Menu
Draft or review minimal, testable goals. Use only when the user explicitly asks to write, revise, or review a goal.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use this skill whenever code-review feedback already exists and may affect a code decision or change. This includes PR comments, findings returned by invoke or any external model or review tool, and delegated-review results—even when the user simply says to fix, address, apply, or resolve them. Do not use to perform a new review, diagnose an unrelated bug, implement a new requirement, or merely summarize or explain feedback without deciding about code.
Interview the user to resolve material branches of a decision tree and converge on a shared plan before acting. Use when multiple reasonable choices would materially change scope, cost, reversibility, or outcome, or when the user asks to brainstorm, shape, or grill an idea. Do not use when facts can resolve the ambiguity or a reversible assumption would not materially affect the result.
Create or improve agent skills from concrete behavior and evidence. Use when building or revising SKILL.md, or testing whether a skill earns its context. Do not use for ordinary documentation or one-off prompts.
Diagnose and fix bugs, failures, and performance regressions. Read this skill BEFORE touching any code whenever the user reports a bug, broken behavior, a crash, wrong output, or a regression — even when the cause looks obvious and the user only asked for a fix. Do not use for a simple explanation of a known error when no diagnosis is requested.
Research with parallel agents, independent evidence angles, and cross-validation. Use when the user explicitly asks for parallel or delegated research, or when a high-cost question materially benefits from independent evidence.
Teach with adaptive guidance, retrieval practice, and Socratic questioning. Use when the user wants to study a topic, build durable understanding, practice, or be coached. Do not use for one-off factual answers, quick explanations, or ordinary task guidance.
| name | goal-writer |
| description | Draft or review minimal, testable goals. Use only when the user explicitly asks to write, revise, or review a goal. |
Turn rough intent into the smallest copy-ready execution contract that makes completion decidable. Produce the contract; do not activate it unless explicitly asked.
Define acceptance before execution. Completion requires evidence that every necessary condition holds; partial progress is not completion.
For open-ended research or long search tasks, read the CDC prompt case to see how a real goal excludes plausible false completions and governs evidence-seeking iteration.
A routine goal can be one sentence:
修复登录超时后的错误跳转；完成以新增回归测试通过且正常登录测试仍通过为准。
A real authorization boundary earns one additional sentence, not a new template:
Prepare the customer-data migration and make its dry run pass against the approved fixture with a reviewed rollback plan. Do not execute the production migration without explicit approval.
The examples show required meaning, not required structure. Domain workflows belong to the relevant task skill and repository instructions.
Aim for at most 1000 characters. Return only the contract unless a consequential assumption must be disclosed or the user asks for explanation.
Run python3 scripts/lint_goal.py - with the contract on stdin, or pass one or more files. The linter rejects empty contracts, explicit placeholder tokens, and text over 4000 characters; it warns above 2000. Use --max-chars N when the target has a stricter hard limit.