メニュー
Use when creating a repository-shaped skill with an AGENTS gate, current state, source bootstrap, SKILL.md, first packet, memory delta and promotion boundary.
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
Preserve continuity, sources and boundaries for Starter L1.
Use when working inside a RepoKernel repository on context-aware project structure, current state, source bootstrap, memory delta, skill lifecycle, templates, audit scripts or promotion packets.
Use when a RepoKernel project has dirty, untracked, stale, duplicate or unclear files and needs a non-destructive classification before cleanup, commit, archive, ignore or owner review.
Use when a RepoKernel project must convert an approved event and persistent intent into a bounded observe-align-distill-evaluate cycle without allowing the same process to approve its own goals, actions or evolution.
Use when a project needs a higher-leverage improvement than the visible task suggests, especially under ambiguity, repeated friction, architectural impact, conflicting sources or a transferable local insight.
Use when converting project intent, supplied documents, existing repository state and environment constraints into a custom RepoKernel seed specification and a safe generation or retrofit plan.
| name | create-skill-repo |
| description | Use when creating a repository-shaped skill with an AGENTS gate, current state, source bootstrap, SKILL.md, first packet, memory delta and promotion boundary. |
Create a new repository-skill that is readable by AI systems and can be evaluated, improved or promoted later.
skill_name:
mission:
users:
inputs:
outputs:
source_authority:
boundary:
validation:
promotion_path:
README.md
AGENTS.md
CURRENT_STATE.md
skills/<skill-name>/SKILL.md
sources/bootstrap/PROJECT_INSTRUCTIONS_v1.0.txt
process/FIRST_PACKET.md
examples/
tests/
Create a minimal local structure and validate it with scripts/audit_skill_repo.py. Do not publish or promote until reviewed.