constraint-driven-development
addyosmani
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thr…
91.4KGitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “awesome-vibe-coding”
49–64 / 378
More filters · 1
Candidates in this shortlist, not the full registry. GitHub stars belong to repositories, not individual skills.
Results: 378
demand-first-review
CherryHQ
Use when reviewing a PR, API, IPC channel, endpoint, parameter, type, config, or architectural extension point that adds or expands shared surface area, especially when…
51KGitHub
LiteratureDL4Graph
DeepGraphLearning
A comprehensive collection of recent papers on graph deep learning
ResearchSkill source unconfirmed
3.1KGitHub
claude-automation-recommender
CherryHQ
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to op…
50.9KGitHub
cherry-assistant-guide
CherryHQ
从当前安装包查询 Cherry Studio 产品信息并排查运行问题。当用户询问功能、路由、快捷键、Provider、语言、Agent、频道、定时任务、Code CLI、当前版本，或报告运行错误、连接失败、配置异常并需要诊断时触发。
50.9KGitHub
code-mate-hermes
CherryHQ
Runs Hermes Agent in one-shot mode for bounded local tasks. Use when the user explicitly asks to delegate work to Hermes and accepts its automatic tool approval behavior.
51.1KGitHub
gh-pr-review
CherryHQ
Automated Cherry Studio review for local branches, PRs, commits, files, architecture docs, and repository skills. Use for code or documentation reviews that need project…
51.1KGitHub
cherry-studio-feedback
CherryHQ
收集、脱敏、预览并提交 Cherry Studio BUG、UI/UX 或功能反馈，默认提交到飞书。可在用户同意后调用内置诊断工具整理环境、错误日志、截图和用户导出的 trace，自动提交飞书表单或生成匿名上传 ZIP；也可安全解析反馈 ZIP 为表单字段。用户说“提交问题”“提交反馈”“上报 bug”“收集/上传错误信息”“整理日志/…
50.9KGitHub
cherry-electron-dev
CherryHQ
Develop, fix, and profile Cherry Studio in a tracked Electron instance. Use for everyday implementation, UI and interaction work, bug fixing, runtime debugging, DevTools…
51.4KGitHub
issue-reporter
CherryHQ
只在用户明确要求提交 GitHub Issue、GitHub Bug Report 或 GitHub Feature Request 时使用。用户只说“提交问题”“提交反馈”“上报 bug”“这是个 bug”或描述功能建议但未点名 GitHub 时不得触发，必须改用 cherry-studio-feedback 并默认提交飞书。
50.9KGitHub
skills-manager
CherryHQ
搜索、安装和协调创建 Claude Code Agent Skills。当用户想要搜索技能、安装工具、创建自定义 Skill，或者说"find a skill"、"搜索技能"、"帮我做个 skill"、"create a skill"时触发。也适用于用户说"有没有做 X 的工具"、"我想扩展 Agent 能力"，或当前能力不足需要先查找…
50.9KGitHub
code-mate-kimi-code
CherryHQ
Runs Kimi Code in non-interactive prompt mode and parses its event stream. Use when the user asks to delegate a bounded repository task to Kimi Code.
51.1KGitHub
code-mate-deepseek-harness
CherryHQ
Runs DeepSeek Harness headlessly for bounded repository tasks. Use when the user asks to delegate analysis or implementation to DeepSeek Harness.
51.1KGitHub
customer-research
coreyhaines31
When the user wants to conduct, analyze, or synthesize customer research. Use when the user mentions "customer research," "ICP research," "talk to customers," "analyze t…
46.6KGitHub
code-mate-openclaw
CherryHQ
Runs a local OpenClaw agent non-interactively and returns its structured response. Use when the user asks to delegate a bounded task to the OpenClaw main agent.
51.1KGitHub
clinical-reports
K-Dense-AI
Create safety-bounded draft structures and run local deterministic checks for clinical case, diagnostic, trial, safety, and aggregate research reports. Use only with syn…
41.4KGitHub