setup-matt-pocock-skills · Skill Details

Mechanism

When It Triggers · How It Works · What It Produces

Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.

Trigger: User-invoked, run once per repo. Required before using other engineering skills. /ask-matt lists it as a precondition.
Mechanism: 4 steps: (1) Explore — check git remote, CLAUDE.md/AGENTS.md, CONTEXT.md, docs/adr/, docs/agents/, .scratch/, monorepo signals; (2) Section-by-section prompting — A. Issue Tracker (recommend GitHub/GitLab/Local/Other), B. Triage labels (only if triage skill is installed), C. Domain docs layout (default single-context); (3) Show draft and let user edit/confirm; (4) Write — edit CLAUDE.md or AGENTS.md, create config files under docs/agents/. Prefers editing existing files, never creating duplicates.
Output: issue-tracker.md (tracker choice and workflow), triage-labels.md (label mapping, only if triage is installed), domain.md (domain doc consumer rules and layout), and updated AGENTS.md/CLAUDE.md. Other engineering skills read these config files for their needed information.

Use Cases

Two Typical Use Cases

Scenario 01

First-time configuration for a new project

A developer installs mattpocock/skills in a new GitHub repo and wants to use engineering skills for the first time. Invoking `/setup-matt-pocock-skills`, the skill explores the project state (git remote, existing CLAUDE.md/AGENTS.md, etc.) and steps through sections. For a GitHub repo, it recommends GitHub Issues as tracker, default triage labels, and single-context layout. The user confirms each step and the skill writes the configuration files.

Scenario 02

Configuring for a non-GitHub project

A team using Linear as their issue tracker wants to use these skills. Invoking `/setup-matt-pocock-skills`, the skill detects a non-GitHub/GitLab remote and offers the "Other" option for Issue Tracker, asking the user to describe the Linear workflow. The skill records this workflow as freeform prose for downstream skills, continuing with defaults for triage labels and domain doc layout.

Skill Relationships

Which Skills I Use · Which Skills Use Me

Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.

Tier 1 · These Skills Use Me

No explicit dependency

Tier 2 · Current Skill

setup-matt-pocock-skillsWorkflow

Tier 3 · I Use These Skills

No explicit dependency on other Skills

Full Relationship Graph

Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.

Skill File

SKILL.md

Open in GitHub ↗

SKILL.mdLoading from GitHub…

Skill Composition

Open in GitHub ↗

SKILL.md14.3%
other85.7%

▸skills/setup-matt-pocock-skills/
▸setup-matt-pocock-skills
- ·SKILL.md
- ▸agents
  - ·openai.yaml
- ·domain.md
- ·issue-tracker-github.md
- ·issue-tracker-gitlab.md
- ·issue-tracker-local.md
- ·triage-labels.md

Per the Agent Skills spec, SKILL.md is the only required file. The colored bars classify the rest into the three spec-aligned optional directories (scripts / references / assets) and an 'other' bucket. The full directory tree is below.

Related in Skillset

You May Also Need These Skills

ask-matt

A router skill for the entire skillset: when the user can't remember which skill to use or which flow fits their situation, they invoke this to get a recommendation. It describes the main "idea → ship" flow (grill-with-docs → to-spec/to-tickets → implement), plus on-ramps (triage, diagnosing-bugs, wayfinder), codebase health (improve-codebase-architecture), vocabulary layers (domain-modeling, codebase-design), and standalone skills (grill-me, prototype, research, teach). Following its map leads users to the correct workflow entry point.

Workflow

code-review

A two-axis code review skill: reviews a diff (from a fixed point to HEAD) along both Standards (coding standards + Fowler smell baseline) and Spec (faithful implementation of the originating issue/PRD). Both axes run as parallel sub-agents to avoid context pollution. The report aggregates findings without merging conclusions, ensuring "passes standards but implements the wrong thing" and "implements the right thing but breaks conventions" are both surfaced independently.

Workflow

codebase-design

A shared vocabulary skill for deep module design: provides a precise set of design terms (Module, Interface, Depth, Seam, Adapter, Leverage, Locality) guiding agents and developers to design "deep modules" — a lot of behaviour behind a small interface. Includes design principles (the deletion test, the interface is the test surface) and testability guidelines. A reference skill consumed by other skills (e.g., improve-codebase-architecture, tdd) and invoked directly by engineers.

Style Guide

diagnosing-bugs

A disciplined diagnosis loop for hard bugs and performance regressions. The core idea is to first build a tight feedback loop — no hypothesis phase without one. Six phases: build feedback loop → reproduce + minimise → generate 3-5 falsifiable hypotheses → instrument by prediction → fix + regression test → cleanup + post-mortem. If the codebase architecture can't lock down the bug, it recommends handing off to the improve-codebase-architecture skill.

Workflow