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 2 hours ago
10,031 skills
- grace-executeosovv/grace-marketplaceExecute an approved GRACE 4 GraceChangePlan in sequential or parallel-safe mode with recovery-aware preflight and centralized durable apply.OtherNo warnings★ 254↓ —Also in 1 other repo
- groupsparcadei/Continuous-Claude-v3Problem-solving strategies for groups in abstract algebraOtherNo warnings★ 3.9K↓ —
- search-engine-expertUpdatedroedyrustam/vibes-plugFull-text search engines: Typesense, Meilisearch, and Elasticsearch / Mesin pencarian full-text: Typesense, Meilisearch, Elasticsearch.OtherNo warnings★ 115↓ —
- hair-groomarjun988/blender-skillsHair and fur grooming in Blender using curves, particle hair, geometry nodes, and game hair-card workflows. Use for characters, creatures, and real-time hair cards via MCP.OtherNo warnings★ 1.1K↓ —Also in 1 other repo
- materialsarjun988/blender-skillsBlender PBR and stylized material creation for metal, wood, concrete, fabric, glass, dirt, rust, and procedural shaders. Use for look development, material reuse, and production shading in Blender via MCP.OtherNo warnings★ 1.1K↓ —Also in 1 other repo
- otel-sdk-versionsollygarden/opentelemetry-agent-skillsOpenTelemetry release version lookup for SDKs across languages and for the Collector (core, contrib, distributions, builder/OCB), the declarative configuration schema, semantic conventions, and Weaver. Use when choosing the latest compatible released OpenTelemetry SDK, package, or component version, when asked what the latest release of one of these is, and when locating setup docs or examples. Not for Collector build manifests or upgrade-risk assessment.OtherNo warnings★ 116↓ —
- diaoding-zhuangxiu-zhinanzx029w/zhuangxiu-skills吊顶装修指南专用 Skill。覆盖厨卫吊顶、不吊顶与石膏线、材料与工艺、层高与尺寸、客厅吊顶造型等全流程，倒序整合西安装修课堂会员版知识库精华，帮用户装出更省心、不踩坑的吊顶装修。OtherNo warnings★ 85↓ —
- competitive-asset-auditLMTYdotcom/skillsAudit a body of competitive content - battlecards, sales decks, comparison and alternatives pages, enablement, training, help-center copy - against current evidence, and produce the inventory of claims that are stale, unsupported, contradicted, or newly incomplete, ranked by exposure, with the assets each lives in and the owner or skill that should fix it. Use for "audit our competitive materials", "which claims are stale", "what do we need to update across our battlecards and site", "find competitive claims we can no longer support", and any request whose deliverable is the list of claims and how each one holds up - one page or a whole library, with nothing rewritten. Not for producing the update itself - "update X because Y changed" or "fix the talk track" is competitive-enablement-refresh; a new battlecard is competitive-battlecard; whether the message differentiates is competitive-messaging-audit.OtherNo warnings★ 83↓ —
- claude-md-checkclaude-world/director-mode-liteValidate CLAUDE.md structure and completenessOtherNo warnings★ 80↓ —
- asset-managementserac-labs/seracManage ServiceNow hardware assets, software licenses, and lifecycle states on alm_hardware/alm_license — license allocation, CMDB-to-asset linking, warranty tracking, inventory aggregation (HAM/SAM).OtherNo warnings★ 78↓ —
- manju-director-agentSwotAtmk/infinite-creationAI漫剧导演智能体（等价于扣子3工作流方案）。小说→剧本→元素提取→设计提示词→分镜，一步到位。触发：漫剧导演、AI漫剧导演、漫剧智能体、做漫剧、小说转漫剧、帮我做一集漫剧。OtherNo warnings★ 130↓ —
- cp-skill-ingestzby/commonplaceUse when asked to ingest one URL or local snapshot into a tracked .ingest.md source analysis, or to execute a bounded re-ingest request. Retaining quotes in an existing ingest is cp-skill-ground's job, not this skill's.OtherNo warnings★ 91↓ —
- bmod-toolsmithalvin-reyes/better-agentic-ideRequired bmod metadata. Never invoke this skill.OtherNo warnings★ 85↓ —Also in 1 other repo
- challenging-stakeholder-questionsitseffi/agentic-osGenerate rigorous stakeholder challenge questions for proposal or meeting preparation.OtherNo warnings★ 117↓ —
- delivery-probe-libraryzby/commonplaceIndex of the delivery-probe library. Use when the user asks to follow, run, or look up a delivery-probe procedure, instruction, or type by name (for example "retire a widget" or "calibrate the gadget").OtherNo warnings★ 91↓ —
- zhuangxiu-yanshou-zhinanzx029w/zhuangxiu-skills装修验收指南专用 Skill。覆盖水电隐蔽工程、瓦工木工验收、竣工验收与收房、验收工具与清单等全流程，倒序整合西安装修课堂会员版知识库精华，帮用户装出更省心、不踩坑的装修验收。OtherNo warnings★ 85↓ —
- hidden-agendasitseffi/agentic-osIdentify potential hidden agendas of stakeholders. Use before high-stakes meetings with complex motivations.OtherNo warnings★ 117↓ —
- ost-target-selectionitseffi/agentic-osSelect one target opportunity from an OST using evidence-based weighted scoring and tie-breakers.OtherNo warnings★ 117↓ —
- keting-zhuangxiu-bikengzx029w/zhuangxiu-skills客厅装修避坑指南专用 Skill。覆盖客厅布局、沙发茶几、电视墙、吊顶、地砖、背景墙、无主灯、灯光插座、窗帘、阳台、风格搭配、收纳、投影仪、采光动线等全流程，倒序整合西安装修课堂知识库精华，帮用户装出实用又有品质的客厅。OtherNo warnings★ 85↓ —
- problem-structuringitseffi/agentic-osBreak down complex problems into actionable recommendations using deductive and inductive analysis.OtherNo warnings★ 117↓ —
- assumption-mappingitseffi/agentic-osSurface and categorize assumptions underlying product strategy. Use early in development to document what you're betting on.OtherNo warnings★ 117↓ —
- competitor-analysisitseffi/agentic-osAnalyze competitors using Porter's four-component model - drivers, assumptions, strategy, capabilities.OtherNo warnings★ 117↓ —
- verificationitseffi/agentic-osVerify before claiming completion. No claims without fresh verification evidence. Use before marking work done.OtherNo warnings★ 117↓ —
- verification-before-completionSummerEngine/summerRun verification and read its output before claiming work done, fixed or passing: evidence first.OtherNo warnings★ 88↓ —Also in 1 other repo
sharpen
joetawil7/first-pass
OtherUpdated Oct 17, 2026
From the author
Rewrites the prompt typed after the command before any work starts, then works from the rewrite. Splits a mixed-up message into a numbered list of asks, turns words like "be 100% sure", "cover all cases" or "don't break anything" into the checks they stand for, keeps every name, path, number and quote exactly, and stops to ask only where it would have to guess. Runs only when the user types it.
Install
npx skills add joetawil7/first-pass --skill sharpen -a claude-code
Installs to .claude/skills/sharpen/ · 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
Provenance65
Maintenance100
Licence100
Adoption35
Files (1)
- SKILL.md