ワンクリックで
crow-pet-spec-writer
Ask clarifying questions, write a bounded SPEC.MD, and hand it to the right harness or agent for building.
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。
メニュー
Ask clarifying questions, write a bounded SPEC.MD, and hand it to the right harness or agent for building.
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
Use when a task may need multiple agents, persistent role agents, cross-harness coordination, or generated subagents.
Route crow.pet tasks into records, policy, adapters, subagents, evaluation, and memory.
Classify action risk and return Silent, Notify, Ask, or Block decisions before sensitive, external, or state-changing work.
Convert corrections, approvals, failures, and task patterns into memory, examples, rubrics, and policy proposals.
Turn approved SPEC.MD files or workflow definitions into markdown work items for harness or agent builders, then track verification and handoff state.
Delegate bounded coding tasks to Codex-compatible harnesses for implementation, tests, and structured handoffs.
| name | crow-pet-spec-writer |
| description | Ask clarifying questions, write a bounded SPEC.MD, and hand it to the right harness or agent for building. |
Use this skill when the user wants something built but the build target, constraints, acceptance criteria, or builder surface need to be made explicit first.
SPEC.MD; prefer one to three questions.SPEC.MD from ../../templates/SPEC.md.code_generation, image_generation, repo_write, web_research, browser_control, or tool_execution.tool_profiles when a tool capability is repeated, ambiguous, permission-sensitive, or shared across runtimes.crow-pet-policy-gate.Load ../../templates/SPEC.md only when drafting or checking a spec.
Load ../crow-pet-skill-architect/SKILL.md when the spec concerns a new skill, adapter-backed workflow, composed workflow, compiled workflow, deterministic script-backed skill, or side-effect workflow.
Load ../crow-pet-policy-gate/SKILL.md when the spec includes external writes, repo writes, auth-sensitive workflows, publication, spending, destructive actions, or sensitive context.
Load ../../adapters/patterns/capability-broker.md only when semantic capability needs must bind to a concrete adapter, tool, model, or harness.
Load ../../adapters/patterns/tool-capability-profile.md only when a tool capability needs a reusable profile before binding.
Load ../crow-pet-codex-delegate/SKILL.md when the spec should become code, an app, a tool, an adapter, or repository changes.
Load ../crow-pet-image/SKILL.md when the spec should become an image or visual asset.
Load contract.md and rubric.md only for acceptance or evaluation.
delegates_to: crow-pet-skill-architect, crow-pet-codex-delegate, crow-pet-image, or another selected builder skill.uses_adapter: adapters/patterns/capability-broker.md, adapters/patterns/tool-capability-profile.md when a tool binding needs a reusable profile, adapters/patterns/execution-architecture.md and adapters/patterns/compiled-workflow.md when a skill architecture needs target mapping, plus selected harness, tool, model, or target adapters.loads_context: context capsule only when task-relevant memory or source material affects the spec.evaluates_with: contract.md, rubric.md, and the SPEC.MD acceptance criteria.SPEC.MD portable across harnesses.