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
devspark-upgrade
Check the installed DevSpark version, identify stale framework files, and guide a safe upgrade to the latest release
finnhub-stock-api
Integrate with Finnhub Stock API for real-time and historical stock market data. Covers quote fetching, company profiles, and WebSocket streaming.
devspark-update-pr
Update an existing pull request description with current branch delta, preserving linked work items and metadata
devspark-taskstoissues
Explain why temporary DevSpark tasks cannot be exported as durable issue-tracker records.
enhance-typescript-ui-components
Add visual features (thumbnails, badges, dynamic styling) to TypeScript components by coordinating TypeScript logic changes with CSS updates
devspark-tasks
Coordinate dependency-ordered work when it is useful. Generates tasks.md for existing specification bundles; on work branches identifies deliverables and persists them only when continuity or coordination requires it.
dynamic-panel-component
Create a dashboard panel component with advanced dynamic content updates and robust error handling, including retry logic and state management, using vanilla TypeScript DOM API.
devspark-specify
Understand new work and start the universal implementation path without choosing a workflow size.
devspark-site-audit
Perform comprehensive codebase audit against project constitution/standards, producing structured compliance report
dir-verify-parallel-shell-audit
Diagnose and resolve file access issues by verifying directory structure, reading multiple files in parallel batches, running combined shell property checks (head/wc-l) in the same iteration as directory listing, and validating TypeScript import patterns — all with built-in guidance to minimize total iteration count.
devspark-repo-story
Analyze full repository commit history and produce a compelling narrative for both business and technical audiences
data-service
Create data fetching services with circuit breaker pattern for API resilience. Services handle fetch, cache, retry, and expose typed data to panel components.
devspark-release
Seal a release from the verified repository delta, sweep .devspark.work retention and archive-eligible work, and keep current knowledge accurate.
data-service-proxy-direct
Create resilient data fetching services with circuit breaker pattern, supporting both proxied and direct API calls. Services handle fetch, cache, retry, and expose typed data to panel components.
devspark-quickfix
Optional lightweight WHAT/WHY/HOW record for a defect you have already diagnosed, with targeted constitution checks. /devspark-specify handles fixes too, without a record.
devspark-pr-review
Perform constitution-aware pull request review with actionable feedback for any PR in the repository
data-service-optional-params
Create data fetching services with circuit breaker pattern for API resilience, including a first-class pattern for building optional query parameters via URLSearchParams. Services handle fetch, cache, retry, optional filters, and expose typed data to panel components.
devspark-planning-review
For an existing specification bundle, run Analyze, Critic when applicable, and Judge as one bounded planning decision before implementation. On a work branch, Judge only adjudicates a genuine conflict on demand.