idea-refine
Skill1 starsChanged 46 days agoMITView on GitHub
把一个粗糙、未经推敲的想法(选题、点子、活动创意、立项想法),通过发散—收敛—交付三阶段打磨成一份可执行的一页纸方案(含方向四维对比、隐藏假设、Not Doing 清单与下一步行动)。当用户说"帮我打磨这个想法""我有个点子但没想清楚""帮我评估下这个选题/立项""活动策划先筛一筛""stress-test 我的计划"时使用。
62 other projects use a version of this.
Adopted by
Most recently taken up by
- addyosmani/agent-skillstheir own version, first seen Nov 14, 2026
- ishandutta2007/Awesome-Agent-Skillstheir own version, first seen Nov 8, 2026
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
- gopalparashar421/agent-skillstheir own version, first seen Nov 8, 2026
- celestialdust/achilles-skillstheir own version, first seen Nov 1, 2026
- steven123397/nexuskit-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use constraint-driven-development, observability-and-instrumentation and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
MrCipherSmithSkillconstraint-driven-development
Use when a project needs a persistent, measurable quality bar — starting a project without documented standards, 'set up constraints', or when coverage/perf/a11y thresholds get re-debated per-PR. Produces CONSTRAINTS.md with enforceable numbers, ratchets, and a guard against silent weakening. NOT for throwaway prototypes or a one-off CI setup.
Also in 16 projects that use this
HK-hubSkillobservability-and-instrumentation
Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting. Use when shipping any feature that runs in production and you need evidence it works. Use when production issues are reported but you can't tell what happened from the available data.
Also in 33 projects that use this
HK-hubSkilldeprecation-and-migration
Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when deciding whether to maintain or sunset existing code.
Also in 36 projects that use this
seikaikyoSkilldoubt-driven-development
對非平凡決策啟動新鮮 context 對抗審查(找碴不背書),在修正還便宜的時候抓出錯誤方向。適用:高風險改動(production、資安敏感邏輯、不可逆操作)、不熟的程式碼、要宣稱「這樣是安全的 / 可行的」之前。機械性操作與一行修改不適用。
Also in 41 projects that use this
OpenAISkillsecurity-best-practices
Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.
Also in 3 projects that use this
AnasX7Skillminimalist-ui
Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.
Also in 4 projects that use this
- +2 more from HK-hub
Other versions62 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 62
- addyosmani/agent-skills★ 118ksame name
- shashankswe2020-ux/whoop-mcp★ 181same name
- vinvcn/addyosmani-agent-skills-zh★ 46same name
- sampleXbro/agentsmesh★ 27same name
- jaskirat1616/grok-skills★ 22same name
- ishandutta2007/Awesome-Agent-Skills★ 21same name
- HK-hub/AgentSkills★ 6same name
- lza6/claw-code-tingfeng★ 5same name
- ddddjaak/ae-skills★ 4same name
- dzevs/zynk★ 4same name
52 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository28 other files it gives its agents.
- academic-polishingSkill
- analyze-claimsSkill
- brainstorm-specSkill
- code-reviewSkill
- contract-guardSkill
- data-storytellingSkill
- decision-questionnaireSkill
- doc-summarySkill
- execution-planSkill
- extract-wisdomSkill
- humanize-writingSkill
- interview-meSkill
- meeting-notesSkill
- ppt-outlineSkill
- prompt-designerSkill
- proposal-writerSkill
- resume-reviewSkill
- systematic-debuggingSkill
- teachSkill
- verification-before-completionSkill
- wechat-articleSkill
- xiaohongshu-comment-replySkill
- xiaohongshu-conversion-pathSkill
- xiaohongshu-copySkill
- xiaohongshu-magazineSkill
- xiaohongshu-profileSkill
- xiaohongshu-titleSkill
- xiaohongshu-topic-plannerSkill
The file
Files
想法打磨 · idea-refine
二次开发:本技能改编自 addyosmani/agent-skills 的 idea-refine(MIT License © 2025 Addy Osmani),在保留其核心方法论基础上,升级为「提示词 + 可执行 CLI」双形态。署名见本目录
NOTICE.md与仓库THIRD_PARTY_NOTICES.md。
这个技能做什么
把一个粗糙、未经推敲的想法——一个公众号选题、一个活动创意、一个产品立项点子、一个创业方向——通过结构化的发散与收敛思考,打磨成一份可以直接进入下一步(设计 / 立项 / 放弃)的一页纸方案。
核心是三阶段:
- 发散(打开):把原想法重述成一句 How Might We(HMW)问题;提 3–5 个锐化问题;用一组"透镜"各生成若干变体。
- 收敛(收口):把变体聚成 2–3 个方向;按用户价值 / 可行性 / 差异化做压力测试;显式列出隐藏假设。
- 交付(落纸):输出 Markdown 一页纸方案,必须含 Not Doing 清单及理由——明确这次不做什么、为什么不做。
一句话:不是帮你把想法夸大成计划,而是帮你把想法挤干水分、看清赌注,再决定要不要往前走。
典型适用场景(中文职场高频):
- 公众号 / 内容选题:一个模糊的选题方向,打磨成可写的角度与取舍;
- 活动策划:一个活动创意,筛出 2–3 个可执行方向并标出不做什么;
- 产品立项:一个功能 / 项目点子,在写 PRD 前先压力测试假设;
- 创业点子评估:一个方向,快速判断它是止痛药还是维生素;
- 方案选型前的想法筛选:多个候选想法,先收敛再投入资源。
输入要求
- 必填:一段想法描述——你现在脑子里那个还没说清楚的点子,越原始越好(可以是半句话、一段吐槽、一个截图思路)。
- 可选:背景与约束——面向谁、时间 / 预算 / 技术资源限制、之前试过什么、为什么是现在。
- 可选(CLI):
--lenses自定义发散透镜(默认 7 个:用户 / 商业 / 技术 / 时间 / 成本 / 风险 / 差异化,可按场景替换)。 - 信息不足时:不要替用户脑补,在方案里把缺失处标成"(待确认)",并在"下一步行动"里点明需要先补什么。
输出结构(模板见 scripts/templates/idea-refine.template.md)
一份一页纸方案,自上而下:
- 原始想法与重述(HMW):先原样复述用户的粗糙想法,再把它改写成一句 How Might We 问题——逼自己看清到底在解决谁的什么问题。
- 锐化问题(3–5 个):围绕"这到底为谁、成功长什么样、真实约束是什么、之前试过什么、为什么是现在"提出的关键问题;用户没答的,标(待确认)。
- 方向对比:把变体聚成 2–3 个方向,每个方向都必须过四维评估表——用户价值 / 可行性 / 差异化 / 风险,四维一格都不许空着。
- 推荐方向与理由 + 隐藏假设清单:选一个方向,说清为什么;紧接着逐条列出"我们赌它成立但还没验证"的假设,每条标(待确认)并附一句怎么验证。
- Not Doing 清单:明确这次不做什么——每条都必须带理由。这是整份方案最有价值的部分。
- 下一步行动:三选一——进入设计 / 进入立项 / 放弃(放弃需说明理由)。
工作流程
- 发散:拿到原始想法 → 用 HMW 重述 → 提 3–5 个锐化问题 → 用透镜(默认 7 个,或
--lenses指定)各生成若干变体。变体不求多,5–8 个想透的胜过 20 个肤浅的。 - 收敛:把有共鸣的变体聚成 2–3 个彼此有实质差异的方向(不是同一个主题的微调)→ 逐方向过用户价值 / 可行性 / 差异化 / 风险四维压力测试 → 显式说出每个方向"在赌什么、什么会杀死它、我们暂时选择忽略什么"。
- 交付:按输出结构组装一页纸方案;诚实、不捧场——想法弱就直说,但说得具体、带善意。
质量规则(必须遵守)
- 忠于想法、不脑补:只基于用户给出的想法与背景展开;用户没说的事实不编造,信息不足处一律标"(待确认)"。
- 四维评估不留空白:方向对比表里用户价值 / 可行性 / 差异化 / 风险四格必须逐格填写,不许留空或写"待定"了事。
- 隐藏假设必须显式列出:每条假设都要写成"我们赌 X 成立,但还没验证——怎么验证:Y"。跳过这一步等于没打磨。
- Not Doing 清单必须带理由:每条"不做"后面必须跟一句为什么不做;没有理由的 Not Doing 等于没写。
- 2–3 个方向,不要更多:方向之间必须有实质差异,不是换汤不换药。
- 做一个诚实的思考伙伴,不做捧场机器:想法弱要敢于说,并指出弱在哪;语气直接、有思考、略带一点挑战性,但不刻薄。
- 输出是一页纸,不是报告:控制篇幅,每节点到即止,不堆废话。
边界与异常处理
- 想法过于宽泛(如"我想做个 App")→ 先用锐化问题收窄,再开始发散;收不动的地方标(待确认)。
- 想法明显已被现有方案完美解决 → 在方向对比里如实指出,并在下一步行动建议"放弃或另找角度"。
- 用户只给一句话、没有背景 → 正常出方案,但把缺的背景全部进"隐藏假设"与"待确认"。
--lenses传入自定义透镜 → 用它替换默认 7 透镜做发散,不机械套用默认透镜。- 涉及代码库 / 既有项目 → 把现有架构与约束当作真实前提写进可行性评估,不脱离实际空想。
与脚本配合
- 批量 / 命令行场景:
scripts/draft_idea_refine.py(纯标准库,一条命令跑通);输入为想法描述文本(可含背景 / 约束),输出为一页纸方案 Markdown。 - 自定义透镜:
--lenses "付费意愿、渠道能力、政策合规"用顿号分隔。 - 自定义模板:复制
scripts/templates/idea-refine.template.md修改后使用。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

