Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
46,700 skills from 2,243 repositories · updated 9 hours ago
10,031 skills
- accountsonilo-ai/skillsCheck the Sonilo account's available services, rate limits, free-trial allowance, and usage/billing history. Use before calling a paid Sonilo tool to confirm it's available and whether free-trial runs remain, or when the user asks about their Sonilo usage, limits, or billing.OtherNo warnings★ 117↓ —
- fieldsparcadei/Continuous-Claude-v3Problem-solving strategies for fields in abstract algebraOtherNo warnings★ 3.9K↓ —
- repo-mapejboy/agent-scriptsCompatibility skill for existing RepoMap instructions. RepoLink and repolink are canonical for new usage.OtherNo warnings★ 117↓ —
- decision-journalitseffi/agentic-osCreate structured records of decisions with expected outcomes, probabilities, and quit conditions. Use for important decisions.OtherNo warnings★ 117↓ —
- draft-responseBevel-Software/HexisDraft a professional customer-facing response tailored to the situation and relationship. Use when answering a product question, responding to an escalation or outage, delivering bad news like a delay or won't-fix, declining a feature request, or replying to a billing issue.OtherNo warnings★ 120↓ —
- zhangyi-systemsaph199686/zhangyi-studio张翼机制与系统设计：核心循环细化、新机制评审过闸、数值纪律与平衡裁决。每个机制必须回答'解决哪个病灶'、区分'强化内核还是堆系统'、推演诱发的玩家行为与情绪，输出系统裁决书。Use when the user designs mechanics/systems, tunes numbers or balance, evaluates adding a new mechanic, designs core loop details, or asks whether a feature is worth building. 用户设计机制与系统、调数值做平衡、纠结加不加某个机制、细化核心循环、或问某个功能值不值得做时使用。OtherNo warnings★ 119↓ —
- expansion-whitespaceBevel-Software/HexisFind the expansion whitespace in an account or a book - what they own vs. what they could own, the evidence for each play, and the open opps to create. Use when the user asks "what's the whitespace at [account]", "where can I expand [account]", "upsell opportunities in my book", or "which customers should I be growing".OtherNo warnings★ 120↓ —
- ardot-create-new-filebalabalabalading/huuuuuuho-skills**强制性前置条件** — 每次调用 `create_new_page` 工具之前，必须先调用此技能。 未经加载此技能，绝不能直接调用 `create_new_page`。 当用户想要在 Ardot 设计文件中创建新页面时触发。 关键词：在 Ardot 上下文中的"创建新页面"、"添加页面"、"新画布"。OtherNo warnings★ 118↓ —
- crm-hygiene-checkBevel-Software/HexisRead-only audit of your CRM opportunities for missing fields, stale dates, and stage mismatches - outputs a fix checklist to apply by hand or through update-opportunity. Use when the user asks "check my CRM hygiene", "check my Salesforce or HubSpot data", "clean up my CRM", "audit my opps", "what's missing in the CRM", or "clean up my pipeline".OtherNo warnings★ 120↓ —
- startup-ideafabricioctelles/skillsAnalyze startups with Paul Graham mindset (pressure, founder-market fit, brutal validation), Dan Koe discipline (monetization, offer, distribution, sales), and Seth Godin principles (differentiation, narrative, smallest viable audience). Triggers on startup idea, business validation, MVP, first customers, revenue model, GTM, product-market fit, "I have an idea".OtherNo warnings★ 122↓ —
- limit-based-strategyitseffi/agentic-osDevelop a limit-based product strategy with convergence milestones, acceleration levers, assumptions, and phased execution.OtherNo warnings★ 117↓ —
- ribaoorziz/odai日报、周报、工作总结、状态更新：基于可核证事实形成完整汇报。用户要求汇报一段时期的工作、沿用既有汇报模板、整理进展与风险，或 odai 判断专业汇报工艺会改善结果时使用。OtherNo warnings★ 119↓ —
- inbox-sweepBevel-Software/HexisBatch-process unread customer emails - classify, prioritize, and draft replies. Use when the user asks "sweep my inbox", "what customer emails need a reply", "draft replies to my customer emails", or "what needs a response".OtherNo warnings★ 120↓ —
- llm-finops-routerroedyrustam/vibes-plugAI FinOps, dynamic model routing (LiteLLM), and token cost control / FinOps AI, routing model dinamis (LiteLLM), dan kontrol biaya token.OtherNo warnings★ 115↓ —
- manga-full-stackSwotAtmk/infinite-creationAI漫剧全栈技能包：基于19份专业资料整合的AI漫剧全流程制作技能，覆盖分镜提示词（14要素公式）、角色一致性控制（五维框架+参考图锁定+参数固化）、剧本结构设计（三段式+万能故事公式）、多风格体系（3D动漫/古风玄幻/赛博朋克/暗黑悬疑）与50+运镜提示词模板。OtherNo warnings★ 130↓ —
- era-consistency-optimizerSwotAtmk/infinite-creation年代一致性优化器：优化AIGC漫剧提示词，确保场景中出现的所有道具、科技产品、服饰、建筑、交通工具等元素与指定年代完全匹配，避免出现时代错误物体，提升生成内容的真实感与专业度。触发：明确或隐含的时代背景（如唐朝、90年代中国、维多利亚时期、近未来2045年等）。OtherNo warnings★ 130↓ —
- connectednessparcadei/Continuous-Claude-v3Problem-solving strategies for connectedness in topologyOtherNo warnings★ 3.9K↓ —
- end-of-dayBevel-Software/HexisThe closing beat of the day - every call processed or explicitly skipped, the CRM brought current, commitments captured, and tomorrow's top three teed up. Use when the user says "end of day", "close out my day", "process today's calls", "EOD", or on an evening schedule. Companion bookend to daily-briefing.OtherNo warnings★ 120↓ —
- tool.setup_slack.2e0c4f53cfa18218AI45Lab/OpenARTSets up the Slack messaging adapter with agent-first config, reload, verification, and identity linking steps. Use when onboarding or repairing Slack channel integration.OtherNo warnings★ 255↓ —
- agent-ready-personal-agent-protocolfabricioctelles/skillsSub-skill: Implement Personal Agent Protocol (Poppy) discovery. Publish /.well-known/poppy.json (draft 0.1) and validate its OAuth issuer binding. Informational check; does not affect level or score.OtherNo warnings★ 122↓ —
- janitor-fixkhendzel/skills-janitorAutomatically fix skill problems (safe preview first). Also use with --prune to find and remove broken symlinks, empty directories, and orphaned skills. Trigger with '/janitor-fix'.OtherNo warnings★ 122↓ —
- stakeholder-mapBevel-Software/HexisMap the people in a deal or account - roles, influence, sentiment, who's missing, and your best access path to the people you haven't reached. Use when the user asks "who are the players at [account]", "who's my way in", "am I single-threaded on [deal]", "map the stakeholders", or "who else should I be talking to".OtherNo warnings★ 120↓ —
- math-intuition-builderparcadei/Continuous-Claude-v3Develops mathematical understanding through examples, visualization, and analogyOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- root-cause-analysisitseffi/agentic-osUncover root causes through recursive Why questioning and consequence exploration. Use before acting on problems.OtherNo warnings★ 117↓ —
prompt-optimizer
TestAny-io/testany-agent-skills
OtherUpdated 5 days ago
From the author
撰写提示词、优化提示词、改写 Prompt、Prompt 优化。Use when: 用户需要创建或修改可执行提示词；按任务、调用方输出契约与实际工具能力优化，不按模型品牌强制格式。
Install
npx skills add TestAny-io/testany-agent-skills --skill prompt-optimizer -a claude-code
Installs to .claude/skills/prompt-optimizer/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyNo network use seenLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 83
Security100
Provenance63
Maintenance100
Licence100
Adoption33
Files (4)
- SKILL.md
- agents/openai.yaml
- assets/testany-logo-small.png
- assets/testany-logo.svg