菜单
Clarity gate for prompts: intercepts unclear requests and forces the model to restate the user's intent to align before working, then diagnose the root cause and reuse the domain's mature, established practices before improvising. Clear prompts pass through untouched.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/ViryaZheng/promptly-prompt --skill promptly-prompt命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | promptly-prompt |
| description | Clarity gate for prompts: intercepts unclear requests and forces the model to restate the user's intent to align before working, then diagnose the root cause and reuse the domain's mature, established practices before improvising. Clear prompts pass through untouched. |
AI answer quality depends on input clarity, not prompt tricks — and nobody writes perfectly clear prompts all the time. This skill catches the unclear ones at submission and repairs them through alignment.
It operates via a UserPromptSubmit hook that injects two disciplines
into unclear requests, both at once:
Restate to align — echo the user's request in your own words and state your understanding, so a misread surfaces before any work happens. If the restatement reveals a mismatch, raise it before acting.
Diagnose, then reuse prior art — don't solve from memory. Diagnose the root cause of the problem, search for the domain's mature, established practices — methodologies, frameworks, libraries, prior art — and only then proceed. If nothing fits, say so and explain why.
The hook script at scripts/intercept.py scores prompt unclarity using
rule-based signals: vague verbs without success criteria, hedging, and
dangling referents add points; concrete anchors (paths, errors, code),
structure, and explicit criteria subtract them. Length never adds points —
a long, well-specified prompt is the clearest kind and passes untouched.
Unclear requests (score >= 3) get the full injection, in the prompt's own
language (Chinese or English) — both disciplines, every time.
When invoked directly (e.g., user says "optimize this prompt"), apply the two disciplines manually: restate the user's intent with implicit needs surfaced, then locate the domain and the existing methods that belong to it. Rewrite the prompt with that context filled in.