overriding document behavior from another app. Prevents silent hook failures from wrong event names, incorrect execution order assumptions, and broken override chains. Covers doc_events hook syntax, all document events (before_insert, validate, on_submit, etc.), event execution order, extend vs override behavior, cross-app doc_events. Keywords: doc_events, hooks.py, before_insert, validate, on_submit, on_cancel, lifecycle, document events, override, extend, event order, which event fires when, before_save vs validate, document event list..OtherNo warnings★ 198↓ —
- wedding-budgetmohitagw15856/pm-claude-skillsBuild a wedding budget that survives to the wedding — allocation by real shares, the per-guest lever made explicit, the routinely-forgotten line items priced in from day one, and a contingency that isn't decorative. Use when asked make a wedding budget, how do people split X across a wedding, we have N dollars and M guests, or why is our wedding over budget. Produces the allocation table from the script, the guest-count math, the forgotten-items audit, and the track-against-actuals discipline.OtherNo warnings★ 1.5K↓ —
- devexpress-winforms-tab-controlDevExpress/agent-skillsExpert skill for the DevExpress WinForms XtraTabControl (DevExpress.XtraTab, DevExpress.Win.Navigation NuGet). Build tabbed UIs that organize controls into pages — add/remove XtraTabPage pages via the TabPages collection, populate pages, position and orient headers (HeaderLocation, HeaderOrientation), wrap headers into rows (MultiLine), show Prev/Next/Close header buttons (HeaderButtons) and per-page Close buttons (ClosePageButtonShowMode), respond to selection (SelectedPageChanged/SelectedPageChanging) and close (CloseButtonClick) events, hide headers for wizard-style navigation (ShowTabHeader), add header icons (XtraTabPage.ImageOptions), and add custom header buttons (CustomHeaderButtons). Use when a user asks about WinForms tab control, tabbed pages, XtraTabControl, XtraTabPage, tab headers, closable tabs, tab navigation, or organizing controls into pages on a form. For MDI/document interfaces use DocumentManager or XtraTabbedMdiManager instead.OtherNo warnings★ 66↓ —
- ase-meta-quorumrse/aseQuery multiple foreign AIs in parallel and synthesize a consensus ("quorum") answer with a consensus rating. Use when the user wants a quorum, a consensus answer, or the opinions of multiple AIs on a question.OtherNo warnings★ 60↓ —
- agent-self-evalcoco-research/cocoPost-run self-evaluation system that scores agent output on correctness, clarity, actionability, and conciseness. Use after /team runs, skill executions, or when explicitly asked to evaluate output quality.OtherNo warnings★ 795↓ —
- ase-help-intentrse/aseMatch a free-text intent against the accumulated help of all ASE skills, generate all adequately fitting `/ase:ase-xxx-xxx` commands -- ranked best-fitting first, each with concrete options and arguments -- and let the user execute one of them, refine the intent, or cancel. Use when the user knows what they want but not which skill or flags realize it, or mentions "intent" or requests "help".OtherNo warnings★ 60↓ —
- dedup-skillsOutlineDriven/outline-driven-developmentUse when asked to deduplicate a skill tree, fold overlapping skills, or cut the skill count: analyze, gate per family, then fold. Not for prompt-doctrine cascades: use cascade-dedup.OtherNo warnings★ 55↓ —
- trajectory-analysisawslabs/hcls-agent-skillsSingle-cell trajectory inference pipeline covering diffusion pseudotime (DPT), PAGA, RNA velocity with scVelo, and fate mapping with CellRank. Use when the user mentions pseudotime, trajectory, lineage, differentiation, RNA velocity, scVelo, CellRank, PAGA, diffusion map, fate probabilities, terminal states, spliced/unspliced, velocyto, order cells by development, cell differentiation path, cell fate, branching analysis, monocle, developmental trajectory, stem cell differentiation, progenitor to mature, how do cells differentiate, cell lineage tree, velocity arrows, fate mapping, transition probabilities, root cells, terminal states, absorption probabilities, or latent time.OtherNo warnings★ 68↓ —
- skypilot-multi-cloud-orchestrationKalarisLabs/research-agent-skillsMulti-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.OtherNo warnings★ 76↓ —
- ase-help-skillrse/aseShow the manual page of an ASE skill, addressed by its full name, by any abbreviation of it, or by a description of its purpose, and list the entire skill catalog when no name is given. Use when the user wants the "manual", "man page", "manpage", or "help" of a particular ASE skill, or asks what a certain `ase-xxx-xxx` skill does.OtherNo warnings★ 60↓ —
- verify-thisOutlineDriven/outline-driven-developmentUse when a measurable claim needs before/after proof. Not for fact-checking or done-claim gating: use verify-both-ways or verification-before-completion.OtherNo warnings★ 55↓ —
- final-grainOutlineDriven/outline-driven-developmentUse when asked to push an already-working artifact to finished composition, texture, and feel. Not for remote or irreversible changes. Not for hygiene routing: use clean-and-true.OtherNo warnings★ 55↓ —
- evaluating-llms-harnessKalarisLabs/research-agent-skillsEvaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.OtherNo warnings★ 76↓ —
- torchforge-rl-trainingKalarisLabs/research-agent-skillsProvides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.OtherNo warnings★ 76↓ —
- qdrant-vector-searchKalarisLabs/research-agent-skillsHigh-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.OtherNo warnings★ 76↓ —
- ase-meta-eli5rse/aseExplain a topic in "Explain Like I'm 5" (ELI5) style, optionally grounded in Internet/Web facts. Use when the user wants a topic explained in a very simple, child-friendly way, or mentions "eli5" or "explain like I'm 5".OtherNo warnings★ 60↓ —
- ase-meta-whyrse/aseFive-Whys Root-Cause Analysis.OtherNo warnings★ 60↓ —
- sujet-crfpa-allison-fiorentinolawve-ai/awesome-legal-skills>Ce skill génère des sujets d'entraînement pour les deux épreuves écrites de consultation du CRFPA : l'épreuve de droit des obligations (tronc commun) et l'épreuve de spécialité (civil, affaires, social, pénal, administratif, international et européen, fiscal). Chaque sujet est accompagné d'une grille de notation détaillée sur 20 points. Vous ciblez un thème précis, ou vous laissez le skill procéder à un tirage au sort couvrant l'ensemble du programme. Connexion aux MCP OpenLegi et GoodLegal requise : toutes les références d'articles et d'arrêts sont vérifiées sur les sources officielles, sans citation inventéeOtherNo warnings★ 911↓ —
- minutes-tagsilverstein/minutesLightweight outcome tagging for meetings — won, lost, stalled, great, or noise. Use whenever the user says "tag this meeting", "mark that as a win", "that one was a loss", "tag yesterday's call as stalled", "mark this great", "that meeting was noise", "label that meeting", or any time they describe a meeting outcome in passing. Tagging takes 5 seconds and unlocks /minutes-mirror correlation analysis — the more meetings get tagged, the smarter mirror gets at telling the user what behavior patterns lead to wins. Surface this skill any time the user mentions a meeting result, win, loss, or wasted time.OtherNo warnings★ 1.6K↓ —Also in 1 other repo
- finishing-a-development-brancharbiterForge/codeArbiterOpen a PR or finish branch disposition; route CI watching and post-merge cleanup to their owners. Merge and discard need explicit authority.OtherNo warnings★ 149↓ —
- uber-directAnil-matcha/awesome-muse-connectorsQuote and dispatch same-day Uber Direct courier deliveries, and check their status. Trigger phrases: uber direct, same-day delivery, dispatch courier, delivery quote.OtherNo warnings★ 1.4K↓ —
- slime-rl-trainingKalarisLabs/research-agent-skillsProvides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.OtherNo warnings★ 76↓ —
- leaf-agricultureAnil-matcha/awesome-muse-connectorsRead and manage farm data through Leaf Agriculture: fields, boundaries, machine operation files, and as-applied irrigation. Trigger phrases: leaf agriculture, farm data, field boundaries, as-applied irrigation, john deere data, operation files.OtherNo warnings★ 1.4K↓ —
- ray-trainKalarisLabs/research-agent-skillsDistributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.OtherNo warnings★ 76↓ —