ask-matt

An agent skill by mattpocock, from mattpocock/skills. Tags: catalog, multi-agent, routing, workflow.

What it does

Ask which skill or flow fits your situation. A router over the skills in this repo.

Install

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

npx skills add mattpocock/skills --skill ask-matt

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/ask-matt ~/.claude/skills/ask-matt

Safety box score

Grade A, minimal risk: 9 of 100 risk points, rated 2026-10-16. 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.

Ask-matt is a pure router for a larger workflow map: it helps choose which skill to use and points you at the relevant docs. It does not itself run commands, touch secrets, or modify files; the main risk is indirect, because it can steer the agent into downstream skills that do those things.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No scripts, shell commands, or code evaluation appear in this skill; it only names other workflows and documents.
Network access	0 (none)	There is no downloading, uploading, or remote API use in the skill itself; the only URLs are informational references.
Filesystem reach	1 (low)	The router is built around repo-local artifacts like `PHASE-BOUNDARIES.md`, `GLOSSARY.md`, ADRs, and `.scratch/<feature>/issues/`, but this file does not itself write or delete them.
Secrets & credentials	0 (none)	It does not request tokens, keys, `.env` contents, browser sessions, or any other secret material.
Privilege & persistence	0 (none)	No sudo, service registration, global installs, or shell/OS setting changes are present in this skill.
Instruction hijack surface	1 (low)	It contains strong workflow directives such as 'Before stating what a skill does... read that skill's SKILL.md' and 'don't compact until after `/to-tickets`', but nothing that hides instructions or tells the agent to ignore safeguards.
Irreversible actions	0 (none)	This skill only recommends a path; it does not itself deploy, post, merge, pay, book, or delete anything.
Transparency	0 (none)	All files are plain text and readable; there are no binaries, embedded blobs, or runtime-generated code paths.

Before installing

Read `PHASE-BOUNDARIES.md` and the downstream skills this router points to before relying on its workflow advice.
Verify whether `/setup-matt-pocock-skills` has already been run in your workspace if you plan to use the broader skill tree.
Inspect any downstream skill you actually intend to invoke, especially `/wizard` and `/pr`, because that is where the real side effects live.

Rated 2026-10-16 by an automated review of 3 files from the skill's repository.

Source

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

continual-learning — Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.
orchestrate — Use only when the user explicitly types `/orchestrate <goal>` to decompose a large task.
principle-guard-the-context-window — Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning.
ralph-loop — Start a Ralph Loop for iterative self-referential development.
swarm — Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
claude-handoff — Hand the current conversation off to a fresh background agent that picks up the work immediately.