agentleFS
Sign inStart free
HippocampusEvolveHippocampusEvolve/universal-agent-seed/.claude/skills/bootstrap-stack/SKILL.md

bootstrap-stack

Skill0 starsChanged 4 months agoMITView on GitHub

Grow the stack-agnostic seed into a concrete language stack (Python or TypeScript/Node/Bun, Go, Rust) — enabling tools, language config, a sample test, and wiring the mise lint/test/ build tasks. Use only when the user explicitly runs /bootstrap-stack <lang>.

  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. kohj1018/agentic-dev-harness★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository8 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Add the $ARGUMENTS stack to this seed.

    line 13
  2. Very specific:

    Run mise run check and confirm it passes.

    line 26
  3. Very specific:

    Add a [tool.ruff] section.

    line 33
  4. Distinctive:

    Keep changes minimal and idiomatic for the chosen stack.

    line 55

≈ “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

Add the $ARGUMENTS stack to this seed. Ask first if $ARGUMENTS is empty or ambiguous.

General steps (adapt to $ARGUMENTS):

  1. Enable tools in mise.toml: uncomment (or add) the relevant [tools] lines, then run mise install.
  2. Create the language config at repo root (see per-stack details below).
  3. Wire mise.toml tasks so lint, test, and build are no longer no-ops — replace their echo placeholders with the real commands.
  4. Add a tiny sample (one source file + one passing test) under src/ so mise run check proves the toolchain end-to-end.
  5. Update AGENTS.md: the Commands table, Project structure, Testing, and Code style sections to reflect the real stack.
  6. Run mise run check and confirm it passes. Then, if git is initialized, commit: chore: bootstrap $ARGUMENTS stack.

python

  • Tools: python = "3.13", uv = "latest", ruff = "latest".
  • uv init → pyproject.toml; add ruff + pytest as dev deps (uv add --dev ruff pytest).
  • Add a [tool.ruff] section. Tasks: lint = "ruff check .", fmt also runs ruff format ., test = "uv run pytest -q", build = "uv build".
  • Sample: src/example.py + tests/test_example.py.

typescript / node

  • Tools: node = "lts", pnpm = "latest", "npm:@biomejs/biome" = "latest".
  • pnpm init; add typescript, vitest, @biomejs/biome (pnpm add -D ...); create tsconfig.json and biome.json.
  • Tasks: lint = "biome check .", fmt also runs biome format --write ., test = "pnpm vitest run", build = "pnpm tsc -p tsconfig.json".
  • Sample: src/example.ts + src/example.test.ts.

bun

  • Tools: bun = "latest". bun init; tasks use bun test / bun build. Use Biome for lint/fmt.

go / rust

  • Tools: go = "latest" or rust = "latest". Standard layout; tasks use go test ./... / cargo test, go build ./... / cargo build. Keep dprint for md/json/toml.

Keep changes minimal and idiomatic for the chosen stack; don't pull in frameworks unless asked.

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.

Check your setup, free