setup-matt-pocock-skills

An agent skill by mattpocock, from mattpocock/skills. Tags: catalog, configuration, setup, triage, workflow.

What it does

Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add mattpocock/skills --skill setup-matt-pocock-skills

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/mattpocock/skills
cp -r skills/skills/engineering/setup-matt-pocock-skills ~/.claude/skills/setup-matt-pocock-skills

Safety box score

Grade B, low risk: 21 of 100 risk points, rated 2026-10-21. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is mostly a repo setup and documentation pass, but it can also talk to GitHub/GitLab and mutate the remote tracker by creating labels. The main risks are bounded file writes in the repo and networked account changes on whatever issue tracker the repo uses.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It invokes shell/CLI commands such as `git remote -v`, `gh label create`, and `glab label create`, but it does not ship or evaluate arbitrary code.
Network access	2 (moderate)	It reaches out to GitHub/GitLab through `gh`/`glab` and can create labels on the remote tracker, so data leaves the machine.
Filesystem reach	1 (low)	Writes are confined to the repo, mainly `CLAUDE.md` or `AGENTS.md` and `docs/agents/*.md`, with in-place updates to an existing `## Agent skills` block.
Secrets & credentials	0 (none)	It does not ask for passwords, tokens, browser sessions, or key files; it only inspects repo metadata like `.git/config`.
Privilege & persistence	0 (none)	No sudo, global installs, services, scheduled tasks, or shell/OS settings are involved.
Instruction hijack surface	0 (none)	The skill tells the agent to confirm with the user and does not ask it to ignore instructions, fetch remote prompts, or hide anything.
Irreversible actions	2 (moderate)	It can make remote workflow changes by creating missing tracker labels after setup, which is an external state change even though the path is user-confirmed.
Transparency	0 (none)	All shipped files are plain Markdown/YAML; there are no binaries, decoded-at-runtime payloads, or unpinned installer commands.

Before installing

Check whether this repo already has `CLAUDE.md` or `AGENTS.md`, since the skill will only edit one of them.
Confirm whether the optional `triage` skill is installed, because that changes whether labels get created.
Run `gh auth status` or `glab auth status` in the intended account first so remote writes use the right identity.
Skim the `docs/agents/*.md` templates and make sure you want the chosen issue tracker and the default PR/MR triage flag left off.

Rated 2026-10-21 by an automated review of 7 files from the skill's repository.

Source

Repository: mattpocock/skills (all skills from this repository)
Path: skills/engineering/setup-matt-pocock-skills/SKILL.md
Branch: main
Updated: 2026-10-05

setup-benny — Configure Benny and prepare its triage and repro automations.
setup-pstack — Configure which models pstack uses per role and at what reasoning budget.
wizard — Generate an interactive bash wizard that walks a human through steps only they can perform.
setup-deploy — Configure deployment settings for /land-and-deploy.
skill-governance — Govern the real Claude Code and Codex Skill surface without losing cold capability.
create-plugin-scaffold — Create a new Cursor plugin scaffold with a valid manifest, component directories, and marketplace wiring.