agentleFS
HeyEddi-comHeyEddi-com/heyeddi-skills/skills/heyeddi-setup/SKILL.md

heyeddi-setup

Skill0 starsChanged 3 months agoMITView on GitHub

ALWAYS-ON prefs gate: ensures `.heyeddi/stack.json` holds git/env and agent prefs. Incomplete prefs fail git/CI/commit/push assumptions until verify_setup --check passes. Asks env layout, custom workflow escape hatch, worktrees, commit/push autonomy. Tech stack is discovered by other skills. Use when setup is incomplete or the user says setup, preferences, or heyeddi-setup.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before commit, push, PR base, or branch/env assumptions

    line 24
  2. Distinctive:

    Ask the user (defaults shown)

    line 42
  3. Very specific:

    Read .heyeddi/stack.json before git/commit/push (only after verify_setup --check passes):

    line 75
  4. Distinctive:

    Ask frontend / backends / package manager / CI in this skill

    line 84
  5. Very specific:

    Put prefs outside .heyeddi/stack.json

    line 85
  6. Distinctive:

    Treat incomplete prefs as advisory when about to commit, push, or assume branches

    line 87

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

HeyEddi Setup

Project working agreement for agents: ensure .heyeddi/stack.json has git/env + agent prefs. Re-run anytime to update.

Always on as the prefs hard gate before git/CI/commit/push or agent autonomy. See reference/setup-always-on.md and hub docs/always-on-skills.md.

Does not quiz frontend, backends, package manager, or CI — those are filled by scaffold / engineering / CI skills as the project evolves.

When to use

  • Missing git / agent / setup prefs in stack.json
  • User says "setup", "preferences", or @heyeddi-setup
  • Session start when verify_setup --check fails (hard route — do not invent prefs)
  • Before commit, push, PR base, or branch/env assumptions
  • Re-run to change env layout or agent autonomy

Hard gate

python .agents/skills/heyeddi-setup/scripts/verify_setup.py --project-root . --check
  • Exit 0 — honor prefs in stack.json
  • Exit 1 — stop git/CI/agent assumptions; finish this skill until check passes

Non-git work may continue. Never invent branch names, PR bases, or auto-commit/push while incomplete.

Mandatory pipeline

  1. load_setup — current stack.json + missing paths
  2. list_questions — ask all on re-run; --missing-only on first pass OK
  3. Ask the user (defaults shown)
  4. write_setup --json '…'
  5. verify_setup --check — must pass before you stop

Questions (prefs only)

#AskChoices
1Env / branch layout?main_staging_dev (default) or main_dev
2Different workflow?no → keep preset; or describe (gitflow, trunk+tags, …) → custom
3Git worktrees for parallel features?yes / no
4Agent may commit without asking?ask / auto
5Agent may push without asking?ask / auto
6Penpot as design source?auto (default) / on / off. Taste always stays on.

Presets (always production + staging)

PresetMapping
main_staging_devprod ← main, staging ← staging, dev ← dev; pr_base = dev
main_devprod ← main, staging ← dev; pr_base = dev

Tools

python .agents/skills/heyeddi-setup/scripts/load_setup.py --project-root .
python .agents/skills/heyeddi-setup/scripts/list_questions.py --project-root .
python .agents/skills/heyeddi-setup/scripts/write_setup.py --project-root . --json '{"git.preset":"main_staging_dev","git.custom_workflow":null,"git.worktrees":false,"agent.commit":"ask","agent.push":"ask"}'
python .agents/skills/heyeddi-setup/scripts/verify_setup.py --project-root . --check

Agents: always honor prefs

Read .heyeddi/stack.json before git/commit/push (only after verify_setup --check passes):

  • git.environments — which branch maps to production / staging / (optional) dev
  • git.pr_base / git.default_branch
  • git.custom_workflow — if set, follow that description over the preset
  • agent.commit / agent.push — if ask, confirm first

Never

  • Ask frontend / backends / package manager / CI in this skill
  • Put prefs outside .heyeddi/stack.json
  • Claim setup done without verify_setup --check
  • Treat incomplete prefs as advisory when about to commit, push, or assume branches
  • Replace @project-engineering / @flutter-engineering scaffold duties

When the task is complete: suggest next skills

python .agents/skills/heyeddi/scripts/suggest_next_skill.py --current-skill heyeddi-setup --project-root .

Include the script's ### Next step block in your final reply.

Related

  • reference/setup-always-on.md — hard gate policy
  • reference/stack-schema.md — key list
  • @heyeddi — hard-route setup when prefs incomplete
  • @pre-merge-gate — runs verify_setup --check
  • @project-engineering / @flutter-engineering — discover and write tech into stack.json

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.