メニュー
Create a fresh venv, editable-install a Python project, and run its test suite — pure shell, zero LLM calls
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
SOC 職業分類に基づく
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/ikangai/tmuxllm --skill dev-env-setupコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
Clone a GitHub repository, detect its build system, and run the canonical install — pure shell, zero LLM calls. Crystallises the install-from-source dance so an agent doesn't surrender on "binary not found".
Single-conversation role-cycling variant of codebase-trio — one tmuxllm agent performs writer and reviewer roles in sequence, with role briefs loaded substrate-purely from roles/*.md
Spawn a persistent named agent from a known role archetype (calendar, email, code-review, monitor, scheduler). Reads the archetype's markdown template, asks the user the domain questions it names, composes a role-shaped persona, then calls `system/spawn-agent` to spawn with that persona installed. Use when the user says "set up a calendar agent", "give me an email assistant", "spawn a code-review bot", etc.
| name | dev-env-setup |
| description | Create a fresh venv, editable-install a Python project, and run its test suite — pure shell, zero LLM calls |
| capabilities | ["shell"] |
Bootstrap and verify a Python project's development environment without
involving an LLM. Reads pyproject.toml (or falls back to requirements.txt),
provisions a venv, installs the project editable, and runs the test suite.
This is a procedure skill (class: procedure): the harness encodes the
steps, so the LLM is removed from the deterministic plumbing entirely. It
exists to anchor the Phase 1 token-savings thesis (≥5× without/with) on a
task class where the thesis actually applies.
tmuxllm-skill run dev-env-setup
| var | default | meaning |
|---|---|---|
REPO | $PWD | Project to set up |
WS | /tmp/dev-env-setup-<pid> | Workspace for venv + result.json |
PYTHON | python3 | Interpreter to seed the venv with |
PYTEST_ARGS | -q | Args appended to pytest. Quoted multi-word args survive (e.g. -m "not e2e" -q). |
$PYTHON; abort if missing.python -m venv $WS/venvpyproject.toml present → pip install -e '.[dev]' (or '.' if no
dev extras).requirements.txt present → pip install -r requirements.txt.failure.pytest $PYTEST_ARGS (run from $REPO).$WS/result.json with the canonical envelope (status, summary,
decisions: 0, zero-token tokens block).Each step has a single deterministic right answer for any given project
state. Wrapping these in an LLM loop is wasteful: a from-scratch tmuxllm
agent would burn ~10–20 decisions deciding which Python to use, where to
put the venv, parsing pyproject.toml, interpreting pytest output, deciding
when to declare done. The skill replaces that with bash and reports the
outcome.
TMUXLLM_PROFILE=openrouter-sonnet \
python tools/skill_ab.py \
--skill dev-env-setup \
--scratch-goal "Set up a fresh Python development environment for $REPO: \
create a venv, install the project editable with dev extras, and run the \
test suite excluding e2e markers. Report success or the failing test names."
Pass criteria: ratio ≥ 5× (the procedure-skill criterion from the revised Phase 1 verification gate).