Skills / Category
Agent building
3,343 skills
Showing 169–192 of 3,343
- 0.754score
quota-tracker
sonichi
Track Claude Code quota usage via Anthropic API rate limit headers.
SkillAFreshness: A★ 400Claude Code +9 - 0.754score
self-diagnose
sonichi
Sutando introspection — read logs + git + memory + build log for a chosen time window and produce a concise narrative of what the agent has been doing, what's…
SkillAFreshness: A★ 400Claude Code +9 - 0.754score
gemini-deep-researcher
duotify
Use this skill when a user wants a comprehensive research report on any topic with cited sources.
SkillBFreshness: B★ 254Claude Code +9 - 0.754score
skills-governance
cnfjlhj
Use when auditing a large local skill collection, identifying duplicate or imported skills, comparing skill roots, or deciding what to keep, disable, or…
SkillBFreshness: B★ 456Claude Code +9 - 0.753score
process-hygiene
sonichi
Report, and with --reap stop, orphaned processes that interrupted agent test runs left behind in per-session scratchpads (PPID 1, this user, older than 2 h by…
SkillAFreshness: A★ 400Claude Code +9 - 0.752score
gpt-image-2-prompt-engine
anbeime
面向电商设计师、海报美工、品牌视觉、UI设计师、信息图编辑、商业摄影师、内容创作者等需要高质量可控出图的角色,在需要用 GPT-Image-2 生成电商主图、电影海报、信息图、品牌视觉、UI截图、古籍国风、角色IP等场景时,通过「Prompt as…
SkillBFreshness: B★ 8.6KClaude Code +9 - 0.752score
grok-cli
scarletkc
Delegate bounded tasks to Grok Build from a supervising agent such as Codex.
SkillBFreshness: B★ 225Claude Code +9 - 0.750score
git-guardrails-claude-code
mattpocock
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.
SkillAFreshness: A★ 302.4KClaude Code +9 - 0.749score
subagent-driven-development
obra
Use when executing implementation plans with independent tasks in the current session
SkillAFreshness: A★ 304.6KClaude Code +9 - 0.748score
antigravity-cli
scarletkc
Delegate bounded investigation, review, or implementation tasks to Antigravity CLI from a supervising agent.
SkillBFreshness: B★ 225Claude Code +9 - 0.748score
bmad-tea-evaluate
bmad-code-org
Run scored behavioral evaluations and repair gaps.
SkillAFreshness: A★ 110Claude Code +9 - 0.748score
autodesign-video
Yaxin9Luo
Create a narrated, subtitled, source-grounded conference video from a research paper.
SkillBFreshness: B★ 253Claude Code +9 - 0.748score
autodesign-webpage
Yaxin9Luo
Use when turning a paper, preprint, or manuscript into a responsive research project webpage, especially when the page must remain source-grounded, editable…
SkillBFreshness: B★ 253Claude Code +9 - 0.748score
collaboration-intelligence
sonichi
Maintain and use a cross-channel collaboration map of rooms, people, agents, agent owners, relationships, expertise, ownership, roster, priority/VIP handling…
SkillAFreshness: A★ 400Claude Code +9 - 0.745score
ethos-write
NVIDIA
Writes an AI agent's ethos.md — a durable snapshot of its purpose, intended behavior, boundaries, and success criteria — from the answers gathered by…
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.745score
wizard
mattpocock
Generate an interactive bash wizard that walks a human through steps only they can perform.
SkillAFreshness: A★ 302.4KClaude Code +9 - 0.743score
antinet-provenance
anbeime
软件开发工程师与信息安全分析师在构建多智能体系统时,当需全链路可观测与安全审计,请用此技能。它自动收集操作日志,生成可追溯证据链与向量索引,开箱即用实现系统审计与精准回放,让Agent运行安全透明。
SkillBFreshness: B★ 8.6KClaude Code +9 - 0.743score
web-design-analyzer
anbeime
网页与数字界面设计师和网页开发工程师在需要逆向分析网页截图时,使用本技能一键提取配色、排版及组件特征,自动生成结构化 Design System 数据与 AI Coding Prompt,让设计还原与前端开发更高效。
SkillBFreshness: B★ 8.6KClaude Code +9 - 0.741score
complexa-evaluate-pdbs
NVIDIA
Agent runbook for evaluating an existing PDB directory through the separately installed first-party Proteina-Complexa CLI.
SkillAFreshness: A★ 3.7KClaude Code +9 - 0.740score
hyperframes-scene-animator
bozhouDev
接管 talking-head-hyperframes 的 READY_FOR_EXECUTION 交接,由主 Agent 完成字幕分镜与具体导演,先交付全镜头最终静态页审核,批准后再用快速子 Agent 协助实现互不冲突的镜头与动效,最后完成 HyperFrames proof、四遍审查与…
SkillBFreshness: B★ 153Claude Code +9 - 0.740score
viral-video-benchmark
bozhouDev
判断、扫描、拆解并归档抖音视频、小红书图文或小红书视频。实时读取用户同平台粉丝数并划分主对标池/跨级灵感池,用已登录浏览器读取目标作品和作者主页公开指标,再用确定性代码判定普通、小爆、爆款、现象级并扫描作者近 20 条候选;只对用户选中的爆款和现象级先构建可追溯证据包,再调用子 Agent…
SkillBFreshness: B★ 153Claude Code +9 - 0.740score
skill-to-document
aws-jp-fsi-saOfficial
Convert an Agent Skill into a formatted document (PDF, DOCX, or HTML).
SkillAFreshness: A★ 15Claude Code +9 - 0.740score
open-tag-admin
zilliztech
Admin/control console for an Open Tag Slack tag-in workflow backed by MFS.
SkillBFreshness: B★ 157Claude Code +9 - 0.739score
agent-plugin-eval
fabricioctelles
Audit, score, and compare repositories containing portable Agent Plugins against the official Agent Plugins specification.
SkillBFreshness: B★ 119Claude Code +9