pi-goal
Write or improve Pi /goal, goal prompt files, long-running objectives, or goal_prompt_file.md. Not for PRDs or task planning.
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
Write or improve Pi /goal, goal prompt files, long-running objectives, or goal_prompt_file.md. Not for PRDs or task planning.
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
Pi extensions and tool policy: extensions/*.ts, hooks, registerTool, promptGuidelines, registerCommand, footer/status UI, tool_result, session hooks, or subprocesses. Not for slash-command placement; use pi-command.
README, CHANGELOG, docs/, RFCs, ADRs, guides, or Markdown structure. Not for prose cleanup or archival work.
Prose cleanup for filler, hype, vague claims, repetition, detection tells, or uncited specifics. Not for Markdown architecture or archival work.
Requirements, user stories, acceptance/verification criteria, or testable outcomes. Not for PRD drafting (/prd) or Pi /goal prompts.
Use for /prd-it or to draft, refine, or review a Product Requirements Document. Not for acceptance criteria, planning, or Pi /goal prompts.
Pi session, trace, metrics, routing, workflow-friction, workflow-telemetry, usage, or local JSONL analysis with DuckDB. Use for aggregating or correlating Pi runtime logs. Not for adding telemetry, generic SQL/database design, or non-Pi logs.
| name | pi-goal |
| description | Write or improve Pi /goal, goal prompt files, long-running objectives, or goal_prompt_file.md. Not for PRDs or task planning. |
Use this skill when the output will be pasted into /goal or saved as a goal prompt. Use planning for acceptance criteria and prd for product requirement documents.
A goal prompt should state the outcome and constraints clearly enough for autonomous execution without turning ordinary work into a project-management artifact.
/goal ... unless the user asks for a file or the prompt needs durable detail./goal Outcome: <specific end state>
Scope: <important boundaries and constraints>
Work: <tasks only when needed>
Validation: <checks that directly test the outcome, or omit>
Completion: Call goal_complete when complete, naming any real gap.
For actual stateful infrastructure, add the minimum safe rollout details: one independent target at a time, current backup or explicit no-prior-state evidence, restore action, rollback boundary, health check, and stop-on-failure behavior.