mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
mattpocock/skills 323,108
claude
toolbelt
Tools for Claude Code you can carry into any repo: audit code, run experiments, write up findings, review and sweep PRs, and dig into a question.
/
Plugin toolbelt from marketplace toolbelt in Seuketchi/toolbelt. Commands read from the repo's manifest — 26 days ago.
What it installs
Skills (7)
code-auditAudit how our own code or system behaves today, citing file:line for every claim. Use when a decision waits on what the existing code actually does, not what anyone remembers.
experimentSettle a question by measuring it: run the build, call the API, drive the device, and record the data with its setup. Use when reading can't answer it: real latency, real API responses, behaviour on a real phone or board.
findingsThe findings format every investigation writes to: research, audit, reverse-engineering, experiment. Use when writing one up, or reading one into a spec.
lean-pr-reviewInstall a lean Claude PR review in a repo — a GitHub workflow that scopes each run before calling Claude, posts comment-only findings on changed lines, and re-checks its own open threads on later pushes.
pr-sweepDrive every open PR and issue in the current repo to merged or closed, in a safe order, with the user deciding each merge and close.
rabbit-holeFollow your curiosity down a rabbit hole, one cited step at a time, steering as you go.
recallSearch your past Claude Code sessions for how something was done or decided.
Similar plugins
agents-md
claudeAGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.
anthropics/claude-code 155,476
agent-skills
claudecodexProduction-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.
25 skills · 4 agents
addyosmani/agent-skills 116,782
agentic-qe-fleet
claudeAgentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
ruvnet/ruflo 81,589
Install the "AAS Security Engineer" workflow plugin from Agentic Awesome Skills.
12 skills
sickn33/agentic-awesome-skills 49,620
reverse-engineering
claudecodexBinary reverse engineering, malware analysis, firmware security, and software protection research for authorized security research, CTF competitions, and defensive security
4 skills · 3 agents
wshobson/agents 42,461
Maintain toolbelt?
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.
claude & codex pluginslisted