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.
46,100 skills from 2,198 repositories · updated 7 hours ago
9,541 skills
- source-command-prepare-assetslegioncodeinc/vibe-coding-toolsPrepare the minimum launch assets and accounts with owners, environments, dated costs, prerequisites and blockers.OtherNo warnings★ 94↓ —
- network-boundaries-stingerlegioncodeinc/vibe-coding-toolsChoose firewall, WAF and rate-limit placement from actual network flows. Return one sourced control recommendation with owner and proof gaps. Read README.md for the guide map.OtherNo warnings★ 94↓ —
- time-blocked-turnslegioncodeinc/vibe-coding-toolsFollow a requested agent work cadence. Use for timed blocks, retry limits, checkpoints, questions, and handoff reports. Read references/ for details.OtherNo warnings★ 94↓ —
- customer-support-tooling-stingerlegioncodeinc/vibe-coding-toolsChoose and configure a SaaS support stack. Use for inboxes, AI deflection, SLAs, routing, or founder triage. Read README.md for the guide map.OtherNo warnings★ 94↓ —
- source-command-prepare-native-releaselegioncodeinc/vibe-coding-toolsPrepare a native release artifact matrix with signing, update, install, and device evidence boundaries.OtherNo warnings★ 94↓ —
- vultr-platform-stingerlegioncodeinc/vibe-coding-toolsAssess Vultr workload fit, compute forms, operator duties, data/recovery and dated cost inputs. Use for a read-only Vultr recommendation. Read README.md for guides.OtherNo warnings★ 94↓ —
- source-command-assess-digitaloceanlegioncodeinc/vibe-coding-toolsAssess DigitalOcean service fit with dated responsibilities, eligibility, scaling, recovery and cost inputs for a supplied workload.OtherNo warnings★ 94↓ —
- source-command-onboard-contributorlegioncodeinc/vibe-coding-toolsPrepare and exercise a contributor setup path, first contribution and complete contractor handoff packet when requested using actual repository evidence.OtherNo warnings★ 94↓ —
- digitalocean-platform-stingerlegioncodeinc/vibe-coding-toolsRecommend DigitalOcean App Platform or Droplet fit from supplied workload, data, operator and recovery needs. Prepare dated cost inputs and readiness handoffs; no provisioning.OtherNo warnings★ 94↓ —
- teachnota-america/forgecat-agent-profilesTeach the user a new skill or concept, within this workspace.OtherNo warnings★ 93↓ —
- handoffnota-america/forgecat-agent-profilesCompact the current conversation into a handoff document for another agent to pick up.OtherNo warnings★ 93↓ —
- said-it-alreadylegioncodeinc/vibe-coding-toolsMine meeting transcripts for reusable lines the user already said. Use for content ideas, drafts, or authentic social posts. Read README.md for the guide map.OtherNo warnings★ 94↓ —
- source-command-forgelegioncodeinc/vibe-coding-toolsRun queen-wasp-stinger's seven-stage forge pipeline end to end for a brand-new Wasp Nest component, starting with mandatory topic elicitation before any work begins. Trigger with "forge a new stinger", "build a new drone", "we need a new command for X", "create a skill for Y", "make a new rule for Z".OtherNo warnings★ 94↓ —
- math-modelingXiaoMaColtAI/math-modeling-skill当用户要求数学建模、建模竞赛、建模分析、代码求解、结果可视化或生成数学建模论文时使用。支持完整三阶段流程、单独执行任一角色，以及在关键节点使用独立 Subagent 进行阶段内质检；默认只启用质检 Subagent，用户可明确选择额外协作。OtherNo warnings★ 1.9K↓ —Also in 1 other repo
- tracking-quality-trendsjaktestowac/awesome-copilot-for-testersTurns point-in-time quality readings into a trend: archives each run, diffs against the previous one, and reports direction per metric - practices newly present or regressed, coverage movement, flake rate, waivers expiring, eval scores - using limit/current/goal framing. Use when quality reporting is a series of disconnected snapshots, when a team needs to show improvement over a quarter, when a number is quoted with no baseline, or when a regression in the quality system itself should be visible.OtherNo warnings★ 118↓ —Also in 1 other repo
- treatRuya-AI/cozempicPrune bloated session with a prescription. Removes progress ticks, stale reads, duplicate content, and more.OtherNo warnings★ 427↓ —
- reloadRuya-AI/cozempicTreat the current session and auto-resume in a new terminal window.OtherNo warnings★ 427↓ —
- source-command-build-web-applegioncodeinc/vibe-coding-toolsScope and build an authorized web-app slice using an actual supported framework owner and verified boundaries.OtherNo warnings★ 94↓ —
- swiftui-graphicsAThevon/genjutsuAdvanced SwiftUI visuals - Metal shaders (.colorEffect, .layerEffect, .distortionEffect), .visualEffect, Liquid Glass (iOS 26), Canvas, holographic and CRT effects.OtherNo warnings★ 701↓ —
- github-discussion-to-devrel-contentVarnan-Tech/opendirectoryFind recurring confusion in your repo's GitHub Discussions, rank it by urgency, and draft the actual docs fixes and content angles — with verbatim community quotes and source links as evidence.OtherNo warnings★ 686↓ —
- bunshinAThevon/genjutsuSummon shadow clones: genjutsu's full-scale pipeline for a whole website or web app, from scratch or as a full redesign. Harvests the client's real material, researches in parallel, lets Impeccable lead the direction and genjutsu the motion, builds the pages with parallel agents, then loops fixes, verdicts and a cold-eyes art director until only minor issues remain, the round cap of the chosen tier is reached, or a round fixes nothing. Announces its cost first and asks twice. Web. Needs a host that can spawn subagents.OtherNo warnings★ 701↓ —
- rag-evalagentscope-ai/OpenJudgeUse when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues. Also use when the user mentions RAG evaluation, faithfulness checking, hallucination detection in RAG, retrieval quality, chunking optimization, or "is my RAG pipeline working." Outputs a diagnostic matrix that pinpoints whether problems are in retrieval or generation.OtherNo warnings★ 981↓ —
- graphic-chartVarnan-Tech/opendirectoryGenerates data visualization charts (bar, line, area, pie, doughnut, scatter, radar, treemap) as PNG using Apache ECharts v6. 1080×1080px default, 5 style presets, highlight annotations. Trigger when user says "create a chart", "visualize data", "make a bar chart", "line graph", "pie chart", "data visualization", "chart this data", "plot", "graph", or "visualize these numbers".OtherNo warnings★ 686↓ —
- hackernews-intelVarnan-Tech/opendirectoryMonitors Hacker News for user-configured keywords, deduplicates against a local SQLite cache, and sends Slack alerts for new matching posts. Use when asked to monitor Hacker News for mentions, track keywords on HN, get alerts when something is posted about a topic on Hacker News, or set up HN keyword monitoring. Trigger when a user mentions Hacker News alerts, HN monitoring, keyword tracking on HN, or wants to know when a topic appears on Hacker News.OtherNo warnings★ 686↓ —
no-lead-left-behind-lead-treatment-audit
zapier/gtm-cheat-codes
OtherUpdated Jul 13, 2026
From the author
Audit lead handling quality across GTM systems and identify missed or low-quality follow-up.
Install
npx skills add zapier/gtm-cheat-codes --skill no-lead-left-behind-lead-treatment-audit -a claude-code
Installs to .claude/skills/no-lead-left-behind-lead-treatment-audit/ · 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 81
Security100
Provenance71
Maintenance70
Licence100
Adoption42
Files (6)
- ONBOARDING-PROMPT.md
- README.md
- SCHEMA-MAP.md
- SETUP.md
- SKILL.md
- metadata.yaml