メニュー
Use when asked to create, scaffold, or write a new vibe-lab Agent Skill. Generates an Agent Skills compatible SKILL.md with optional scripts, references, assets, adapter symlinks, and verification.
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 | create-skill |
| description | Use when asked to create, scaffold, or write a new vibe-lab Agent Skill. Generates an Agent Skills compatible SKILL.md with optional scripts, references, assets, adapter symlinks, and verification. |
Use this skill when the user asks to:
Do not use when the user is only discussing a skill idea. Use skill-authoring when modifying an existing skill.
A skill is .agents/skills/<name>/SKILL.md; optional scripts/, references/, and assets/ are allowed only when they reduce repeated agent work.
Use canonical/skill-template.md.
Minimum shape:
.agents/skills/<name>/
├── SKILL.md
├── scripts/ # optional executable helpers
├── references/ # optional on-demand docs
└── assets/ # optional templates/resources
SKILL.md from canonical/skill-template.md with name and description frontmatter.scripts/ and document usage plus dependencies.references/ and say exactly when to read it.lazyai-cli compile to regenerate adapters and generated docs.lazyai-cli doctor to verify output consistency.--help, useful error messages, and structured output when practical.bin/ or scripts/, not inside one skill.SKILL.md has valid name and description frontmatter.name matches the directory and Agent Skills naming constraints.bin/inject, bin/doctor, and tests/test-provenance-drift.sh pass.Use when debugging a failing test, broken build, runtime error, or unexpected system behavior. Drives hypothesis-based investigation, root-cause fixes, verification, and reusable learning capture.
Use when a claim, plan, spec, doc, or design must be attacked against source evidence before implementation or approval. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when fixing broken behavior and the priority is reproduce, root cause, regression proof, and the smallest safe repair. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when reviewing code changes with explicit stage, target, and focus so own-code checks and others’ PR reviews stay distinct but share one contract. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when the deliverable is docs or reference material and every claim must stay tied to observed behavior or cited source evidence. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.
Use when adding or changing product behavior that must ship with explicit purpose, scenarios, and verification. Uses write tools, shell execution, and may spawn subagents. Invoke with enable_write_tools=true and enable_subagent_tools=true.