Skills for Real Engineers. Straight from my .agents directory.
yao-websecurity-skill
Agent skill fromyaojingang/yao-open-skills
Use when auditing an authorized website, SaaS, API, AI app, local code path, GitHub repo, staging URL, or owned runtime for security risks, vulnerability checklist scoring, static review, dynamic review, active validation, or Chinese security reports.
How to install yao-websecurity-skill
npx skills add yaojingang/yao-open-skills# or add only this skill to Claude Code: copy the folder
skills/yao-websecurity-skill/
# into
~/.claude/skills/yao-websecurity-skill/ (all projects)
.claude/skills/yao-websecurity-skill/ (one project)
1# Yao Websecurity Skill23## Use45Use when the user gives a local path, archive, GitHub repo, staging URL, or owned runtime and wants a defensive website security audit, vulnerability checklist review, scorecard, remediation plan, static review, dynamic review, active validation, or Excel/HTML/Markdown/PDF report.67Do not use for unauthorized targets, exploit development, credential theft, stealth, malware, third-party public-target scanning, or bypass instructions.89## Required Reading1011- `references/security-audit-method.md`12- `references/report-contract.md`13- `references/review-modes.md`14- `references/vulnerability-ontology.csv`15- `references/scanner-registry.md`1617## Workflow18191. Confirm mode, scope, authorization, environment, intensity, forbidden actions, test accounts, rate limits, rollback/reset plan, and whether online targets are allowed. Without active-test authorization, use `static`.202. Prepare an isolated workdir before review: `python3 scripts/security_audit_report.py prepare-env --source "<path-or-url>" --workdir "<fresh-temp-workdir>" --project "<name>" --mode "<mode>"`. Local and GitHub targets must be copied or cloned into this fresh temp directory; never install, build, migrate, write reports, or mutate the original source tree.21…
Excerpt shown under the repository's MIT license.
More skills in yao-open-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
