mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Satori's full development workflow as peer skills: xp-pair, handoff, continue, pre-pr-audit, address-pr-issues, adversarial-review, reasoning-audit
Plugin satori from marketplace satoris-claude-config in fransonsr/satoris-claude-config. Commands read from the repo's manifest — 3 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
address-pr-issuesSystematically address GitHub Copilot and SonarQube issues on pull requests with comprehensive tests. Reads PR comments, prioritizes issues, implements fixes, and resolves conversations.
adversarial-reviewMulti-round parallel adversarial pattern review against copilot-review-patterns.md. One agent per pattern class, cascade-sweep within each class, human review-pause between rounds, git-guardrailed fixes. Invoked by /pre-pr-audit (3 rounds) and /address-pr-issues (1 round), or standalone. Use before
continueONLY invoke when the user explicitly requests a session checkpoint or says '/handoff:continue'. Builds a self-contained continuation doc to resume after /clear — capturing plan state, agent findings, decisions/pivots, dead ends, and the verbatim next action. Do NOT trigger on conversational use of '
handoffCreate comprehensive handoff documents for tasks to be implemented in a fresh Claude Code session. Includes verified context, explicit unknowns, scope boundaries, and acceptance criteria.
pre-pr-auditProactive code quality audit before creating a pull request - runs a mandatory multi-round adversarial pattern review plus pattern matching and optional SonarQube analysis to identify resource leaks, edge case gaps, test coverage issues, and code quality problems. Automatically fixes issues when pos
reasoning-auditPeriodically re-examine an existing CLAUDE.md, skill, script, or Claude Code auto-memory corpus for reasoning that has gone stale — thresholds with no evidence, capability claims overtaken by reality, citations that no longer resolve, guards that stopped guarding, and scripts being bypassed. Use whe
xp-pairXP pair programming with navigator (design oversight) and driver (implementation). Use for complex features requiring design oversight, TDD coaching, or high-quality code with continuous review.
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/reasoning_audit_cadence.py"
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/mcp_entry_guard.py"
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
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 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.