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.
45,286 skills from 2,181 repositories · updated 16 minutes ago
2,579 skills
- cossno-ai/sno-station-skillsMANUAL-ONLY: load solely when the human owner types `/cos`, uses `$cos`, or asks you to act as the Chief of Staff (COS). The COS is the one agent the owner talks to; it coordinates the owner and the per-project Project Leads (PLs). A task card, charter, or dispatch makes you an executor, not COS.ProductivityNo warnings★ 731↓ —
- heartbeatsno-ai/sno-station-skillsSet recurring checks or completion watches with `sno heartbeat` and its persistent log reader. Use for periodic reports or unattended long runs. Not for calendar scheduling or commands watched directly.ProductivityNo warnings★ 731↓ —
- handoffsno-ai/sno-station-skillsTransfer full task ownership to a fresh agent with a verified brief and explicit release. Use for replacing the current executor, including a directly assigned task with no work card; not for supervising a helper.ProductivityNo warnings★ 731↓ —
- reachsno-ai/sno-station-skillsContact another agent, exchange work cards, inspect replies, or manage reachable seats through the installed Reach program. Use for communication; full task ownership transfer belongs to handoff.ProductivityNo warnings★ 731↓ —
- cold-email-verifierVarnan-Tech/opendirectoryUse when the user wants to verify cold emails, enrich a lead list, or autonomously guess email addresses from a CSV using ValidEmail.co or the open-source Reacher engine.ProductivityNo warnings★ 686↓ —
- task-clarifierdongshuyan/compass-skillsDeep need-clarification skill. Use only when the user explicitly invokes $task-clarifier. Once activated, keep asking until all three goals are met: the user fully understands their own needs, the AI fully understands the user's needs, and the user confirms the AI's understanding is correct. Do not intervene in task execution unless explicitly invoked.ProductivityNo warnings★ 761↓ —
- ima-notescountbot-ai/CountBot通过 IMA OpenAPI 处理笔记任务。支持搜索笔记、读取笔记、列出笔记、新建笔记、追加笔记。用户提到笔记、备忘录、记一下、追加到某篇笔记时使用。ProductivityNo warnings★ 782↓ —
- emailcountbot-ai/CountBot通过 QQ 或 163 邮箱发送和接收邮件。支持发送普通邮件、带附件邮件、接收邮件、检查新邮件。当用户要求发送邮件、查看邮件、检查新邮件时使用。ProductivityNo warnings★ 782↓ —Also in 1 other repo
- cold-emailborghei/Claude-SkillsWrite and optimize B2B cold email outreach sequences that get replies, covering personalization, follow-up cadence, deliverability, and compliance. Use when writing cold outreach, prospecting/SDR emails, or building outbound sequences.ProductivityNo warnings★ 971↓ —
- engagement-memoryhypnguyen1209/offensive-claudeUse when recalling prior techniques at recon/weaponize, or recording a confirmed finding at report — cross-engagement pattern memory ranked by impactProductivityNo warnings★ 401↓ —
- ai-agent-redteamhypnguyen1209/offensive-claudeUse when red-teaming an agentic AI / LLM application — indirect & zero-click prompt injection, MCP tool poisoning, persistent memory poisoning, excessive-agency tool abuse, multi-turn jailbreaks, PyRIT/Garak/Promptfoo harnessesProductivityNo warnings★ 401↓ —
- eni-firmware-workflowalicewe1/alice_skill[DOCUMENTATION ONLY] [仅文档] Firmware and IoT extraction, filesystem, service, emulation, reverse engineering, validation, and reporting workflow.ProductivityNo warnings★ 53↓ —
- competition-ios-runtimealicewe1/alice_skillInternal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for IPA runtime analysis, Frida hooks, Objective-C or Swift method tracing, Keychain inspection, SSL pinning bypass, URL scheme handling, and iOS request-signing recovery. Use when the user asks to hook an IPA, trace Objective-C or Swift runtime behavior, inspect Keychain or plist state, bypass pinning, analyze deeplinks or universal links, or replay accepted iOS requests. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.ProductivityNo warnings★ 53↓ —
- ollvm-recovery-workflowalicewe1/alice_skillAlice 集成技能包 · 放进去就能用 · Drop-in skill suite for AI coding agentsProductivityNo warnings★ 53↓ —
- notion-infographicRylaispirit/rylai-codex-hermes-skillsTurn articles, notes, transcripts, or research into a consistent series of clean hand-drawn infographics with concise text and visual verification.ProductivityNo warnings★ 60↓ —
- summarise-ecosystem-resultsmodem-dev/ossrulesUse when a user says "summarise ecosystem results", "summarize this ty ecosystem report", "what changed in this ecosystem run?", or asks to summarise or summarize ty ecosystem results for a Ruff PR from a PR number, PR URL, GitHub ecosystem-results comment, or detailed HTML report.ProductivityNo warnings★ 64↓ —
- eni-fuzzing-workflowalicewe1/alice_skill[DOCUMENTATION ONLY] [仅文档] Coverage-guided fuzzing workflow for local or authorized targets, including harnesses, corpus design, sanitizers, campaigns, minimization, triage, and regression.ProductivityNo warnings★ 53↓ —
- context-leveltobihagemann/turboReport how much of the session's context window remains. Use when the user asks "how much context is left", "check the context level", "how full is the context window", or "is context running low".ProductivityNo warnings★ 416↓ —
- anarlog-workflowmodem-dev/ossrulesExecute Anarlog work immediately while recording issues, decisions, progress, and lessons in Linear. Use for Anarlog repository or Anarlog desktop, web, mobile, and API work, including related worktrees and ANLG issues. Explicit brainstorming stays discussion-first. Do not use for unrelated repositories or meeting-data queries.ProductivityNo warnings★ 64↓ —
- gapthousandflowers/skillreaperMeasure the loaded-versus-fired gap - what fraction of each category of loaded context is ever actually invoked, and which MCP tools return mostly noise. Use when asked how much of the context is earning its place, or which categories are worst.ProductivityNo warnings★ 62↓ —
- advai-handoffadvai-x/advai-skillsPersists session handoff notes in `.advai/HANDOFF.md` and restores prior context from that file. Invoke when user wants to record current session progress or resume work in a new session.ProductivityNo warnings★ 78↓ —
- goal-progress-barjamditis/claude-skills-journalismUse to show weighted progress for a multi-step task and update it from recorded evidence.ProductivityNo warnings★ 432↓ —
- unlazyaiskillstore/marketplaceAnti-laziness execution discipline for substantial tasks. Use when work keeps coming back half done, when an agent reports done before it is done, when output must be exhaustive rather than fast, on long autonomous runs that tend to stall at 80 percent, or on any invocation like /unlazy, "tree N", "gates", or "do not stop until it is done". v2 enforces completion through gate files and runnable checks instead of promises. Core method is the Depth Tree, which decomposes work into leaves that each get finished against their own gates.ProductivityNo warnings★ 443↓ —
- tmuxaiskillstore/marketplaceRemote control tmux sessions for interactive CLIs, background tasks, and services. Supports sub-tasks, long-running processes, and service management with session persistence and automatic cleanup.ProductivityNo warnings★ 443↓ —