setup-skills
Configure this repo for the engineering skills — set up its durable document layout, temp-artifact policy, and domain doc layout.
Skill by clementcaron
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/clementcaron-setup-skills
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: documents
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. 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-skills
What's inside
- Skill name
setup-skills- Description
- Configure this repo for the engineering skills — set up its durable document layout, temp-artifact policy, and domain doc layout. Run once before first use of the other engineering skills.
- License
- MIT
- Instructions
- 110 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- SKILLS.md
- artifact-policy.md
- domain.md
SKILL.md (first lines)
# Setup Skills Scaffold the per-repo configuration that the engineering skills assume: - **Durable docs** — which artifacts are allowed to persist in the repo - **Temp artifacts** — which artifacts should live in the OS temp directory by default - **Domain docs** — where `CONTEXT.md` and ADRs live, and the consumer rules for reading them This is a prompt-driven skill, not a deterministic script. Explore, present what you found, confirm with the user, then write. ## Process ### 1. Explore Look at the current repo to understand its starting state. Read whatever exists; don't assume: - `AGENTS.md` and `CLAUDE.md` at the repo root — does either exist? Is there already an `## Agent skills` section in either? - `CONTEXT.md` and `CONTEXT-MAP.md` at the repo root - `docs/adr/` and any `src/*/docs/adr/` directories - `docs/slices/` — sign that durable slice documents are already in use - `docs/agents/` — does this skill's prior output already exist? ### 2. Present findings and ask 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. 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. **Section A — Durable docs.** > Explainer: Durable docs are the few markdown artifacts that are worth keeping in the repo because they remain useful after the current session is over. These skills work best when the durable set stays small and intentional. Default posture: - `CONTEXT.md` - `docs/adr/` - `docs/slices/` only when the user explicitly wants slice docs kept or needs a persistent multi-session handoff **Section B — Temp artifacts.** > Explainer: Temporary artifacts are planning and coordination outputs that help during the current session but would create clutter if they stayed in the repo. These should live in the OS temp directory by default. Default posture: - PRDs - draft slice breakdowns - handoff documents - triage notes - prototype verdict notes If the user wants one of these to persist, ask for the exact path before writing it. **Section C — Domain docs.** > Explainer: Some skills (`improve-codebase-architecture`, `diagnosing-bugs`, `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. Confirm the layout: - **Single-context** — one `CONTEXT.md` + `docs/adr/` at the repo root. Most repos are this. - **Multi-context** — `CONTEXT-MAP.md` at the root pointing to per-context `CONTEXT.md` files (typically a monorepo). ### 3. Confirm and edit Show the user a draft of: - The `## Agent skills` block to add to whichever of `CLAUDE.md` / `AGENTS.md` is being edited (see step 4 for selection rules) - The contents of `docs/agents/artifact-policy.md` and `docs/agents/domain.md` Let them edit before writing. ### 4. Write **Pick the file to edit:** - If `CLAUDE.md` exists, edit it. - Else if `AGENTS.md` exists, edit it. - If neither exists, ask the user which one to create — don't pick for them. Never create `AGENTS.md` when `CLAUDE.md` already exists (or vice versa) — always edit the one that's already there. If an `## Agent skills` block already exists in the chosen file, update its contents in-place rather than appending a duplicate. Don't overwrite user edits to the surrounding sections. The block: ```markdown ## Agent skills ### Durable docs Durable artifacts for this repo live in `CONTEXT.md`, `docs/adr/`, and optionally `docs/slices/`. See `docs/agents/artifact-policy.md`. ### Temp artifacts Transient artifacts live in the OS temp directory unless the user explicitly asks to keep them. See `docs/agents/artifact-policy.md`. ### Domain docs [one-line summary of layout — "single-context" or "multi-context"]. See `docs/agents/domain.md`. ``` Then write the two docs files using the seed templates in this skill folder as a starting point: - [artifact-policy.md](./artifact-policy.md) — durable-docs and temp-artifacts policy - [domain.md](./domain.md) — domain doc consumer rules + layout ### 5. Done Tell the user the setup is complete and which engineering skills will now read from these files. Mention they can edit `docs/agents/*.md` directly later — re-running this skill is only necessary if they want to change the policy or restart from scratch.
From clementcaron/skills, MIT.
More from clementcaron/skills
- 0.469score
to-prd
clementcaron
Turn the current conversation into a PRD — no interview, just synthesis of what you've already discussed.
SkillCFreshness: CClaude Code +9 - 0.455score
diagnosing-bugs
clementcaron
Diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: CClaude Code +9 - 0.450score
codebase-design
clementcaron
Shared vocabulary for designing deep modules.
SkillCFreshness: CClaude Code +9 - 0.450score
domain-modeling
clementcaron
Build and sharpen a project's domain model.
SkillCFreshness: CClaude Code +9 - 0.444score
to-issues
clementcaron
Break a plan, spec, or PRD into independently-grabbable vertical slices using tracer-bullet slices.
SkillCFreshness: CClaude Code +9 - 0.444score
resolving-merge-conflicts
clementcaron
Use when you need to resolve an in-progress git merge/rebase conflict.
SkillCFreshness: CClaude Code +9 - 0.439score
handoff
clementcaron
Compact the current conversation into a handoff document for another agent to pick up.
SkillCFreshness: CClaude Code +9 - 0.439score
implement
clementcaron
Implement a piece of work based on a PRD, a slice document, or a single approved slice.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 17, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/clementcaron/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from clementcaron
- 0.469score
to-prd
clementcaron
Turn the current conversation into a PRD — no interview, just synthesis of what you've already discussed.
SkillCFreshness: CClaude Code +9 - 0.455score
diagnosing-bugs
clementcaron
Diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: CClaude Code +9 - 0.450score
codebase-design
clementcaron
Shared vocabulary for designing deep modules.
SkillCFreshness: CClaude Code +9 - 0.450score
domain-modeling
clementcaron
Build and sharpen a project's domain model.
SkillCFreshness: CClaude Code +9 - 0.444score
to-issues
clementcaron
Break a plan, spec, or PRD into independently-grabbable vertical slices using tracer-bullet slices.
SkillCFreshness: CClaude Code +9 - 0.444score
resolving-merge-conflicts
clementcaron
Use when you need to resolve an in-progress git merge/rebase conflict.
SkillCFreshness: CClaude Code +9
Cite this page
setup-skills. Agent Mart. https://agentmart.dev/skills/clementcaron-setup-skills (last updated 2026-10-24)