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.
46,692 skills from 2,243 repositories · updated 33 minutes ago
9,997 skills
- papercut-voice0xS4N4TG/papercut-explainerVoice a papercut reel and time it to the picture. Three paths, local Qwen3-TTS, your own recording or another TTS, or a placeholder voice. Covers delivery rules, voice.json, captions and scene timing. Use for "set up the voice", "re-voice this", "time the script".OtherNo warnings★ 89↓ —
- environment-triageparcadei/Continuous-Claude-v3Environment TriageOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- compound-learningsparcadei/Continuous-Claude-v3Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".OtherNo warnings★ 3.9K↓ —Also in 1 other repo
- categories-functorsparcadei/Continuous-Claude-v3Problem-solving strategies for categories functors in category theoryOtherNo warnings★ 3.9K↓ —
- template-usageharness/harness-skillsTrack Harness template dependencies, usage, and adoption via MCP v2 tools. Find which pipelines or other templates reference a given template, analyze update impact, identify unused templates, and compare version adoption. Use when asked about template usage, template references, template dependencies, impact analysis before updating a template, finding unused templates, or tracking template adoption across projects. Trigger phrases: template usage, who uses template, template references, template dependencies, template impact, unused templates, template adoption. Do NOT use for creating or updating templates (use create-template instead).OtherNo warnings★ 125↓ —
- skill-upgraderparcadei/Continuous-Claude-v3Upgrade any skill to v5 Hybrid format using decision theory + modal logicOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- create-handoffparcadei/Continuous-Claude-v3Create handoff document for transferring work to another sessionOtherNo warnings★ 3.9K↓ —
- indie-horror-aestheticsarjun988/blender-skillsIndie horror aesthetic pack for Blender covering Silent Hill, Fear to Fathom, Puppet Combo, corporate horror, cabin/forest/hospital horror, and related looks.OtherNo warnings★ 1.1K↓ —Also in 1 other repo
- lightingarjun988/blender-skillsCinematic and game lighting in Blender including three-point lighting, HDRI, horror lighting, volumetrics, rim lighting, and mood-driven illumination. Use for look development and scene atmosphere via MCP.OtherNo warnings★ 1.1K↓ —Also in 1 other repo
- operator-theoryparcadei/Continuous-Claude-v3Problem-solving strategies for operator theory in functional analysisOtherNo warnings★ 3.9K↓ —
- pm-changekonglong87/superPMUse when: 项目进行中出现需求变更、需要评估变更影响范围和风险、记录变更历史 Do NOT use when: 变更极小无需正式评估、变更已有明确决策无需分析OtherNo warnings★ 84↓ —
- mcp-scriptsparcadei/Continuous-Claude-v3MCP Script RulesOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- skill-syncjdrhyne/agent-skillsSync skills between local installation and the GitHub source-of-truth repository. Use when asked to install, update, list, or push skills.OtherNo warnings★ 240↓ —
- describe-prparcadei/Continuous-Claude-v3Generate comprehensive PR descriptions following repository templatesOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- genre-metroidvania-roguelikearjun988/blender-skillsArt direction for metroidvania, roguelike, and roguelite games in Blender with biome gates, room modules, and run-readable props.OtherNo warnings★ 1.1K↓ —Also in 1 other repo
- genre-open-world-sandboxarjun988/blender-skillsArt direction for open world and sandbox games in Blender with biome landmarks, traversable scale, and discovery props.OtherNo warnings★ 1.1K↓ —Also in 1 other repo
- update-flag-targetingharness/harness-skillsChange how a Harness FME feature flag serves traffic in environments. Covers percentage rollout, individual targets, targeting rules (attribute/segment/flag-dependency), defaultTreatment, trafficAllocation, treatments, kill/restore, and copying or initializing a definition in an environment. Use when asked to ramp a flag, add rules/users, change allocation, kill/restore, or promote config. Not for creating flags (create-feature-flag), metadata like tags/owners/archive (manage-flag-lifecycle), segment keys (manage-segments), pipeline rollouts (fme-pipeline), or flag analysis (explain-flag). Trigger phrases: update targeting, ramp flag, percentage rollout, add rule, add users, kill flag, restore, copy config.OtherNo warnings★ 125↓ —
- tldr-statsparcadei/Continuous-Claude-v3Show full session token usage, costs, TLDR savings, and hook activityOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- 会记成报YiShu5/claude-skills将会议转写稿、会议笔记或聊天记录整理为可核对的会议纪要、用户本人的日报和周报素材卡,并可把本周多份已确认日报按事项合并去重生成周报。适用于:会议结束后需要沉淀纪要、待办(负责人、截止时间、完成状态);需要从会议中提取个人日报;周五需要把多份已确认日报合并生成周报素材;用户要求整理会议纪要、提取日报、合并周报、复盘会议待办时使用。核心原则:区分讨论/建议/决定,不编造未确认事实,关键信息缺失时一次只追问一个问题,所有输出先经用户核对。OtherNo warnings★ 131↓ —
- graph-algorithmsparcadei/Continuous-Claude-v3Problem-solving strategies for graph algorithms in graph number theoryOtherNo warnings★ 3.9K↓ —
- fantasy-worldsarjun988/blender-skillsFantasy world-building art direction for Blender covering medieval, high fantasy, dark fantasy, and urban fantasy asset language.OtherNo warnings★ 1.1K↓ —Also in 1 other repo
- genre-stealtharjun988/blender-skillsArt direction for stealth-game spaces in Blender with shadow volumes, patrol-friendly layouts, and concealment materials.OtherNo warnings★ 1.1K↓ —Also in 1 other repo
- hooksparcadei/Continuous-Claude-v3Hook Development RulesOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- cloth-simarjun988/blender-skillsGarment blockout, cloth simulation, pin groups, and bake to shape keys or caches for characters and props in Blender via MCP.OtherNo warnings★ 1.1K↓ —Also in 1 other repo
bounty-recon
26zl/cybersec-toolkit
From the author
Use at the start of a bug bounty engagement. Provides scope-aware recon methodology — passive enumeration, subdomain discovery, asset attribution, tech stack fingerprinting, content discovery. Respects scope and program rules. Triggers on "bounty recon", "subdomain enum", "attack surface map", "h1 recon", "bug bounty start".
Install
npx skills add 26zl/cybersec-toolkit --skill bounty-recon -a claude-code
Installs to .claude/skills/bounty-recon/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Safety checks on SKILL.md
No warnings.
Why 83
Files (1)
- SKILL.md