mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Disciplined AI Research Assistant for economists: plan-implement-integrate workflow with implementer–reviewer pair, data-analysis discipline, and drift-test-verified integration.
Plugin superRA from marketplace superRA in FuZhiyu/superRA. Commands read from the repo's manifest — 2 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.
academic-writingAcademic prose support. Use for reviewing, polishing, proofreading, consistency checks, citation checks, or drafting manuscript text in LaTeX, Markdown, Quarto, or plain text.
agent-orchestrationCoordinate superRA agents and handoffs. Requires superRA:using-superra. Use to dispatch roles, run parallel agents, choose reviewers, or preserve workflow state.
communicateCommunication discipline for writing, rewriting, distilling, and reviewing any text meant for human reading, including conversation, task files, planning updates, results, reports, reviews, handoffs, documentation, and interactive HTML pages. Use for every message or artifact a human will read; Must
econ-data-analysisEconomic data-analysis discipline. Use for importing, cleaning, merging, filtering, variables, aggregation, summary stats, regressions, or figures on economic, financial, or panel data.
handoff-docDEPRECATED. Redirects to task-tree and the role skills.
implement-taskImplementer role protocol for a superRA task — execute the objective, self-check, write results into the task file, commit, and return status. Load when a dispatch assigns you an implementer seat or when you fill one yourself.
mistral-pdf-to-markdownConvert PDFs to Markdown with Mistral OCR and extracted images. Use for scanned PDFs or complex layouts where structured text or images matter.
onboardingBring an existing research project into superRA — a retroactive task tree, a reproduction graph, version control, and an optional isolated reproduction run — while teaching a researcher new to superRA each concept. Use whenever a project has code, data, or results but no superRA/ task tree, even wit
refactor-and-integrateCodebase integration discipline. Use when refactoring for local conventions, reviewing post-sync quality, auditing project docs, pruning diffs, or using Sync Impact evidence.
reproducibilityRegister and verify task-declared reproduction graphs. Use when planning, producing, changing, recording, or reviewing retained results that depend on executable steps, writing drift tests or validation scripts, adopting reproduction, deciding external inputs at Protect, or judging whether to rerun
result-protectionProtect key research results with permanent documentation, drift tests, or artifact-appropriate checks. Use when selecting protection, creating or reviewing tests, or guarding important outputs through integration.
review-taskReviewer role protocol for a superRA task — a scoped pass at a named tier and focus, reporting evidence-backed blocking and advisory findings into the task file. Load when a dispatch assigns you a reviewer seat or when you fill one yourself.
semantic-mergeSemantic branch integration. Use before git merge, rebase, or cherry-pick, or when syncing branches where conflicts or overlapping intent must be resolved deliberately.
slide-designResearch slide communication. Use when creating, revising, polishing, or reviewing Beamer, PowerPoint, Keynote, or browser slide decks.
superimplementRun a superRA task tree autonomously through dispatched implementer and reviewer seats. Requires superRA:using-superra. Use when the researcher asks for autonomous execution or accepts a recommendation for it, and to resume mixed task statuses or verify code-complete work.
superintegrateIntegrate code-complete superRA work. Requires superRA:using-superra. Use for result protection, base sync, codebase-fit refactors, permanent records, cleanup, or PR preparation.
superplanProactively plan or update superRA work. Requires superRA:using-superra. Use when starting or changing work, creating/revising superRA/, reflecting material decisions in the task tree, or on any request to grill, stress-test, or interrogate a loose idea into decisions.
task-treeOperate on superRA/ task trees. Use to query frontier, DAG, or tree views; create or restructure tasks; edit statuses; serve dashboards; or migrate legacy PLAN.md/RESULTS.md.
theory-modelingMathematical-modeling discipline. Use for assumptions, FOCs, equilibria, proofs, comparative statics, numerical checks, or renderable model notes.
using-superraMaster superRA workflow skill. Use proactively whenever superRA is mentioned or when planning, implementing, integrating, merging, or loading a superRA/ task tree.
worktree-data-syncSync non-git data (datasets, outputs, caches, symlinked data) between git worktrees. Use proactively whenever creating or entering a worktree whose work depends on non-git-tracked data — seed the data in before dispatching or doing work there — and to seed, diff, reconcile, or tear down managed data
zotero-paper-readerUse Zotero to find, read, summarize, cite, or export academic papers. Use for paper lookup, library searches, attachments, BibTeX, and draft citation work.
"${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" autoload-superra
"${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" task-hook
"${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" agent-model-guard
"${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" guard-task-approval
"${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" guard-task-cycles
"${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" ensure-communicate
"${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" merge-guard
"${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" task-hook
"${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" ensure-companion
"${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" task-hook
"${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" exit-plan-mode
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
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
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.