Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.
日本語の概要は準備中です。原文の説明を表示しています。
Scaffolds new projects with git, CI/CD workflows, pre-commit hooks, and build config. Use when starting a new Python, Rust, or TypeScript project from scratch.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Interactive workflow for initializing new software projects with complete development infrastructure.
Load modules/language-detection.md
Load modules/metadata-collection.md
Gather:
Check for existing configurations:
ls -la
Verification: Run the command with --help flag to verify availability.
If files exist (Makefile, .gitignore, etc.):
Load modules/template-rendering.md
Run initialization script:
python3 plugins/attune/scripts/attune_init.py \
--lang {{LANGUAGE}} \
--name {{PROJECT_NAME}} \
--author {{AUTHOR}} \
--email {{EMAIL}} \
--python-version {{PYTHON_VERSION}} \
--description {{DESCRIPTION}} \
--path .
Verification: Run the command with --help flag to verify availability.
The script also scaffolds the project decision journal: docs/tradeoffs.md
and docs/lessons-learned.md. These are append-only logs that later workflows
(brainstorm, specify, plan, execute, review) write to as decisions and lessons
arise. Existing journal files are never overwritten. The format follows the
leyline:decision-journal contract; init uses leyline's template when present
and a vendored copy otherwise, so it works with or without leyline installed.
Verification: Confirm docs/tradeoffs.md and docs/lessons-learned.md
exist and each contains an ## Active index and an ## Archive section.
# Check if git is initialized
if [ ! -d .git ]; then
git init
echo "Git repository initialized"
fi
Verification: Run git status to confirm working tree state.
Validate setup:
# Check Makefile targets
make help
# List created files
git status
Verification: Run git status to confirm working tree state.
Advise user to:
# Install dependencies and hooks
make dev-setup
# Run tests to verify setup
make test
# See all available commands
make help
Verification: Run pytest -v to verify tests pass.
--langchmod +x on scriptsmake help shows available targetsmake test runs without errors (even if no tests yet)docs/tradeoffs.md and docs/lessons-learned.md exist, each with an
## Active index and an ## Archive section.--no-git) and make help lists targets.--dry-run writes no files, including the journal.**Verification:** Run `pytest -v` to verify tests pass.
User: /attune:project-init
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Shapes turns action-first: action leads, steps numbered, state restated. Use for ADHD-friendly output. Do not use to trim tokens; use response-compression.
日本語の概要は準備中です。原文の説明を表示しています。
Inverts burden of proof for code additions. Use when reviewing PRs, planning refactors, or running unbloat to challenge every addition's necessity.
日本語の概要は準備中です。原文の説明を表示しています。
Tracks per-agent token usage and flags waste in parallel dispatch. Use when evaluating parallel agent efficiency or after a multi-agent run.
日本語の概要は準備中です。原文の説明を表示しています。
Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.
日本語の概要は準備中です。原文の説明を表示しています。
Evaluates API surface design, consistency, and exemplar alignment. Use when reviewing public API changes or before releasing a new API surface.
日本語の概要は準備中です。原文の説明を表示しています。
Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.
日本語の概要は準備中です。原文の説明を表示しています。