菜单
Use when about to start a significant coding task — transforms rough thoughts into a disciplined prompt with acceptance criteria, anti-sycophancy rules, and complexity budget. Also use for "write a prompt", "create prompt for", or "discipline this task".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when you need to commit and push changes — stages files, commits with co-author tags, pulls with rebase, resolves conflicts, and pushes. Also supports "pr" mode for creating PRs and "clean" mode for pruning merged branches. Also use for "commit", "push", "sync", or "create PR".
Use when the user wants short-and-sweet answers to one or more questions. Restates each question as a bold heading, then answers in 2–5 lines per question. Bullets and small tables allowed when they help. Also use for "quick question", "qq", "answer briefly", or any "/my-qq <question>" invocation.
Use when starting implementation on any project — reads planning docs, dispatches sub-agents, and creates or reiterates docs/acceptance-criteria.md with measurable criteria per feature. Must run before writing implementation code. Also use for "create acceptance criteria", "what are the requirements", or "define done".
Use when starting a new feature or project from a raw idea — asks targeted questions and produces a structured PRD at docs/prd-<slug>.md. Sits upstream of /my-prompt. Also use for "write a PRD", "product requirements", or "what should we build".
Use when code needs rigorous review before shipping — spawns skeptic/believer/referee agents in iterative rounds until findings converge to nitpicks. Use after implementing features, before merging PRs, or when the user asks for a "thorough review", "adversarial review", or "tear this apart".
Use when facing a complex task that benefits from multiple specialized agents working in parallel — spawns, delegates, tracks status, and collects results. Also use when the user says "use agents", "multi-agent", or "parallelize this".
| name | my-prompt |
| description | Use when about to start a significant coding task — transforms rough thoughts into a disciplined prompt with acceptance criteria, anti-sycophancy rules, and complexity budget. Also use for "write a prompt", "create prompt for", or "discipline this task". |
| argument-hint | < your rough idea or task description > |
| allowed-tools | Bash(bash:*), Read, Write, Edit, Glob, Grep |
You are a prompt engineer whose job is to transform the user's rough thoughts into a disciplined prompt that will produce correct, minimal code — not plausible-looking code.
LLMs optimize for plausibility over correctness. Research confirms:
The failure mode is NOT broken syntax. It's:
Take the user's raw input (provided as ARGUMENTS) and produce an improved prompt. Follow these steps:
Read the user's rough thoughts. Ask yourself:
Every improved prompt MUST include measurable acceptance criteria:
Read references/checklist.md for the quality checklist before finalizing. Inject the anti-sycophancy rules, complexity constraints, and verification requirements into the generated prompt.
Read assets/prompt-template.md for the output template. Present the improved prompt in a clean, copy-paste-ready format following that structure.
What: Transforms rough ideas into disciplined prompts with anti-sycophancy guards, complexity budgets, and verifiable acceptance criteria.
Usage: /my-prompt add a webhook handler for Stripe — pass your rough task description.
Output: A structured prompt with: task restatement, scope limits, acceptance criteria, anti-patterns to avoid, and verification steps.
When: Before starting any significant coding task. Prevents LLMs from generating plausible-but-wrong code.
