Stop Vague

Rewrites vague workplace feedback (performance reviews, 1:1 notes, peer feedback, promotion write-ups) into specific, behavioral, actionable feedback. Use when the user pastes feedback that sounds like "great job", "needs more ownership", "be more strategic", or asks to sharpen, fix, or score feedback before delivering it ("use stop-vague", "sharpen this feedback", "score this feedback").

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add sumanbukka/stop-vague --skill stop-vague
Manual install
git clone --depth 1 https://github.com/sumanbukka/stop-vague.git /tmp/stop-vague
mkdir -p ~/.claude/skills
cp -r /tmp/stop-vague/. ~/.claude/skills/stop-vague

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Stop Vague

Most feedback fails because the writer knows what they mean and the reader does not. "Needs more ownership" tells the reader something is wrong and nothing about what to do on Monday. This skill finds the vague parts, asks for or infers the missing facts, and rewrites the feedback so a person could act on it or repeat it back.

## Workflow

1. Check "When to step back" first. Then read the draft. Note who it is for (the person, their manager, a calibration committee) and whether it is praise, correction, or both.
2. Score it on the five dimensions below, 1 to 10 each.
3. List every violation of the rules, quoting the exact phrase.
4. If key facts are missing (no example, no outcome), ask up to three short questions. If the user cannot answer, rewrite with clearly marked placeholders like [date] or [outcome] instead of inventing facts.
5. Rewrite with all violations fixed. Keep the writer's voice and level of warmth. Write in the language the feedback was written in, and keep names, dates, and quotes exactly as given.
6. Re-score, counting only what the writer provided. A dimension whose content is a [placeholder] cannot score above 6. If any dimension is below 7 and the missing facts can be supplied, ask for them or rewrite again; if they cannot, say what is still missing instead of raising the score.

Never invent events, quotes, numbers, or outcomes. A sharp but fabricated example is worse than a vague true one.

## Sensitive content
Read the full skill on GitHub

Details

Skill name
stop-vague
License
MIT
Repo updated
26 October 2026

FAQ

What does the Stop Vague skill do?

Rewrites vague workplace feedback (performance reviews, 1:1 notes, peer feedback, promotion write-ups) into specific, behavioral, actionable feedback. Use when the user pastes feedback that sounds like "great job", "needs more ownership", "be more strategic", or asks to sharpen, fix, or score feedback before delivering it ("use stop-vague", "sharpen this feedback", "score this feedback").

How do I install the Stop Vague skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add sumanbukka/stop-vague --skill stop-vague. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Stop Vague popular?

It lives in sumanbukka/stop-vague, which has 5 GitHub stars and 0 forks.

Related skills

Story Master

5

idonafraid-create/story-master

Professional agent skill for story development and script doctoring. Active for writing novels (写小说), screenplays (剧本), or analyzing 7 key steps (七大步骤), 22 steps (22步情节), four-corner opposition (四角对立), moral arguments (道德议题/主题), symbol networks (象征网络), scene weaving (场景编排), and symphonic dialogue (交响式对白).

Writing & Content

Ste Writing

5

1fc0nfig/ste-writing

Rewrite prose (docs, READMEs, PR descriptions, error messages, release notes, comments, commit messages, changelogs - never code) into ASD-STE100 Simplified Technical English to remove "AI slop". Use when asked to make writing not sound like AI, make docs clear or plain, remove slop or fluff from text, enforce a controlled writing style, or write technical documentation that reads human. Two modes - strict (procedures, safety, error messages) and STE-flavored (general prose).

Writing & Content

Story Structuring

5

XueweiW-21/socratic-questioning-story-structure

苏格拉底式提问技能,帮助小说创作者(尤其是同人文作者)通过引导式对话梳理故事思路。适用于中短篇网络小说(2,000–50,000字)。当创作者想要梳理剧情、整理大纲、或理清故事结构时触发。触发短语包括:"帮我梳理剧情"、"我想写一篇文"、"帮我理思路"、"故事大纲"、"剧情结构"、"我有一个故事想法"等。当用户提及同人文、大纲、剧情梳理、起承转合,或希望在不让AI生成内容的前提下整理叙事结构时,也应触发此技能。

Writing & Content

Social Media Scraper

5

elbis330/social-media-scraper-skill

Skill that pulls and analyzes all data from social media posts. Fetches content from Instagram (reel, post, story), TikTok, Twitter/X and YouTube links. Collects all metadata including text, description, comments, like/share counts, date info, hashtags. Automatically transcribes with faster-whisper and applies visual analysis with Gemini Vision on posts containing video or audio. MANDATORY TRIGGERS: whenever a social media link is shared (instagram.com, tiktok.com, x.com, twitter.com, youtube.com, youtu.be), "read this tweet", "fetch this reel", "analyze this video", "look at this post", "what

Writing & Content

Wechat Article Studio

5

LostSirius/wechat-article-studio-skill

Creates or revises polished Chinese WeChat Official Account articles from briefs, notes, documents, reference posts, and image folders. Use when the user asks to write, humanize, typeset, beautify, preview, or prepare a 微信公众号/公众号 article; reduce AI-like prose; reproduce an editorial visual direction; process article images or slideshow GIFs; or generate paste-ready inline-style HTML. Covers evidence checking, voice matching, editorial rewriting, layout planning, image preparation, deterministic rendering, WeChat compatibility checks, and iterative quality review.

Writing & Content

Six Wise Minds

5

nightboy87/Six-Wise-Minds-Skill

Use this skill when the user needs help clarifying, stress-testing, comparing, or deciding a fuzzy issue through structured multi-perspective deliberation. Use for product decisions, writing topics, project choices, demand review, personal choices, career reflections, and other decisions where facts, emotions, risks, value, alternatives, and process all matter. Do not use for simple factual lookup, pure translation, pure rewriting, direct code execution, or as final medical/legal/financial/psychological advice.

Writing & Content

Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.