Testing

Module Loop and Iteration Skill for orchestrating multi-phase penetration testing workflows.

Browser automation CLI for AI agents.

Audit projects, containers, sudoers/IaC, and shell-out call sites for dangerous Living-Off-the-Land binary exposure using GTFOBins data.

Check documentation against code.

Give your AI agent a professional health checkup (AgentVitals).

Routes requests to the BMad Method (v6.12.4) agile framework: persona agents, planning skills (brief, PRFAQ, PRD, UX, spec, architecture, epics, sprint…

Drive a Claude Code session toward a verifiable goal until done or a hard cap fires - autonomous loop, no user intervention.

Manage named persistent browser profiles (cookies, localStorage, IndexedDB, cache) that both you and Claude can use against the SAME Chrome window without…

Stealth Firefox browser server for agent-driven Google OAuth and bot-protected sites.

Use this skill whenever you work on giclaw's self-iteration ("loop evolution") system, or whenever a giclaw skill needs to be diagnosed and fixed.

The house tech stack for a new web project on Cloudflare — framework, lint, test, CI, docs, and repo conventions, with copy-ready config templates.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Implement a backlog item (Issue / Sub-Epic / Epic) created by /architect:export-backlog in the project's real source tree, test-first, consistent with its…

Evaluate C ref-model decoder against JVET/JCTVC conformance bitstreams (bitexact/MD5) — 'decoder conformance'; C-level, not RTL (rtl-conformance-test).

Final codec standards compliance gate: bitexact RTL bitstream check against JM/HM reference.

Generate a demo of a feature developed in this session, in a web app, in a Chromium-based desktop app (Electron), or in a native mobile app on an iOS…

Find blog posts semantically similar to a topic — pulls from the posts embedding source.

Show content quality scores and QA results for tasks that have cleared the pipeline.

qa-skills shared knowledge base — dependency, NOT triggerable: executability standards, evidence grading, risk model, type matrix, templates, scripts.

Drive the teeth-gated lifecycle for reported defects: diagnose root cause, prove it, and prevent regression through REPORTED → DIAGNOSING → ROOT_CAUSED →…

Run a static-analysis pass on a project — detect the ecosystem (Python or Node), drive its linter (ruff / eslint, plus advisory pyright/complexity/ prettier…

Drive the red-green-refactor loop for any non-trivial code change.

Prove that every acceptance criterion (AC-<n>) in a plan.md has at least one passing test and that no test mapped to a criterion failed, by reading JUnit XML…

Build evaluation frameworks for agent systems.