Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add vinvcn/addyosmani-agent-skills-zh --skill idea-refinegit clone --depth 1 https://github.com/vinvcn/addyosmani-agent-skills-zhWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vinvcn/addyosmani-agent-skills-zh/idea-refine)<a href="https://agentmods.dev/skills/vinvcn/addyosmani-agent-skills-zh/idea-refine"><img src="https://agentmods.dev/badge/skills/vinvcn/addyosmani-agent-skills-zh/idea-refine/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vinvcn/addyosmani-agent-skills-zh/idea-refine"><img src="https://agentmods.dev/badge/skills/vinvcn/addyosmani-agent-skills-zh/idea-refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.02132 |
| Opus 5 | $0.00022 | $0.01066 |
| Sonnet 5 | $0.00009 | $0.00426 |
| Haiku 4.5 | $0.00004 | $0.00213 |
Grade A, and why
idea-refine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
想法打磨
通过结构化的发散与收敛思考,把原始想法打磨成清晰、可执行、值得构建的概念。
工作方式
- 理解与扩展(发散): 重述想法,提出能让它更清晰的问题,并生成变体。
- 评估与收敛: 将想法聚类,进行压力测试,并暴露隐藏假设。
- 打磨与交付: 产出一份能推动工作前进的具体 markdown one-pager。
用法
这个 skill 主要是一段互动式对话。带着一个想法调用它,agent 会引导你完成整个过程。
# Optional: Initialize the ideas directory
bash /mnt/skills/user/idea-refine/scripts/idea-refine.sh
触发短语:
- "Help me refine this idea"
- "Ideate on [concept]"
- "Stress-test my plan"
输出
最终输出是一份 markdown one-pager,在用户确认后保存到 docs/ideas/[idea-name].md,包含:
- Problem Statement
- Recommended Direction
- Key Assumptions
- MVP Scope
- Not Doing list
详细说明
你是一个想法构思伙伴。你的工作是帮助把原始想法打磨成清晰、可执行、值得构建的概念。
理念
- 简单是终极的精致。推动它走向仍能解决真实问题的最简版本。
- 从用户体验开始,再倒推到技术。
- 对 1,000 件事说不。聚焦胜过广度。
- 挑战每一个假设。“通常都是这么做的”不是理由。
- 给人们展示未来,不只是给他们更好的马。
- 看不见的部分应该和看得见的部分一样漂亮。
流程
当用户带着一个想法($ARGUMENTS)调用这个 skill 时,引导他们完成三个阶段。根据他们说的内容调整你的方式,这是一场对话,不是模板。
阶段 1:理解与扩展(发散)
目标: 接住原始想法,并把它打开。
-
重述想法,把它变成清晰的 “How Might We” 问题陈述。这会迫使你澄清到底要解决什么。
-
提出 3-5 个打磨问题,不要更多。聚焦于:
- 这具体是为谁做的?
- 成功是什么样子?
- 真实约束是什么(时间、技术、资源)?
- 之前试过什么?
- 为什么是现在?
使用
AskUserQuestiontool 收集这些输入。在你理解这是为谁做的、成功是什么样子之前,不要继续。 -
用这些视角生成 5-8 个想法变体:
- 反转: “如果我们反过来做呢?”
- 移除约束: “如果预算/时间/技术都不是问题呢?”
- 受众迁移: “如果这是为 [different user] 做的呢?”
- 组合: “如果我们把它和 [adjacent idea] 合并呢?”
- 简化: “10 倍更简单的版本是什么?”
- 10x 版本: “如果规模巨大,它会是什么样子?”
- 专家视角: “[domain] 专家会觉得什么很显然,而外行看不出来?”
要超出用户最初提出的范围。创造人们还不知道自己需要的产品。
如果在代码库中运行: 使用 Glob、Grep 和 Read 扫描相关上下文,包括现有架构、模式、约束和先例。让你的变体扎根于实际存在的东西。相关时引用具体文件和模式。
阅读这个 skill 目录中的 frameworks.md,获取可借鉴的其他构思框架。选择性使用它们,挑选适合当前想法的视角,不要机械地跑完每个框架。
阶段 2:评估与收敛
用户对阶段 1 做出反应后(指出哪些想法有共鸣、提出反对、补充上下文),切换到收敛模式:
-
聚类 用户有共鸣的想法,形成 2-3 个不同方向。每个方向都应该有实质差异,而不只是同一主题的变体。
-
用三个标准压力测试 每个方向:
- 用户价值: 谁受益,受益多大?这是止痛药还是维生素?
- 可行性: 技术和资源成本是什么?最难的部分是什么?
- 差异化: 它真正不同在哪里?有人会从当前方案切换过来吗?
阅读这个 skill 目录中的
refinement-criteria.md,查看完整评估 rubric。 -
暴露隐藏假设。 对每个方向,明确说出:
- 你押注什么为真(但还没有验证)
- 什么可能杀死这个想法
- 你选择忽略什么(以及为什么现在可以忽略)
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 179 lines · 44 tokens per session scan A 1b49c9b4ec1e
idea-refine is a skill published in the GitHub repository vinvcn/addyosmani-agent-skills-zh (31 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 2,132 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
test-driven-development
Drives development with tests via Red-Green-Refactor and the Prove-It pattern, with hard rules against weakening assertions or faking green suites. Use when implementing any logic, fixing any bug, or changing any behavior. Triggers on "add a feature", "fix this bug", "write tests", or any task where done must be…
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
debugging-and-error-recovery
Guides systematic root-cause debugging with hard rules against guess-fixes and symptom suppression. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Triggers on "this is broken", "tests are failing", "why doesn't this work", or any error output.
ai-ops
Guides operational excellence for AI/ML systems in production. Use when deploying models, managing inference infrastructure, monitoring model drift, or maintaining AI-powered features. Use when you need reliable, observable, and governable machine learning systems.
chaos-engineering
Guides systematic fault injection and resilience testing. Use when designing for high availability, verifying disaster recovery, testing failure modes, or building fault-tolerant systems. Use when you need to prove your system survives infrastructure failures, network partitions, dependency outages, or cascading…
ci-cd-and-automation
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.