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 keyelifeai/keye-open-skills --skill storm-deepresearchgit clone --depth 1 https://github.com/keyelifeai/keye-open-skillsWrote 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/keyelifeai/keye-open-skills/storm-deepresearch)<a href="https://agentmods.dev/skills/keyelifeai/keye-open-skills/storm-deepresearch"><img src="https://agentmods.dev/badge/skills/keyelifeai/keye-open-skills/storm-deepresearch/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/keyelifeai/keye-open-skills/storm-deepresearch"><img src="https://agentmods.dev/badge/skills/keyelifeai/keye-open-skills/storm-deepresearch.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 | $0.00056 | $0.01094 |
| Opus 5 | $0.00028 | $0.00547 |
| Sonnet 5 | $0.00011 | $0.00219 |
| Haiku 4.5 | $0.00006 | $0.00109 |
Grade A, and why
storm-deepresearch 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.
What it actually says
STORM Deep Research
这是 Keye 编写的多视角研究工作流，受 Stanford OVAL Lab 的 STORM 研究启发。它不是 Stanford STORM 项目的官方实现，也不复现该项目的软件流程。方法归属与链接见“来源与边界”。
开始前
- 明确研究问题、使用者、决策场景和时间范围。
- 询问是否允许联网搜索；未获允许或网络不可用时，将证据状态标为“待核验”。
- 对医疗、法律、投资等高风险主题说明输出仅用于研究整理，并建议由合格专业人士复核。
- 不把模型记忆当作来源，不虚构引用、数据或共识。
Step 1：多视角扫描
按问题选择 4 至 6 个彼此有区分度的视角。默认候选包括：
- 实践者：日常约束、真实流程与失败模式。
- 学术研究者：可重复证据、研究设计与外推限制。
- 怀疑论者：最强反论点和被忽略的反例。
- 经济与激励视角：受益者、成本承担者和制度激励。
- 历史视角：相似案例、条件差异和演变路径。
- 受影响群体：不同角色承担的收益、风险和不可逆影响。
每个视角输出：核心立场、最强证据需求、关键假设、独特问题。没有来源支持时写“假设”或“待核验”，不要写成事实。
Step 2：矛盾图
把视角之间的关系整理为：
- 直接冲突：具体主张、适用条件和冲突原因。
- 证据缺口：哪些结论缺少一手数据或高质量研究。
- 可化解问题：哪个问题一旦回答，最能缩小不确定性。
- 暂时共识：多方在什么边界条件下同意。
- 盲区：没有被任何视角充分覆盖的人群、时间尺度或副作用。
不要用“多数视角同意”代替证据质量判断。
Step 3：证据搜索
联网搜索获准时，从矛盾图提取 2 至 5 个可验证查询：
- 争议最大的因果或趋势主张；
- 盲区和前沿问题；
- 会改变决策的关键参数。
优先使用论文原文、政府和监管机构、标准组织、官方数据、项目官方文档。每条证据记录标题、发布者、日期、URL、支持或挑战的主张，以及适用限制。找不到可靠证据时保留“不确定”，不要降低来源标准补数。
Step 4：综合简报
按以下顺序输出：
- 决策摘要：研究问题、当前结论和最重要的不确定性。
- 关键发现：每条标明证据强度、支持与挑战视角。
- 矛盾与边界：哪些结论只在特定条件下成立。
- 行动选项：可逆动作、观察指标和停止条件。
- 待核验清单：缺失数据、负责人和下一次复核触发点。
Step 5：自我复核
逐条检查：
- 引用是否真实存在并支持相邻主张。
- 事实、推断、观点和建议是否清楚分开。
- 是否遗漏受影响群体或反例。
- 是否把相关性写成因果性。
- 哪条结论最弱，需要什么证据才能提高可信度。
- 新证据出现时，哪些结论必须重新评估。
最后给出高、中、低三档证据强度，不使用看似精确但没有量表依据的数字评分。
来源与边界
- 论文：Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models
- 官方代码：stanford-oval/storm
本 Skill 只借鉴多视角知识整理与证据复核的研究思路。Keye 负责本仓库中的工作流文字；Stanford OVAL Lab 不负责维护、验证或认可本 Skill。
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 · 86 lines · 56 tokens per session scan A 19d95247ba82
storm-deepresearch is a skill published in the GitHub repository keyelifeai/keye-open-skills (10 stars, last pushed 12d ago), licensed MIT. It adds 56 tokens to every session and 1,094 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…