GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
chembl-database
Query the ChEMBL database for bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures. Use when the user asks about compounds, targets, IC50/Ki values, drug mechanisms, or structure searches.
alphagenome-single-variant-analysis
Analyzes genetic variant effects on gene expression (RNA-seq), chromatin accessibility (DNASE), histone marks (ChIP), and transcription factors using the AlphaGenome API. Use when the user asks about non-coding variant effects, pathogenicity, clinical significance, disease associations, functional effects, gene expression changes, splicing disruption, or regulatory effects in promoters and enhancers. Also use for resolving biological terms to tissue/cell-type ontologies (UBERON/CL) or analyzing variants in chr:pos:ref>alt format.
alphafold-database-fetch-and-analyze
Retrieve and analyze AlphaFold predicted structures for a protein. Use when the user provides a specific UniProt Accession ID and wants structural confidence metrics (pLDDT), domain boundary analysis, or disorder assessment. Do not use if the user only has a protein name, gene name, or amino acid sequence — ask for a UniProt ID first.
writing-great-prompt
Prompt-contract authoring for frontier reasoning and coding agents. Use when the user wants a new implementation prompt, a phased agent task, a copy-ready prompt, or an evidence-based upgrade of an existing prompt that should work across capable model providers.
uv-env
Create and manage Python project environments with the uv package manager. Use whenever the user wants to set up a new Python project, create a virtual environment, initialize a pyproject.toml, install/add Python packages, lock or sync dependencies, or pin a Python version — even if they don't explicitly mention "uv". Prefer this skill over raw pip/venv/conda for any Python environment work in a project directory.
task-file-builder
Interactively draft a well-structured `task.md` brief for Claude Code by walking the user through Objective, Acceptance Criteria, Relevant Files, Constraints, Background, Known Context, and Questions based on Opus 4.7 best practices. Use this skill whenever the user wants to prepare a task, brief, spec, prompt, plan, or instructions for Claude Code to execute in a fresh session — even if they don't explicitly ask for a "task file" or "task.md". Trigger on phrases like "help me write a task", "draft instructions for Claude Code", "prepare a brief", "plan what to ask Claude to do", "turn this idea into a task.md", "write a spec for Claude", or "front-load context for a new Claude Code session".
skill-organizer
Registers a newly added skill into a Research-skills-hub collection by updating that collection's index.md and README.md. Handles two collections: collected-skills/ (external skills — needs a source URL and optional license) and open-paper-skills/ (skills the repo owner authored — provenance is Original or Adapted, no external URL required). Use whenever: a new SKILL.md has been dropped into research-skills-hub/collected-skills/ or research-skills-hub/open-paper-skills/; the user says they added a new skill (with or without a source URL); the user asks to update a collection's index or README. Always invoke when the user adds a skill to either collection — even if the request is phrased as 'update the index' or 'register this skill'.
session-handoff
Maintain or resume repository-root HANDOFF.md for cross-session work. Use when recording a task arc that may span sessions, preparing its next-session handoff, or continuing and verifying an earlier arc.
sell-research-honestly
Audit, position, and communicate research value without outrunning the evidence. Use when users need audience-specific buy-in from advisors, collaborators, reviewers, talk audiences, or the research community; want to pitch or promote an idea, paper, result, codebase, or demo; plan research PR; or need to detect and repair overclaiming. Do not use for generic proofreading, summarization, or formatting.
research-skill-installer
Install, remove, disable, enable, list, or check the status of skills from this repository's Research-skills-hub across every registered agent directory — the repository's own, the global ones, and each Research Project's. Use when the user wants an agent to be able to use a hub skill, wants a skill installed into or removed from a specific project or globally, wants to turn a skill off in one place without deleting it, wants to know which research skills are installed where, or wants to check that installs still match the hub.
research-project-manager
Create, inspect, validate, update, sync, or archive Research Projects under `projects-folder/`. Use when asked to start a project from a template or promote an idea into a project, list the project portfolio or check that projects still match the template contract, change a project's stage, status, owner, priority, or next action, archive a project, rewrite the Active Projects table from project memory, or fix a `project contract` failure reported by `./verify.sh`.
research-bible
Research operating-system guidance for ML/AI research. Use this skill when you need to help choose research problems, design experiment loops, improve research taste, debug model training or eval workflows, inspect failures, keep research logs, build reading plans, or turn how_to_be_good_at_research.md principles into concrete plans, checklists, habits, or advice.
project-dispatch
Root-agent workflow that hands Research Tasks to per-project Claude Code or Codex sessions through os-harness. Use when the human asks for work to be done in a project, asks how dispatched work is going, wants a finished run reviewed, revised, or accepted, or wants a run stopped.
paper-wiki-manager
Maintain an OKF paper wiki under `paper-wiki/` or another user-named wiki root, including optional Chinese mirror notes under `papers_zh/`. Use when asked to add arXiv or research-paper URLs, capture non-paper sources such as blog posts, docs, or talks, update or translate paper notes, maintain paper/topic/concept/source indexes, automatically create or update topic summary pages for important new themes, maintain concept entity pages for methods, datasets, benchmarks, metrics, terms, or tools, link papers to research projects, normalize paper metadata, track reading status, compare papers, generate required `viz.html` visualizations, or validate the paper wiki.
paper-search
Search and read research papers across alphaXiv, OpenAlex, bioRxiv, PubMed, Hugging Face Papers, Papers with Code, and arXiv, honouring the human's per-source on/off switches and full-text read order. Use when finding papers, related work, prior art, or code for a method; when reading a paper's full text or record from its id; or when the human asks to switch a source on or off or reorder where papers are read from.
okf-repo-organizer
Organize a repository, folder, or knowledge corpus into generic Open Knowledge Format (OKF) bundles. Use when you are asked to convert or normalize repo files and folders to OKF, add OKF index/log/concept frontmatter, choose bundle boundaries, migrate idea/project/doc folders into OKF-style structure, or validate generic OKF conformance.
map-then-territory
Map scattered ideas into a human-approved DAG of verifiable states, then drive fresh agents through it edge by edge. Use when the user has a destination or idea fragments but lacks the domain knowledge to identify or sequence the route; when revising a map bundle; when compiling approved edges into launch prompts; or when recording execution evidence, deviations, and human verification.
karpathy-coding-rules
Andrej Karpathy's field notes (CLAUDE.md, v260626) on getting a language model to write code you will NOT have to rewrite — ten earned rules covering read-before-write, think-before-code, simplicity, minimal/surgical diffs, verification, goal-driven execution, debugging, dependency hygiene, communication, and the common failure modes. Read and apply these BEFORE starting ANY coding task: writing new code, editing or refactoring existing code, fixing a bug, adding a feature, implementing from a spec, reviewing a diff, or scaffolding a project — even when the user does not explicitly ask for "best practices" or "clean code." Whenever the task is to produce or change source code, consult this skill first so the rules shape how you read, plan, write, verify, and report.