Security

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or…

Vendor-neutral skill to audit image alt-text coverage and basic quality heuristics for accessibility.

Passive, headless recon of a web app's frontend to infer its backend and tech stack - API endpoints, third-party vendors, CSP allow-lists, auth provider…

Unit-level security judgment of a repository, a folder of repositories, or the units a pull request changed, with TypeSafe's Jev: code splits every source…

Measure always-on context (settings, MCP, skills, CLAUDE.md, AGENTS.md, memory) and prune it with approval.

Design audit checklist - motion gaps, accessibility, color consistency, responsive, performance.

顽皮制造 — Fuse multiple external skill repos/sources into an existing skill to create a unified, more capable version.

Core extraction + vocabulary for the @llodev/pm-tasks-* family.

Audit and enforce the AGENTS.md "Scripts" guidelines for helper scripts in this repo - banning Python, preferring Node.js `.mjs` modules or zsh, requiring…

產生一個互動式 bash wizard，引導人類走過只有他們能做的步驟。用於佈建基礎設施、設定憑證或 CI secrets、走訪陌生的第三方儀表板，或執行一次性遷移或切換。不要為代理自己能做的步驟叫用它。

Concatenate many files in a directory into a single markdown document when the user asks to read, analyze, scan, load, dump, audit, concatenate, or merge many…

Start a persistent Claude Code Remote Control session on the GPU host (Command Center) for phone/laptop monitoring of container agents.

Author beautiful, hand-drawn-style Excalidraw diagrams and export them to PNG/SVG headlessly.

Enforces 100% template fidelity for GitHub markdown files (README.md, ARCHITECTURE.md, CONTRIBUTING.md, CODE_OF_CONDUCT.md, SECURITY.md, PRIVACY.md…

Owns the decision trail for long, risky, or unattended work: one row per decision in a TSV, evidence as a pointer, append-only.

全面分析 Office 文档安全性 (.doc/.docx/.docm/.xls/.xlsx/.xlsm/.ppt/.pptx/.pptm/.rtf/.wps/.one/.xll)。当用户要求"分析 Office 文档"、"检测宏病毒"、"VBA 分析"、"OLE…

Converge a GitHub repository's settings — merge hygiene, a guardrail ruleset on the default branch, Dependabot and secret scanning.

Create, edit, improve, tidy, review, audit, or restructure AgentSkills and SKILL.md files.

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any…

Critically review code/plans via adversarial expert subagent to find bugs, edge cases, security holes, and architectural flaws before merge.

Execute a full La Posta Cine bug and editorial repair pass on a fresh fix branch.

Find one publishable La Posta Cine release from the last seven days and hand it to the movie-load workflow.

Use to audit R/C helper sprawl, redundant checks, complexity, or host-unsafe assertions with Tree-sitter.

Comprehensive security audit, hardening, and automated penetration testing suite.