mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Correct tool calls are not enough: audit MCP servers (lint, scorecard, effect probes), turn agent traces into tool-call tests, check that an agent told the truth about what its tools did, and pin MCP servers against drift in CI.
Plugin toolscore from marketplace toolscore in yotambraun/Toolscore. Commands read from the repo's manifest — 5 days ago.
add-tool-call-testsAdd deterministic tool-call regression tests for an LLM agent with Toolscore - capture what the agent really calls (an MCP session recording, a provider response, a framework run result or a trace file), write a contract of required, optional and forbidden calls, and add a pytest test that fails whe
audit-mcp-serverAudit an MCP server with Toolscore - lint its tool definitions, run the A-F scorecard, run effect probes that check its tools really did what they reported, and explain each finding with a concrete fix. Use when someone wants to test, grade, review, harden or debug an MCP server (local stdio command
check-agent-honestyCheck with Toolscore whether an AI agent told the truth about what its tools did - claimed success after a failed call, ended right after an error, kept a tool warning to itself, or used a code-execution tool to override a refusal (for example force-enabling a disabled button) - from a trace, a reco
pin-mcp-serversPin the tool definitions of MCP servers with Toolscore (toolscore.lock.json with a hash of every tool, the server, protocol and instructions, and a read/write/delete/network/exec capability manifest) and verify the pin in CI, so a changed tool description, a new tool or a new delete or exec capabili
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
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · 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
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.