setup
Set up or update the repo's Tracker ref, where its Issues live; its Verify skill, which drives the app the way a user does; or its Models ref, the model and…
Skill by michielvandermeer
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/michielvandermeer-setup
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/setup
What's inside
- Skill name
setup- Description
- Set up or update the repo's Tracker ref, where its Issues live; its Verify skill, which drives the app the way a user does; or its Models ref, the model and effort each plugin agent runs at.
- License
- MIT
- Instructions
- 51 lines in SKILL.md · view on GitHub
Files (8)
- GITHUB.md
- JIRA.md
- LOCAL.md
- MODELS.md
- SKILL.md
- VERIFY-EXAMPLE.md
- VERIFY-UPKEEP.md
- VERIFY.md
SKILL.md (first lines)
# Setup Write or update `.agents/refs/tracker.md`, the **Tracker ref**: the repo's own description of its **Tracker** and of how each operation the skills name is carried out there. The plugin ships one **Tracker template** per system — [LOCAL.md](LOCAL.md), [GITHUB.md](GITHUB.md), [JIRA.md](JIRA.md). The copy this skill writes is the repo's own to edit; the skills follow it as written, and later changes to a template do not reach it. Everything the user reads runs at the bar [`technical-writing/SKILL.md`](../technical-writing/SKILL.md) sets: read it and follow it before the first message — `/technical-writing` does not load as a skill. With the argument `verify`, follow [VERIFY.md](VERIFY.md) in place of the steps below. With the argument `models`, follow [MODELS.md](MODELS.md). ## 1. Read what is there - `.agents/refs/tracker.md`. When it exists, this run is an update: show its settings, ask what should change, and take the existing ref as the draft at step 3. - `git remote -v`, and `gh auth status` when the remote is on GitHub. - Old tracker docs: `issue-tracker.md` and `triage-labels.md` under `.agents/refs/`, `.agents/ref/`, or `docs/agents/`. Read them only for what they say about the repo's tracker. - Each line in `AGENTS.md` or `CLAUDE.md` that says where work is tracked. - `CONTEXT-MAP.md`. Its contexts become labels on GitHub and Jira. - Local work under `.agents/issues/`, `.agents/ideas/`, and `.agents/specs/`, in [LOCAL.md](LOCAL.md)'s shape or an older one. Done: you can name the tracker the repo appears to use and list every local work document it holds. ## 2. Choose the tracker Suggest one: GitHub Issues when the remote is on GitHub and `gh` is signed in; Jira when the old docs or the user name it; local Markdown otherwise. The invocation's argument counts as the user's pick. Otherwise ask the user to confirm the suggestion or pick another. Then ask, in one round, for every setting the chosen template's `## Settings` section lists. For a tracker with no template, ask the user to describe how it does each operation the templates name. Done: the tracker and every setting are known. ## 3. Draft and show Copy the chosen template and fill in its settings. For a tracker with no template, write the user's description under the headings every template uses — Settings, Issues, Statuses, Maps and Decision tickets — with one entry for each operation the templates list. Show the draft and wait for a yes. An answer that changes the draft gets the changed draft shown again. Done: the user said yes to the draft. ## 4. Apply 1. Write `.agents/refs/tracker.md`. 2. On GitHub, create each label the ref names that `gh label list` lacks: the statuses, the Decision ticket types, the categories, and the contexts. 3. Offer to move the local work from step 1. On yes, file each open document in the new Tracker — an old Idea as an Issue in `needs-grilling`, an old Spec as one in `ready-for-agent`, an Issue in its own status, a Map in `wayfinding` with its open Decision tickets as children — and skip any whose title the Tracker already holds. Delete each local file once its Issue exists. When the new Tracker is local Markdown, moving rewrites each document into LOCAL.md's shape at the path LOCAL.md gives it. 4. Offer to delete the old tracker docs, and to fix each `AGENTS.md` or `CLAUDE.md` line that contradicts the new ref. Apply what the user accepts. 5. When `.agents/refs/models.md` is missing, write it and its pointer line with every agent at its default, as [MODELS.md](MODELS.md#the-models-ref) shows. 6. Commit everything this run changed, staged by name, in one commit. Done: the commit exists, and every move is done, declined, or reported as failed. ## 5. Report Name the Tracker and the ref's path, and the Models ref when this run wrote it. List the labels created, each document moved with its new reference, each skipped because its title was already there, each move that failed, and each offer the user declined. Done: every label, move, skip, failure, and declined offer from step 4 appears in the report.
From michielvandermeer/skills, MIT.
More from michielvandermeer/skills
- 0.628score
hillclimb
michielvandermeer
Hillclimb one measured number — test-suite time, build time, memory, bundle size — keeping only the changes that measurably help.
SkillAFreshness: A★ 9Claude Code +9 - 0.628score
technical-writing
michielvandermeer
The house standard for every sentence a person reads.
SkillAFreshness: A★ 9Claude Code +9 - 0.628score
implement
michielvandermeer
Implement a spec by slicing it into steps, then a loop of implement, review, and verify, each in its own sub-agent.
SkillAFreshness: A★ 9Claude Code +9 - 0.628score
verify
michielvandermeer
Drive this checkout's skills the way a user does — load the working tree as the plugin in a headless Claude Code session inside a scratch repo, type the slash…
SkillAFreshness: A★ 9Claude Code +9 - 0.627score
pr
michielvandermeer
Pull request descriptions.
SkillAFreshness: A★ 9Claude Code +9 - 0.625score
doctor
michielvandermeer
Moves documents into this project's canonical layout, closes local Issues the code already implements, and brings every ADR to state the decision in force.
SkillAFreshness: A★ 9Claude Code +9 - 0.625score
explain
michielvandermeer
Explain anything as a written walkthrough, a diagram in the chat, an HTML page, or a narrated video, picking the format that fits.
SkillAFreshness: A★ 9Claude Code +9 - 0.625score
retro
michielvandermeer
Look at a finished session, apply high-priority changes this repository owns, file the structural ones as Issues, and summarise the rest.
SkillAFreshness: A★ 9Claude Code +9 - 0.622score
brainstorm
michielvandermeer
Explore a vague problem as very different Directions, side by side, and file the ones you keep as Issues.
SkillAFreshness: A★ 9Claude Code +9 - 0.622score
learn-habits
michielvandermeer
Rebuild a person's Grilling profile from the Habits in their past grilling sessions.
SkillAFreshness: A★ 9Claude Code +9 - 0.622score
triage
michielvandermeer
Sort incoming reports into Specs and parked Issues — one Issue per distinct problem.
SkillAFreshness: A★ 9Claude Code +9 - 0.620score
grill-with-docs
michielvandermeer
A relentless round-by-round interview to sharpen a plan or design, which also creates docs (ADRs and glossary) as we go.
SkillAFreshness: A★ 9Claude Code +9
Signals
- Stars
- 9
- Forks
- 0
- Open issues
- 8
- Last commit (this folder)
- Oct 17, 2026 (12 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/michielvandermeer/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from michielvandermeer
- 0.628score
hillclimb
michielvandermeer
Hillclimb one measured number — test-suite time, build time, memory, bundle size — keeping only the changes that measurably help.
SkillAFreshness: A★ 9Claude Code +9 - 0.628score
implement
michielvandermeer
Implement a spec by slicing it into steps, then a loop of implement, review, and verify, each in its own sub-agent.
SkillAFreshness: A★ 9Claude Code +9 - 0.628score
verify
michielvandermeer
Drive this checkout's skills the way a user does — load the working tree as the plugin in a headless Claude Code session inside a scratch repo, type the slash…
SkillAFreshness: A★ 9Claude Code +9 - 0.628score
technical-writing
michielvandermeer
The house standard for every sentence a person reads.
SkillAFreshness: A★ 9Claude Code +9 - 0.627score
pr
michielvandermeer
Pull request descriptions.
SkillAFreshness: A★ 9Claude Code +9 - 0.625score
doctor
michielvandermeer
Moves documents into this project's canonical layout, closes local Issues the code already implements, and brings every ADR to state the decision in force.
SkillAFreshness: A★ 9Claude Code +9
Cite this page
setup skill. Agent Mart. https://agentmart.dev/skills/michielvandermeer-setup (last updated 2026-10-24)