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
migration-management
Manage Migration entities — pending, in-progress, and applied transitions between upstream source versions. Use when an upstream source bumps version (processkit, aibox, a community package), when a user wants to draft a migration plan, when an agent needs to reason about pending migrations, or when working through an in-progress migration.
index-management
SQLite-backed index over all entity files in the project. The read-side foundation for every other MCP server. Use whenever an agent needs to look up entities by ID, kind, state, or text — instead of grepping the filesystem.
id-management
Generate unique entity IDs following the project's configured format. The write-side foundation that every entity-creating skill depends on. Use whenever a new entity is being created and needs an ID, or when validating an ID format, or to inspect the project's ID configuration.
gate-management
Manage Gate entities — validation checkpoints that processes must pass (code review, security scan, tests). Use when defining or updating a checkpoint a process must pass — code review, tests green, security scan, stakeholder approval.
event-log
Append-only event log — the probabilistic record of everything that happened in the project. Use whenever something notable happens that the project should remember — work items created/transitioned, decisions recorded, bindings changed, incidents occurred, releases shipped.
discussion-management
Manage Discussion entities — structured, multi-turn conversations that explore questions and produce decisions. Use when a question or design choice needs multi-turn exploration before a decision is reached — RFCs, design debates, trade-off analyses.
decision-record
Record decisions with rationale, alternatives, and consequences — the ADR pattern as a primitive. Use when a consequential choice is made — architecture, tooling, process, scope, trade-off. Capture WHY, not just WHAT.
cross-reference-management
Conventions and helpers for lightweight relationships between entities expressed as frontmatter references (not first-class Binding entities). Use when linking two entities with a simple, unscoped, untemporal relationship — 'this work item blocks that one', 'this decision relates to that work item'. For scoped/temporal relationships, use binding-management instead.
matrix-first-refactor
Simplify or refactor this repository's matrix-first preprocessing, stability analysis, mechanism reporting, contracts, runners, or compatibility code while preserving audited scientific outputs. Use for staged architectural changes, consolidation, deletion, and new-landscape support.
context-grooming
Review and prune the project context — archive completed work, summarize stale entries, and propose disabling unused skills.
paper-writing-renato
Draft, revise, and critique research papers (abstract, introduction, setup, method, theory, experiments, discussion, captions) in the style of Renato Berlinghieri, as learned from his PhD advisor Tamara Broderick at MIT (statistics / probabilistic ML). Also follows Jesse Shapiro's "four steps" process (aspirational intro → research → robot body → contractual intro). Use this whenever the user is working on a paper, manuscript, arXiv preprint, conference or journal submission, thesis chapter, abstract, contributions paragraph, theorem write-up, figure caption, limitations paragraph, or asks for feedback on academic prose — even if they only paste a LaTeX paragraph and say "does this read ok?" or "tighten this". Also use it when starting a new project ("help me think through the intro for a paper on X").
constraint-management
Manage Constraint entities — rules and limits the project must respect (budget, latency SLO, team size, compliance). Use when recording a rule, limit, or boundary that affects decisions — budget ceiling, latency SLO, regulatory requirement, team bandwidth.
category-management
Manage Category entities — taxonomies and classification schemes that group other entities by type, area, tier, etc. Use when defining a new classification axis (priority levels, bug severity, feature tier, product area) that other entities will be tagged with.
binding-management
Manage Binding entities — scoped, temporal, many-to-many relationships between any two primitives. Use when a relationship between two entities needs scope, time, or its own attributes — e.g. 'Alice is the tech lead for project X from Jan to June' or 'the security gate applies to the release process only on the main branch'.
artifact-management
Create, retrieve, query, and update Artifacts — tangible deliverables produced by the project. Use when storing or retrieving documents, designs, datasets, build outputs, slide decks, or any completed deliverable that should be registered in the project catalog.
agent-management
Orchestrate multi-agent workflows with task decomposition, role assignment, handoff protocols, and per-session context budgeting.
actor-profile
Create and maintain Actor entities — humans and AI agents that participate in the project. Use when adding a new collaborator (human or agent) to the project, updating their preferences/expertise, or querying who does what.
webhook-integration
Webhook design and consumption — payload format, HMAC signatures, idempotency, retries, dead-letter queues, security. Use when implementing a webhook consumer, designing an event-notification system, adding signature verification, or debugging duplicate or failed webhook deliveries.