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 AgenticAIPlan/AgenticAISkills --skill org-researchgit clone --depth 1 https://github.com/AgenticAIPlan/AgenticAISkillsWrote 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/agenticaiplan/agenticaiskills/org-research)<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/org-research"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/org-research/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/agenticaiplan/agenticaiskills/org-research"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/org-research.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 | $0.00100 | $0.03977 |
| Opus 5 | $0.00050 | $0.01988 |
| Sonnet 5 | $0.00020 | $0.00795 |
| Haiku 4.5 | $0.00010 | $0.00398 |
Grade A, and why
org-research 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 10d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
单位调研 Pipeline Skill
本 Skill 不是普通报告生成器,而是一个调研流水线。它必须先产出关键事实的证据(来源链接),再写报告;必须先过链接审计和事实准入,再进入成稿,以尽量确保关键事实有可核查来源,有助于在交流前深入了解对方机构的情况和业务情况;必须通过 Reviewer 终审,才能标记为正式报告。
业务价值
本 Skill 的核心价值不只是生成机构背景报告,而是帮助各领域业务同学在与各类客户会议交流前,可以实现快速、可靠地理解一个机构的管理情况和业务情况。它面向会前沟通、合作研判、客户拜访、政府事务、产业研究和跨团队信息同步等场景,提供两类关键价值:
- 快速建立机构认知:通过基本介绍、主要职责、隶属关系图示、内设机构、负责人、近期动态和业务相关部门等固定章节,帮助用户快速看清机构定位、权责边界、组织关系和沟通切入点。
- 显著降低模型幻觉风险:通过候选来源、原子事实、链接审计、事实准入和 Reviewer 终审形成完整证据链,要求关键事实均可回到公开来源复核,避免无来源结论、虚假链接和模型记忆进入正式报告。
在此基础上,本 Skill 进一步解决机构调研中最容易反复出现的五类问题:
- 报告内容不可查证,无法判断是大模型幻觉还是真实信息。
- 虚假链接、首页链接、频道页链接进入正文,导致报告无法复核。
- 机构简介、职能职责、组织架构、负责人信息混入无来源判断。
- 把业务栏目、项目、活动新闻误写成现行内设机构或稳定隶属关系。
- 多单位或多轮调研时格式不一致,后续同事无法沿证据链继续补查。
目标交付不是“看起来完整”的长报告,而是可核查、可降级、可复用的会前机构情报:每个关键事实都能回到候选来源、原子事实、链接审计和事实准入表中复核,尽量确保关键事实真实、可核查,便于业务同学基于这些公开事实做出业务判断,以及基于有可能开展合作的方向,可以方便快捷地通过备注的来源链接进一步深入了解,以寻找业务合作机会。
业务收益:
- 提高调研效率:将官网检索、来源筛选、事实抽取、链接检查和报告成稿固化为同一套流程,减少从零搭建调研框架的时间。
- 降低协作成本:不同同事产出的报告使用相同字段、附录和准入标准,便于接力补查、复用和交叉复核。
- 支持业务判断:把主管关系、组织架构、负责人、近期动态和业务相关部门放在同一证据链中,帮助判断沟通路径、审批链条和合作切入点。
- 提升风险控制:通过事实准入和 Reviewer 终审,显式区分准入事实、待核实线索和剔除信息,避免无来源结论进入正式材料。
适用场景
当用户要求了解、拜访、会见、调研某个政府单位、企事业单位、研究机构、协会、基金会、科技馆、智库或其他机构时使用。
不适用场景 / 边界
本 Skill 保持独立完整,但不应被泛化为所有研究任务。以下情况不使用或必须降级:
- 只要求政策、行业或议题背景,不需要围绕具体单位建立事实链。
- 要求无来源内部判断、非公开信息、私人信息或未公开负责人分工。
- 要求直接生成合作建议、商业方案或沟通策略,但缺少单位事实证据;此时应先完成机构调研,再另行生成建议。
- 要求法律、投资、审计、合规结论等高风险判断;本 Skill 只提供公开事实背景和待核实线索。
- 只有主站首页、搜索结果、登录页、无法访问页面或无关页面时,不生成正式报告。
输入
单位名称:必填;可一次输入多个单位。会议主题:可选;用于排序重点,不得用于创造无来源事实。单位类型:可选;政府机构 / 事业单位 / 企业 / 社会组织 / 自动判断。交付形式:可选;完整报告 / 简版正文 + 完整附录 / 仅输出证据表。默认完整报告。
默认执行完整高可靠调研流程。除非用户明确要求简版或只要证据表,否则不得省略候选来源、原子事实、链接审计、事实准入和 Reviewer 终审。
Step 0:输入与默认假设
若用户未提供完整信息,不要阻塞执行,但必须在报告开头标注默认假设:
- 会议主题缺失:默认做通用会前背景调研。
- 单位类型缺失:先自动判断,并在候选来源表中说明判断依据。
- 交付形式缺失:默认完整报告。
只有当用户目标会影响检索范围且无法合理默认时,才提出简短澄清问题。
最小合格交付标准
标记为正式报告前,必须同时满足:
- 至少覆盖官网或官方介绍页、职责或业务说明、机构设置或组织关系、负责人信息、近期动态五类检索方向;确无公开来源时必须写入缺口说明。
- 每个进入正文的关键事实都能在原子事实证据表中找到对应行。
- 每个正文链接都通过链接审计,并在事实准入表中标记为
准入。 - 附录 A-E 齐全;如果用户要求简版正文,附录可另存为单独文件,但不得省略。
- Reviewer 终审不存在未修复
error。
What ships with it
18 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.
- assets/atomic-evidence-template.md 829 B
- assets/candidate-sources-template.md 791 B
- assets/fact-admission-template.md 533 B
- assets/link-audit-template.md 798 B
- assets/report-template.md 4.6 KB
- assets/reviewer-output-template.md 507 B
- references/common-failure-cases.md 3.4 KB
- references/evidence-gate.md 1.7 KB
- references/example-good-report.md 1.7 KB
- references/example-nda-good-report.md 7.7 KB
- references/final-review-checklist.md 3.6 KB
- references/leader-research.md 1.2 KB
- references/link-audit.md 1.4 KB
- references/org-structure.md 5.8 KB
- references/recent-news.md 904 B
- references/search-paths.md 2.2 KB
- references/source-rules.md 2.1 KB
- scripts/link_audit.py 6.6 KB runs code
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.
- 10d ago First seen · 258 lines · 100 tokens per session scan A 384075b3cfd2
org-research is a skill published in the GitHub repository AgenticAIPlan/AgenticAISkills (11 stars, last pushed 3mo ago), licensed MIT. It adds 100 tokens to every session and 3,977 once invoked, about $0.0005 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
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…