mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Evidence-backed, read-only code audits (Full Scan), cited answers to code questions (Quick Ask), and guided fixes — AI Theresa Waggle inside Claude Code.
Plugin theresa-waggle from marketplace ai-theresa in ai-theresa-lab/ai-theresa-waggle-skill. Commands read from the repo's manifest — 25 days ago.
askAnswer one concrete question about a codebase with AI Theresa Waggle's Quick Ask: a read-only Claude agent investigates the selected repository or folder and answers with cited file and line evidence. Use when the user wants an evidence-backed answer about how existing code behaves (e.g. 'where is m
fixWork through an AI Theresa Waggle REMEDIATION.md: re-verify each finding against the current code, fix the confirmed ones on a new branch one commit per finding, and run the tests — with the user's approval at each step. Use after a Waggle Full Scan when the user asks to fix its findings.
reportShow the status or results of AI Theresa Waggle runs (Full Scans and Quick Asks): list recent runs, check a running scan's progress, or summarize a finished run's findings and where its reports are. Use when the user asks how a Waggle scan is going, what a previous Waggle run found, or where its rep
scanRun an AI Theresa Waggle Full Scan: a team of read-only Claude agents audits a codebase (security, architecture, release engineering, business logic and more), verifies every claim against the code, and returns an evidence-backed Leadership brief, an Execution report and a REMEDIATION.md. Usually ta
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.