メニュー
Conventional Commits style guide + safety rules. Pull this before any git commit so the message shape and staging rules stay consistent.
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。
SOC 職業分類に基づく
| name | commit |
| description | Conventional Commits style guide + safety rules. Pull this before any git commit so the message shape and staging rules stay consistent. |
| allowed-tools | ["Bash","Read"] |
type(scope): summary
<optional body — explain the why, not the what>
Types: feat | fix | refactor | test | docs | chore
Subject line: imperative mood, ≤ 72 characters, no trailing period.
git add <specific-file> — never git add -A or git add ..git diff --cached before committing. If you see a file you did
not intend to stage, unstage it with git restore --staged <file>..env, credentials, API keys, large binaries, generated
output directories.--no-verify or any flag that skips pre-commit hooks.git push --force, git push -f) without explicit
user approval.git reset --hard to discard work that isn't yours.git clean -fd without explicit user approval.feat(cli): add -p/--playbook flag to li o flow
Resolves NAME to ~/.lionagi/playbooks/<NAME>.playbook.yaml and injects the
declared args schema into the parser so flag values aren't eaten by
positional arguments.
fix(agent): resolve dir layout before flat for profile load
Previously only <name>.md was consulted. Now tries
<name>/<name>.md first; flat form kept for backward compat.
docs(cli): document li skill and li play
Multi-perspective PR review procedure. Plan a minimal DAG of specialists scoped to what the PR actually touches, synthesize with a critic, post ONE consolidated comment per verbosity tier. Pull before any structured PR review so the methodology stays consistent.
General-purpose code review checklist. Use when reviewing any code change without a narrower specialization. Complements security-review, pr-review (multi-perspective), and the other review skills — pull this when you need the standard correctness/quality rubric without a specific angle.
Threat-model rubric for a focused security review of a code change. Use when reviewing auth / input validation / crypto / secrets / supply chain, or as the "security" dimension of a multi-perspective PR review. Pull this skill before starting so severity calibration and coverage stay consistent.
Systematic debug workflow: research → orchestrate agents → escalate. Suggest when: stuck after 2-3 attempts, unfamiliar tooling, tempted to "try random things", or errors don't match documentation.
Plan and execute multi-agent workflows using lionagi's CLI: li o flow (DAG pipelines), li o fanout (parallel workers), and li play (playbook invocations). Use when a task needs multiple agents working in parallel or staged phases.
Author lionagi playbooks — reusable YAML workflow templates that define parametric agent tasks. Playbooks live at ~/.lionagi/playbooks/ and run via li play <name>. Use when: creating reusable workflows, parameterizing agent tasks, or setting up repeatable pipelines.