mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
CLI-agnostic Ralph autonomous development loop with token tracking, context rotation, gutter detection, and Spec Kit support. Drives either the Claude Code or cursor-agent CLI from a terminal-run shell loop.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin ralph-wiggum-plugin in lockstride/ralph-wiggum-plugin. Commands read from the repo's manifest — yesterday.
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.
addressing-acceptance-gapsCloses gaps that the verifying-acceptance-criteria skill recorded in the acceptance report. Use when invoked by the running-acceptance-evaluation orchestrator's REWORK mode after the verifier has logged unmet requirements. Reads the report's Gaps section as a work list, makes the code/test changes n
eval-ralphDeeply evaluate the performance of a Ralph Wiggum autonomous loop run from its on-disk logs. Use when the user wants to analyze, review, grade, or post-mortem a Ralph loop / Ralph session / ralph-wiggum-plugin run — typically phrased as "evaluate loop <fragment>", "how did loop 152651 do", "analyze
ralph-plugin-speckit-updateUpdates the ralph-wiggum-plugin's own Spec Kit integration when a new Spec Kit version is released. Use when Spec Kit releases a new tagged version and the plugin's internal files need to be brought in sync — covers the adaptation guide, prompt-resolver, fallback prompt template, docs, and any skill
ralph-plugin-updateImplements a change to the ralph-wiggum-plugin end to end — plugin code, bats tests, version bump, Conventional Commit, push, tag and GitHub release, then a local install refresh via `ralph --update`. Use when the user wants changes applied to the ralph-wiggum-plugin repo — "update ralph", "implemen
running-acceptance-evaluationOrchestrates the post-completion acceptance evaluation loop for a finished Ralph run. Use when invoked by the eval-loop framing prompt (ralph-evaluate.sh writes a tiny framing prompt that points here). Picks one of two modes per loop based on the current state of `.ralph/acceptance-report.md` — VERI
verifying-acceptance-criteriaIndependently verifies a completed Ralph run against its original ground-truth requirements (PROMPT.md / spec tasks.md / custom prompt). Use when invoked by the running-acceptance-evaluation orchestrator's VERIFIER mode, or when the operator explicitly requests an independent acceptance check. Re-de
/ralph-wiggum-plugin:ralph-cancelClean up Ralph state files (.ralph/.loop and .ralph/effective-prompt.md)
/ralph-wiggum-plugin:ralph-evaluatePrint the terminal command to launch Ralph's acceptance evaluation loop
/ralph-wiggum-plugin:ralph-onceRun exactly one Ralph loop in a terminal (smoke test your prompt)
/ralph-wiggum-plugin:ralph-plugin-speckit-updateUpdate the ralph-wiggum-plugin's internal Spec Kit integration files when a new Spec Kit version is released.
/ralph-wiggum-plugin:ralphPrint the terminal command to launch the Ralph autonomous loop
bash "${CLAUDE_PLUGIN_ROOT}/shared-scripts/ralph-guard.sh"
bash "${CLAUDE_PLUGIN_ROOT}/shared-scripts/ralph-guard.sh"
bash "${CLAUDE_PLUGIN_ROOT}/shared-scripts/handoff-check.sh"
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · 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
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents
7 skills · 7 commands · 2 agents · hooks
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.