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
parallel-execution
Build-test orchestration protocol for choosing and running parallel or serial implementation lanes with shared requirement contracts, convergence gates, and triage routing. Use when coordinating multiple concurrent implementation paths, managing convergence gates, or running triage routing. DO NOT USE FOR: exploring ideas or trade-offs (use brainstorming) or evaluating architecture (use software-architecture).
open-for-work
The operating methodology for opening a filed standalone issue for work — the trivial floor, the worth-it doors, beat 1 alignment with its affirmation gate and durable affirmation record, beat 2 routing, and the two outputs (a brief on the routine arm, a continuation into design on the novel arm). Use when `/open {issue}` is invoked, when a `/plan` pre-flight finds an affirmed framing record, or when resuming an issue that already carries one. Activation is by those explicit surfaces only — a bare pickup ("let's work on
naming-register-policy
Two-register naming policy for agent-orchestra: rules for when machine codes stay as-is vs get human names or first-use expansion. Use when authoring human-facing prose, sweeping rename-candidates, or resolving what a code like SMC-20 means. DO NOT USE FOR: deciding whether to create new vocabulary (use design-exploration), auditing docs for general readability (use ai-first-documentation for agent docs or #750/#751 for human docs).
implementation-discipline
Minimal implementation workflow for plan-driven coding. Use when preparing a small implementation slice, applying requirements-first coding discipline, verifying that new code delegates instead of duplicating behavior, propagating a qualifying sentence to several sites, or swapping a term across a migration table. DO NOT USE FOR: test authoring strategy (use test-driven-development) or refactoring-only passes (use refactoring-methodology)
guidance-measurement
Guidance-complexity measurement tooling and usage notes. Use when running or maintaining the guidance measurement script and related deterministic analysis assets for issue #360. DO NOT USE FOR: changing D10 ceiling rules or prompt-facing guidance policy, which remain in agent prompts.
goal-run
Methodology home for the goal-run harness (issue #874): the stage-machine contract, halt-reason precedence, launch arms, worktree lifecycle, the label-to-ledger join query for escape-rate segmentation, and the untrusted-content discipline for a single vendor-goal-loop harness run. Use when extending, halting, resuming, or documenting a /goal-run invocation, or when writing the escape-rate query that segments goal-run PRs from Code-Conductor-orchestrated PRs. DO NOT USE FOR: the live /goal-run execution prose itself (use agents/Goal-Run.agent.md, the shared body this skill is referenced from) or the goal-contract plan-authoring schema (use skills/plan-authoring's goal-contract schema, decision 872-D2).
frontend-design
Guide for creating distinctive UI designs that avoid generic templates. Use when designing new UI components, screens, or evaluating designs for uniqueness and purpose. DO NOT USE FOR: architecture decisions or SOLID evaluation (use software-architecture), open-ended exploration (use brainstorming), or React test strategies (use ui-testing).
frame-spine-lookup
Frame spine lookup methodology for mid-turn slice retrieval by spine-aware specialists. Use when a dispatched specialist needs to fetch an addressable plan slice from the durable plan-issue comment. DO NOT USE FOR: authoring plan spines, emitting frame credits, frame-port adapter declarations, or custom transport implementation.
frame-credit-ledger
Warn-only frame credit-ledger pre-PR hook orchestration. Use when Code-Conductor has just run `gh pr create` and needs to surface frame port-coverage gaps as a non-blocking ledger comment on the new PR, or when a maintainer wants to (re)run the ledger against an existing PR for observation. DO NOT USE FOR: plugin entry-point version-bump guardrails (use `plugin-release-hygiene`), post-merge cleanup or pre-merge strategic assessment (use `post-pr-review`), or any flow that should block PR creation — the ledger is warn-only and never gates the PR.
frame-credit-emission
Frame credit row emission and deferred credit-input methodology for agents and CE Gate surfaces. Use when an agent or skill needs to write frame credits to the PR-body pipeline-metrics block, or when a pre-PR agent needs to persist a credit-input marker for later harvest. DO NOT USE FOR: predicate evaluation logic (use frame port adapter files), or builder function implementation (use frame-credit-ledger-core.ps1).
engagement-record-emission
Marker contract for Segment-A maintainer-evidence and cross-session engagement-state preservation. Use when an agent exits its phase. DO NOT USE FOR: runtime code execution, test writing, or PR creation.
documentation-finalization
Documentation finalization workflow for accuracy, cleanup, and design-doc maintenance. Use when updating implementation-facing docs, synchronizing design documents with shipped behavior, or removing obsolete documentation. DO NOT USE FOR: formal specification drafting (use specification-authoring) or source-code implementation decisions (use implementation-discipline)
design-exploration
Reusable technical design exploration methodology. Use when researching design options, grounding UI changes in the current experience, converging trade-offs into one recommended design direction, proposing a mechanism because a process step did not happen, grounding a chosen option against its rejected alternatives, deciding what an agent judges and what deterministic code checks, designing a record format that claims a property. DO NOT USE FOR: GitHub issue update ownership, adversarial design challenge orchestration, or approval-policy enforcement (keep those in Solution-Designer.agent.md)
customer-experience
Reusable customer framing and CE evidence methodology. Use when turning issue scope into customer journeys, drafting functional plus intent scenarios, or capturing CE Gate evidence against design intent. DO NOT USE FOR: GitHub setup, completion-marker ownership, or adversarial CE prosecution and judgment (keep those in Experience-Owner.agent.md)
copilot-cost-collection
Copilot OTel cost collection setup and interpretation guidance. Use when enabling local Copilot Chat OTel file export, installing the workspace sentinel, or explaining branch-correlated Copilot cost telemetry. DO NOT USE FOR: Claude-native cost capture, durable session memory handoff, review-pipeline scoring logic, or session-cost discipline behavior rules (see skills/terminal-hygiene/SKILL.md § Session-Cost Discipline).
code-review-intake
Deterministic GitHub review intake workflow with ledger-based judgment. Use when processing GitHub code review comments, reconciling Code-Critic findings, or running GitHub review intake mode. DO NOT USE FOR: pre-PR readiness checks (use verification-before-completion) or post-merge cleanup (use post-pr-review).
calibration-pipeline
Calibration and review-pipeline tooling guidance. Use when running or maintaining calibration scripts, review aggregation, and related deterministic assets for issue #360. DO NOT USE FOR: changing orchestration ownership or agent review policy.
browser-canvas-testing
VS Code native browser tool behavior for canvas-based games (Phaser 3, etc.). Use when interacting with HTML canvas elements, clicking game objects, verifying canvas state via browser tools, or when `clickElement` fails on canvas. DO NOT USE FOR: React component tests (use ui-testing) or Playwright E2E tests (use webapp-testing).