Browse the full skills directory.浏览完整技能目录。
Filter by query, category, scenario, platform, and risk signals with server-side catalog results.按关键词、品类、场景、平台和风险信号筛选；URL 参数会直接下推到目录 API。
28 results
GStack Review
Find the risky changes before the branch lands.
Anthropic Skill Creator
Create, test, and improve skills in an eval loop.
QA Loop
Open the product, try the flow, fix what breaks, repeat.
Git Shiproom
Pre-flight every branch before you ask for review.
GStack QA
Open the app, test the flow, fix what breaks.
GStack Investigate
No fixes until the root cause is real.
Incident Investigate
No fixes until the cause is real.
Review Radar
Find the bugs, regressions, and missing tests first.
Nuwa Skill
Distill how a person thinks into a reusable skill.
Anthropic Doc Coauthoring
Guide a doc from raw context to reader-tested clarity.
Docs Release
Sync the docs after the code changes, not three weeks later.
Canary Watch
Verify the live deploy before users tell you it is broken.
DX Audit
Measure the onboarding pain your docs politely hide.
ckm:design
ckm:design: agent skill — from nextlevelbuilder/ui-ux-pro-max-skill.
ckm:banner design
ckm:banner design: agent skill — from nextlevelbuilder/ui-ux-pro-max-skill.
ckm:brand
ckm:brand: agent skill — from nextlevelbuilder/ui-ux-pro-max-skill.
algorithmic art
algorithmic art: agent skill — from anthropics/skills.
cli creator
cli creator: agent skill — from openai/skills.
mcp builder
mcp builder: agent skill — from anthropics/skills.
mcp server builder
mcp server builder: agent skill — from alirezarezvani/claude-skills.
xlsx
xlsx: agent skill — from anthropics/skills.
customer research
customer research: agent skill — from coreyhaines31/marketingskills.
graphify
graphify: agent skill — from safishamsi/graphify.
aso audit
aso audit: agent skill — from coreyhaines31/marketingskills.
ad creative
ad creative: agent skill — from coreyhaines31/marketingskills.
api-security-testing
API安全测试的专业技能和方法论
aig-scanner
A.I.G Scanner — AI security scanning for infrastructure, AI tools / skills, AI Agents, and LLM jailbreak evaluation via
wooyun-legacy
WooYun business logic vulnerability methodology — 22,132 real cases across 6 domains (authentication bypass, authorizati