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.
32,478 skills from 1,425 repositories · updated 13 minutes ago
2,017 skills
- clickupAnil-matcha/awesome-muse-connectorsList ClickUp workspaces and tasks, and create tasks. Trigger phrases: clickup, clickup tasks, my clickup list.ProductivityNo warnings★ 1.4K↓ —
- todoistAnil-matcha/awesome-muse-connectorsList tasks, create tasks, and complete them in Todoist. Trigger phrases: todoist, my tasks, add a task, todo list.ProductivityNo warnings★ 1.4K↓ —
- create-workflow-diagramgooseworks-ai/goose-skillsCreate FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.ProductivityNo warnings★ 1.3K↓ —
- skill-routerrohitg00/pro-workflowThe index of every pro-workflow skill and command, grouped by job, with when to reach for each and whether it is human-run or auto-triggered. Use when you are not sure which skill fits, want the full map, or ask "what can this do", "which skill for X", "list the workflow".ProductivityNo warnings★ 2.9K↓ —
- pro-workflowrohitg00/pro-workflowComplete AI coding workflow system. Orchestration patterns, 18 hook events, 8 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.ProductivityNo warnings★ 2.9K↓ —
- deepmd-finetune-dpa3jinzhezenggroup/computational-chemistry-agent-skillsFine-tune a DPA3 model in DeePMD-kit using the PyTorch backend. Use when the user wants to adapt a pre-trained DPA3 model to a new downstream dataset. Supports fine-tuning from a self-trained DPA3 model (.pt checkpoint), from a multi-task pre-trained model, or from a built-in pretrained model downloaded via `dp pretrained download` (e.g., DPA-3.1-3M, DPA-3.2-5M, DPA-3.3-1M). Covers single-task and multi-task fine-tuning workflows.ProductivityNo warnings★ 154↓ —
- learn-rulerohitg00/pro-workflowCapture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and retrieves rules for future sessions. Use after mistakes or when the user says "remember this", "don't forget", "note this", or "learn from this".ProductivityNo warnings★ 2.9K↓ —
- context-optimizerrohitg00/pro-workflowOptimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.ProductivityNo warnings★ 2.9K↓ —
- wiki-statusAr9av/obsidian-wikiReport wiki ingestion/completeness state, pending source delta, structural insights, or maintenance equilibrium. Use for remaining-work/status questions, hubs and bridges, or whether maintenance skills still have pending changes. wiki-digest summarizes learned knowledge instead.ProductivityReview first★ 3.6K↓ —
- adjudicative-ai-impartiality-challengeNewlawve-ai/awesome-legal-skillsPublic-safe preliminary screen for challenges to the impartiality of an AI evaluator, LLM-as-a-judge, decision-support agent, or adjudicative system based on prior outputs, suspected bias, unstable reasoning, or self-reinforcing memory. Use when asked whether an AI should be recused, disqualified, replaced, audited, or escalated. Does not decide real cases or claim that human judicial-recusal doctrine automatically applies.ProductivityNo warnings★ 894↓ —
- disclosure-strategy-mapper-larissa-meredith-flisterlawve-ai/awesome-legal-skillsThis skill maps disclosure strategy from a case summary, pleading, chronology, or early case theory: the document categories that will matter, likely custodians, adverse material, evidential gaps, search themes, and the risks worth confronting early.ProductivityNo warnings★ 894↓ —
- learning-notes-automationchubbyguan/chubbyskills学习笔记自动化：视频/播客转录 → 知识点提取 → 闪卡生成 → 知识图谱更新。触发词：学习笔记、闪卡、Anki、知识提取、视频学习ProductivityNo warnings★ 1.3K↓ —
- context-budgetcoco-research/cocoAudit token consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations. Use when the context window is filling up too fast or before adding new components.ProductivityNo warnings★ 784↓ —
- relaxjinzhezenggroup/computational-chemistry-agent-skillsPrepare DFTB+ geometry-relaxation task inputs from a user-provided structure and optimization settings. Use when the user needs ion-only or cell-coupled structural optimization.ProductivityNo warnings★ 154↓ —
- staticjinzhezenggroup/computational-chemistry-agent-skillsPrepare VASP static SCF input tasks from a user-provided structure and essential DFT settings. Use when the user needs single-point electronic structure/total-energy calculations with INCAR generation, KSPACING-based k-point policy (or explicit KPOINTS on request), and POTCAR mapping instructions.ProductivityNo warnings★ 154↓ —
- project-docscoco-research/cocoUse when starting a new project, onboarding to an existing product, or auditing an existing folder structure against the standard. Scaffolds the 16-document set, folder structure, project memory and doc-sync config.ProductivityNo warnings★ 784↓ —
- relaxjinzhezenggroup/computational-chemistry-agent-skillsPrepare GPAW geometry-relaxation task inputs/scripts from a user-provided structure and essential optimization settings. Use when the user needs structure optimization with explicit optimizer and force-convergence policies.ProductivityNo warnings★ 154↓ —
- mdjinzhezenggroup/computational-chemistry-agent-skillsPrepare DFTB+ molecular-dynamics task inputs from a user-provided structure and MD controls. Use when the user needs finite-temperature trajectories using DFTB+.ProductivityNo warnings★ 154↓ —
- dpdisp-submitjinzhezenggroup/computational-chemistry-agent-skillsRun Shell commands as computational jobs, on local machines or HPC clusters, through Shell, Slurm, PBS, LSF, Bohrium, etc. USE WHEN the user needs to submit batch jobs to a cluster, run commands on a remote server, execute tasks via job schedulers (Slurm, PBS, LSF), or safely run long-term/background shell commands that require state tracking and auto-recovery.ProductivityNo warnings★ 154↓ —
- recherche-doctrinelawve-ai/awesome-legal-skillsRecherche académique dans les bases de données de doctrine juridique française, européenne et internationale. Utiliser cette skill lorsque l'utilisateur demande de rechercher des articles de doctrine, des thèses, des ouvrages académiques, ou des travaux universitaires en droit — y compris en droit comparé. Sources principales : ISIDORE (agrégateur SHS du CNRS incluant Cairn.info, Persée, OpenEdition), HAL (archive ouverte française), OpenAlex (base ouverte mondiale 250M+ travaux), Semantic Scholar, CrossRef, Persée (OAI direct), et CORE. Couvre la doctrine juridique francophone ET internationale avec workflow bilingue intégré pour le droit comparé. Déclencher aussi pour : bibliographie commentée, état de l'art, revue de littérature juridique, recherche d'auteur, vérification de citation, analyse bibliométrique.ProductivityNo warnings★ 894↓ —
- notion-pmborghei/Claude-SkillsNotion expert for product management workflows. Use for database design for PRDs/OKRs/Roadmaps/Decisions, property and view design, page architecture, Notion REST API, and sync with Jira, Linear, and GitHub.ProductivityNo warnings★ 971↓ —
- mcp-larkaahl/skillsBased on FeiShu(飞书) / Lark's OpenAPI MCP server, manage user information, chats, emails, cloud documents, multidimensional tables, tasks, calendars, etc.ProductivityNo warnings★ 164↓ —
- okf-principlesserradura/okfRestructure agent instruction artifacts (Claude Agent Skills, rules files, CLAUDE.md, playbooks) by applying five structural principles derived from the Open Knowledge Format - bounding the worst-case context a question loads (the mean may rise; the win is the tail and answer accuracy) and making cross-references survive rewrites. Use this skill whenever the user wants to split a monolithic skill or reference file, reduce context loaded per question, add an index layer, make cross-references survive rewrites, or audit a skill's structure for efficiency. Also use it when the user mentions progressive disclosure, token-efficient skills, or restructuring instructions for agents.ProductivityNo warnings★ 180↓ —
- context-creationarbiterForge/codeArbiterBuild source-backed project context through bounded inspection, optional agents, and safe selected writes.ProductivityNo warnings★ 148↓ —