OPENAGENTSKILL / DIRECTORY

AI Agent Skills

为下一项任务找到合适的技能。探索适用于 Codex、Claude Code、Cursor 等 Agent 的工具。

全部 Skills

5,170 Skills

搜索结果: 5170

开发与测试

暂未收录效果图

查看技能说明

Structured co-authoring workflow for specifications, proposals, decision docs, PRDs, RFCs, and other substantial written artifacts. Use when Codex should help a user gat…

价格未确认开发与测试Claude CodeOpenAI Agents
52GitHub
开发与测试

暂未收录效果图

查看技能说明

code-review

martinffx

Multi-agent code review with parallel specialized reviewers, architecture validation, challenge validation, and durable handling of previously decided findings. Use `rq`…

价格未确认开发与测试Claude Code
46GitHub
开发与测试

暂未收录效果图

查看技能说明

Implementation subagent dispatch patterns. Use when independent implementation work is available and subagents can execute it. Covers parallel dispatch, shared-tree patc…

价格未确认开发与测试Claude Code
46GitHub
开发与测试

暂未收录效果图

查看技能说明

spec-finish

martinffx

Post-implementation completion workflow for Spec-backed Plans. Use after spec-implement completes to validate, review, create stacked commits, and open a PR via code-pul…

价格未确认开发与测试Claude Code
46GitHub
开发与测试

暂未收录效果图

查看技能说明

User and grant management for Google Play Console via gplay users and gplay grants commands. Use when asked to manage developer account users, account-wide permissions,…

价格未确认开发与测试Claude Code
45GitHub
开发与测试

暂未收录效果图

查看技能说明

Monitor Android app stability and performance from the Play Developer Reporting API via gplay vitals. Use to query crash/ANR rates, detect release regressions with anoma…

价格未确认开发与测试Claude Code
45GitHub
开发与测试

暂未收录效果图

查看技能说明

anti-ai-slop

DeevsDeevs

After working on the code, ensure the branch contains only the minimal, idiomatic changes by removing AI-generated slop introduced on this branch.

价格未确认开发与测试Claude Code
41GitHub

指南与对比

开发者入口