setup-matt-pocock-skills

Name: setup-matt-pocock-skills
Author: stevesolun

560stars68forks

How to install setup-matt-pocock-skills?

stevesolun/ctx/setup-matt-pocock-skills

$npx -y skills add stevesolun/ctx --skill setup-matt-pocock-skills

Installs into the current project.

Summary

Sets up an ## Agent skills block in AGENTS.md/CLAUDE.md and docs/agents/ so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of to-issues, to-prd, triage, diagnose, `

Files · 1

View on GitHub

SKILL.md

1	# Setup Matt Pocock's Skills
2
3	Scaffold the per-repo configuration that the engineering skills assume:
4
5	- Issue tracker — where issues live (GitHub by default; local markdown is also supported out of the box)
6	- Triage labels — the strings used for the five canonical triage roles
7	- Domain docs — where `CONTEXT.md` and ADRs live, and the consumer rules for reading them
8
9	This is a prompt-driven skill, not a deterministic script. Explore, present what you found, confirm with the user, then write.
10
11	## Process
12
13	### 1. Explore
14
15	Look at the current repo to understand its starting state. Read whatever exists; don't assume:
16
17	- `git remote -v` and `.git/config` — is this a GitHub repo? Which one?
18	- `AGENTS.md` and `CLAUDE.md` at the repo root — does either exist? Is there already an `## Agent skills` section in either?
19	- `CONTEXT.md` and `CONTEXT-MAP.md` at the repo root
20	- `docs/adr/` and any `src/*/docs/adr/` directories
21	- `docs/agents/` — does this skill's prior output already exist?
22	- `.scratch/` — sign that a local-markdown issue tracker convention is already in use
23
24	### 2. Present findings and ask
25
26	Summarise what's present and what's missing. Then walk the user through the three decisions one at a time — present a section, get the user's answer, then move to the next. Don't dump all three at once.
27
28	Assume the user does not know what these terms mean. Each section starts with a short explainer (what it is, why these skills need it, what changes if they pick differently). Then show the choices and the default.
29
30	Section A — Issue tracker.
31
32	> Explainer: The "issue tracker" is where issues live for this repo. Skills like `to-issues`, `triage`, `to-prd`, and `qa` read from and write to it — they need to know whether to call `gh issue create`, write a markdown file under `.scratch/`, or follow some other workflow you describe. Pick the place you actually track work for this repo.
33
34	Default posture: these skills were designed for GitHub. If a `git remote` points at GitHub, propose that. If a `git remote` points at GitLab (`gitlab.com` or a self-hosted host), propose GitLab. Otherwise (or if the user prefers), offer:
35
36	- GitHub — issues live in the repo's GitHub Issues (uses the `gh` CLI)
37	- GitLab — issues live in the repo's GitLab Issues (uses the [`glab`](https://gitlab.com/gitlab-org/cli) CLI)
38	- Local markdown — issues live as files under `.scratch/<feature>/` in this repo (good for solo projects or repos without a remote)
39	- Other (Jira, Linear, etc.) — ask the user to describe the workflow in one paragraph; the skill will record it as freeform prose
40
41	Section B — Triage label vocabulary.
42
43	> Explainer: When the `triage` skill processes an incoming issue, it moves it through a state machine — needs evaluation, waiting on reporter, ready for an AFK agent to pick up, ready for a human, or won't fix. To do that, it needs to apply labels (or the equivalent in your issue tracker) that match strings you've actually configured. If your repo already uses different label names (e.g. `bug:triage` instead of `needs-triage`), map them here so the skill applies the right ones instead of creating duplicates.
44
45	The five canonical roles:
46
47	- `needs-triage` — maintainer needs to evaluate
48	- `needs-info` — waiting on reporter
49	- `ready-for-agent` — fully specified, AFK-ready (an agent can pick it up with no human context)
50	- `ready-for-human` — needs human implementation
51	- `wontfix` — will not be actioned
52
53	Default: each role's string equals its name. Ask the user if they want to override any. If their issue tracker has no existing labels, the defaults are fine.
54
55	Section C — Domain docs.
56
57	> Explainer: Some skills (`improve-codebase-architecture`, `diagnose`, `tdd`) read a `CONTEXT.md` file to learn the project's domain language, and `docs/adr/` for past architectural decisions. They need to know whether the repo has one global context or multiple (e.g. a monorepo with separate frontend/backend contexts) so they look in the right place.
58
59	Confirm the layout:
60
61	- Single-context — one `CONTEXT.md` + `docs/adr/` at the repo root. Most repos are this.
62	- Multi-context — `CONTEXT-MAP.md` at the root pointing to per-context `CONTEXT.md` files (typically a monorepo).
63
64	### 3. Confirm and edit
65
66	Show the user a draft of:
67
68	- The `## Agent skills` block to add to whichever of `CLAUDE.md` / `AGENTS.md` is being edited (see step 4 for selection rules)
69	- The contents of `docs/agents/issue-tracker.md`

People who liked this also viewed

6 picks

Type

setup-matt-pocock-skills

560stars68forks

View on GitHub

How to install setup-matt-pocock-skills?

stevesolun/ctx/setup-matt-pocock-skills

$npx -y skills add stevesolun/ctx --skill setup-matt-pocock-skills

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Setup Matt Pocock's Skills
2
3	Scaffold the per-repo configuration that the engineering skills assume:
4
5	- Issue tracker — where issues live (GitHub by default; local markdown is also supported out of the box)
6	- Triage labels — the strings used for the five canonical triage roles
7	- Domain docs — where `CONTEXT.md` and ADRs live, and the consumer rules for reading them
8
9	This is a prompt-driven skill, not a deterministic script. Explore, present what you found, confirm with the user, then write.
10
11	## Process
12
13	### 1. Explore
14
15	Look at the current repo to understand its starting state. Read whatever exists; don't assume:
16
17	- `git remote -v` and `.git/config` — is this a GitHub repo? Which one?
18	- `AGENTS.md` and `CLAUDE.md` at the repo root — does either exist? Is there already an `## Agent skills` section in either?
19	- `CONTEXT.md` and `CONTEXT-MAP.md` at the repo root
20	- `docs/adr/` and any `src/*/docs/adr/` directories
21	- `docs/agents/` — does this skill's prior output already exist?
22	- `.scratch/` — sign that a local-markdown issue tracker convention is already in use
23
24	### 2. Present findings and ask
25
26	Summarise what's present and what's missing. Then walk the user through the three decisions one at a time — present a section, get the user's answer, then move to the next. Don't dump all three at once.
27
28	Assume the user does not know what these terms mean. Each section starts with a short explainer (what it is, why these skills need it, what changes if they pick differently). Then show the choices and the default.
29
30	Section A — Issue tracker.
31
32	> Explainer: The "issue tracker" is where issues live for this repo. Skills like `to-issues`, `triage`, `to-prd`, and `qa` read from and write to it — they need to know whether to call `gh issue create`, write a markdown file under `.scratch/`, or follow some other workflow you describe. Pick the place you actually track work for this repo.
33
34	Default posture: these skills were designed for GitHub. If a `git remote` points at GitHub, propose that. If a `git remote` points at GitLab (`gitlab.com` or a self-hosted host), propose GitLab. Otherwise (or if the user prefers), offer:
35
36	- GitHub — issues live in the repo's GitHub Issues (uses the `gh` CLI)
37	- GitLab — issues live in the repo's GitLab Issues (uses the [`glab`](https://gitlab.com/gitlab-org/cli) CLI)
38	- Local markdown — issues live as files under `.scratch/<feature>/` in this repo (good for solo projects or repos without a remote)
39	- Other (Jira, Linear, etc.) — ask the user to describe the workflow in one paragraph; the skill will record it as freeform prose
40
41	Section B — Triage label vocabulary.
42
43	> Explainer: When the `triage` skill processes an incoming issue, it moves it through a state machine — needs evaluation, waiting on reporter, ready for an AFK agent to pick up, ready for a human, or won't fix. To do that, it needs to apply labels (or the equivalent in your issue tracker) that match strings you've actually configured. If your repo already uses different label names (e.g. `bug:triage` instead of `needs-triage`), map them here so the skill applies the right ones instead of creating duplicates.
44
45	The five canonical roles:
46
47	- `needs-triage` — maintainer needs to evaluate
48	- `needs-info` — waiting on reporter
49	- `ready-for-agent` — fully specified, AFK-ready (an agent can pick it up with no human context)
50	- `ready-for-human` — needs human implementation
51	- `wontfix` — will not be actioned
52
53	Default: each role's string equals its name. Ask the user if they want to override any. If their issue tracker has no existing labels, the defaults are fine.
54
55	Section C — Domain docs.
56
57	> Explainer: Some skills (`improve-codebase-architecture`, `diagnose`, `tdd`) read a `CONTEXT.md` file to learn the project's domain language, and `docs/adr/` for past architectural decisions. They need to know whether the repo has one global context or multiple (e.g. a monorepo with separate frontend/backend contexts) so they look in the right place.
58
59	Confirm the layout:
60
61	- Single-context — one `CONTEXT.md` + `docs/adr/` at the repo root. Most repos are this.
62	- Multi-context — `CONTEXT-MAP.md` at the root pointing to per-context `CONTEXT.md` files (typically a monorepo).
63
64	### 3. Confirm and edit
65
66	Show the user a draft of:
67
68	- The `## Agent skills` block to add to whichever of `CLAUDE.md` / `AGENTS.md` is being edited (see step 4 for selection rules)
69	- The contents of `docs/agents/issue-tracker.md`

People who liked this also viewed

6 picks

Type