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 jinhanbuilds/brief-me --skill brief-megit clone --depth 1 https://github.com/jinhanbuilds/brief-meWrote 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/jinhanbuilds/brief-me/brief-me)<a href="https://agentmods.dev/skills/jinhanbuilds/brief-me/brief-me"><img src="https://agentmods.dev/badge/skills/jinhanbuilds/brief-me/brief-me/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/jinhanbuilds/brief-me/brief-me"><img src="https://agentmods.dev/badge/skills/jinhanbuilds/brief-me/brief-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00121 | $0.02029 |
| Opus 5 | $0.00060 | $0.01014 |
| Sonnet 5 | $0.00024 | $0.00406 |
| Haiku 4.5 | $0.00012 | $0.00203 |
Grade A, and why
brief-me 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 11d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brief Me
把 AI 的一墙分析,转化为一份结论先行、可视化、可交互的顾问式汇报。让 AI 承担组织复杂度,让真正需要拍板的人更快看清局面、参与判断并作出更高质量的决定。
核心使命
- 像一名准备充分的咨询顾问一样提炼材料:先理解受众和判断任务,再筛选、排序并建立清晰 storyline,不把未经组织的分析重新交给用户。
- 把可视化作为理解复杂局面的核心能力。用层级、版式、关系图、数据图表、因果、时序或情景表达,让重要差异与联系一眼可见。
- 把交互作为决策者参与判断的核心能力。让用户比较、深入、改变条件并表达自己的意见,而不只是阅读 AI 的结论。
- 把更高质量的人类判断作为成功标准。页面、图表和控件只有在降低理解成本或推进决定时才有价值。
- 直接消费已有分析。材料不足以支持任何判断时,指出缺口或补足最小结构,不擅自扩张为新的研究项目。
工作流程
1. 恢复本次汇报任务
弄清真正需要作出判断的人是谁、他此刻需要理解或回应什么、为什么现在处理、会影响什么,这次希望得到决定、倾向、修改、批准还是下一项验证,以及明确不连带决定什么。
材料杂乱、判断任务隐含或存在多个关联问题时,读取 references/decision-context.md。只恢复会改变顾问主线、视觉表达、交互设计或用户回应的信息;未知时保留未知,不为填满结构而猜测。
2. 独立设计人的判断路径
在选择页面形式前,先设计一次认知旅程:决策者进入时知道什么,最先需要看见什么,接下来最可能追问或反对什么,哪些依据必须能够深入,在哪里需要比较或改变条件,怎样表达预设之外的意见,以及离开时应形成决定、倾向、反馈还是下一项验证。
这一步只产生适合这个人的判断路径,不产生固定线框、页面目录或组件清单。
3. 提炼顾问式 storyline
先完成综合,再设计页面:
- 找出最能改变判断的结论、冲突、取舍、关系或数据;
- 决定首屏应该先让用户看见什么;
- 用结论先行和清晰层级组织主张与理由;
- 把背景、来源和细节放进可继续深入的位置;
- 让叙事顺序适配用户真正需要的回应。
用户要建议时,尽早呈现当前判断、最强理由和成立条件;用户要独立判断时,先呈现关键差异、取舍和影响,避免不必要的推荐锚定;用户已有倾向时,优先检验最可能改变决定的条件;多个问题相互影响时,先建立足够的整体局面,再一次处理一个实质判断。
不要把输入材料的章节顺序直接变成页面目录。
4. 选择视觉、交互与辅助能力
完成前三步后,再读取 references/briefing-design.md,选择最能降低当前决策负担的视觉形式、交互方式和辅助能力。
- 视觉必须改变理解: 至少让一项原本藏在长文字里的决定性关系、差异、量级、因果、时序或影响明显更容易理解。视觉可以是层级、空间、路线、情景或图表;删掉它后如果理解没有变差,它就不算有效视觉。
- 交互必须推进判断: 至少让用户完成一次有意义的比较、深入、条件修改、影响查看或回应。删掉控件后如果用户的理解和判断能力没有变差,它就不算有效交互。
- 始终保留人的主体性: 提供预设选项之外的自由意见入口,不把用户限制在 AI 给出的按钮里。
- 变化必须诚实一致: 只有确定性逻辑和现有数据支持时才动态重算;需要新推理、研究或授权时,收集变化,标记受影响的判断,并明确返回对话继续处理。
默认交付可直接打开的自包含 HTML;复杂度确有需要时再使用小型静态项目。根据当前任务选择最少但足够的前端设计、数据可视化、演示叙事、可访问性或数据处理能力,不固定依赖某个外部 Skill。
5. 构建、打开并走查真实路径
实际打开界面,沿以下路径完成走查:
看见局面
→ 理解顾问式主线
→ 看清关键关系、数据和取舍
→ 追到必要依据
→ 比较或改变条件
→ 输入自己的意见或方案
→ 看见一致变化,或明确哪些内容需要重新判断
→ 复制或导出当前判断与反馈,带回对话
检查首屏、核心视觉、至少一次有效交互、自由意见入口、窄屏和键盘状态。反馈交接至少保留用户改变的条件、当前选择或倾向、自由意见,以及哪些结论已经确定性更新、哪些需要重新推理。不要把页面中的选择或摘要表述成已经正式批准、执行或写回外部系统。
必须解决的问题
每次交付都要回答以下问题,但不要把它们固定成页面章节:
- 主线: 用户能否迅速理解正在处理什么、当前最重要的判断是什么?
- 视觉: 哪些关系、差异、量级、因果、时序或影响值得被看见?
- 交互: 用户需要比较、深入、改变什么,怎样表达自己的判断?
- 依据: 支撑主张的信息能否按需追溯,事实与推断是否诚实区分?
- 变化: 条件或意见改变后,相关结论和影响是否保持一致?
What ships with it
8 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.
- agents/openai.yaml 298 B
- evals/cases/condition-change.yaml 2.1 KB
- evals/cases/no-decision-boundary.yaml 1.1 KB
- evals/cases/wall-of-analysis.yaml 3.3 KB
- evals/eval.yaml 531 B
- evals/fixtures/scripts/check-briefing.mjs 2.6 KB runs code
- references/briefing-design.md 5.2 KB
- references/decision-context.md 3.6 KB
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.
- 11d ago First seen · 115 lines · 121 tokens per session scan A c01b454a094d
brief-me is a skill published in the GitHub repository jinhanbuilds/brief-me (35 stars, last pushed 18d ago), licensed MIT. It adds 121 tokens to every session and 2,029 once invoked, about $0.0006 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
strategy-consulting-visualization
Use when turning any content into clear, professional visualizations - board slides, reports, proposals, research summaries, training materials, technical diagrams, infographics, process flows, timelines, benchmarks, waterfall charts, or data-backed visual specs for any audience.
information-ui
Turn a fully grounded answer into an interactive Fify information view when comparison, planning, chronology, tracking, structured explanation, decision support, or editable state materially improves the answer. Use when the user tags @Fify or explicitly asks for an interactive view, and conservatively for naturally…
consulting-deck
Create, revise, and audit executive-ready strategy-consulting presentations as native, editable PowerPoint files. Use when turning topics, text, Markdown, Word, PDF, spreadsheets, CSV data, URLs, research, or an existing PPTX into a board, client, strategy, transformation, market-analysis, or McKinsey-style consulting…
html-ppt-zhangzara-mat
A margin-recovery diagnosis for a regional grocery chain — the governing thought, the driver tree, the priorities, and the roadmap. Built as a decision-grade consulting deck for client sponsor, steering committee.
auto-research
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.
dashboard-design
Use this skill first when the user wants to design or plan a dashboard, especially Vizro dashboards. Enforces a 3-step workflow (requirements, layout, visualization) before implementation. Activate when the user asks to create, design, or plan a dashboard. For implementation, use the dashboard-build skill after…