Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/tashangkd/tashan-writing-system/research-output)<a href="https://agentmods.dev/skills/tashangkd/tashan-writing-system/research-output"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-writing-system/research-output/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/tashangkd/tashan-writing-system/research-output"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-writing-system/research-output.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 | $0.00097 | $0.09343 |
| Opus 5 | $0.00048 | $0.04672 |
| Sonnet 5 | $0.00019 | $0.01869 |
| Haiku 4.5 | $0.00010 | $0.00934 |
Grade A, and why
research-output 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.
This is a copy
100% identical to research-output — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 759 lines — stays where its author put it; the contents beside it link to each section on GitHub.
系统调研输出 Skill（research-output）v2.0
触发词：「调研」「系统调研」「研究一下」「帮我系统了解」「深度研究」「全景调研」「大量调研」「调研一下」+ 主题词 产出：REF-EXT 图文 Markdown → 保存到认知结构知识库 → 自动注册三处 ⚠️ 核心原则：关键词驱动 → 多轮迭代 → 读原文 → 知识网络 → 写稿
知识导航表（执行前必须理解的概念根）
| 层级 | 文档 | 需要理解的概念 |
|---|---|---|
| D0 认知根（必读） | _内部总控/认知结构/L0_大脑总地图.md |
调研成果的存放位置：K2外部参考（REF-EXT）存放在各L1维度的知识库子目录；调研前先确认目标维度 |
| D3 规范参考 | .cursor/rules/knowledge-integrity-rules.mdc（R2 NO_FABRICATION + R3 READ_FIRST） |
R2：调研结论必须有来源，禁止捏造；R3：读原文而非摘要（WebFetch优先于WebSearch） |
| D4 运行时数据 | _内部总控/认知结构/文档分类清单.md + 目标L1维度的 知识库/ 目录 |
注册目标：调研完成后必须注册到分类清单+知识图谱+L0总地图三处 |
核心概念速查： ① 调研产出 = K2 REF-EXT（外部知识汇编），不是L1框架（不代表郑总自己的思考） ② 读原文而非摘要（R3）：WebSearch只用于发现URL，WebFetch读取实际页面内容 ③ 注册三处是ceremony(K2)的强制步骤：文档分类清单 + 知识图谱 + L0总地图
触发判断（先执行）
IF 用户说「帮我调研/大量调研/全景调研/全面调研/研究一下/调研一下/系统了解/深入了解/搜一下/查一下（需要结构化知识产出时）」
AND 有明确的调研对象（不是临时问一个问题/不是空答）
→ 触发本 Skill（mode=research，从 Phase 0 开始）
IF 用户说「完善[已有文档]/给[已有文档]加图/补充[已有文档]/这个文档缺图/按规范完善」
AND 明确指向某个已存在的知识库文档（REF-EXT）
→ 触发本 Skill（mode=improve，从 Phase 7 开始）
不触发（优先判断）：
- 「搜索一下/查一下/找一下」→ 临时查找，直接回答，不触发
- 「解释一下/这个是什么意思」→ 单点解释，不触发
- 「帮我调试/排查错误」→ 不触发
- 「研究一下/帮我研究」+ 后接「报错/错误/bug/为什么/怎么解决/代码问题/调试/排查」→ 调试场景，不触发
主题词不明确时：询问「你想调研的具体主题是什么？」等用户回答后触发。
组合场景：若用户同时含写作类关键词（「调研X然后写成文章/推文」）
→ 告知「本 Skill 先产出调研知识库文档，文章写作请完成本 Skill 后另触发 general-article-writer/wechat-article-writer」
→ 先执行本 Skill 完整流程
D0：认知根确认（所有调研前必做，在三原则之前）
调研不是凭空获取外部知识，而是用认知结构作为框架来组织外部信息。 开始任何调研前，先回答：这个主题在郑总的认知结构（L1文档）里有没有相关内容？
快速读取
_内部总控/认知结构/L0_大脑总地图.md扫描相关维度，若找到相关 L1 文档： → 先读该文档核心框架，以此作为「调研结果的落点」 → 调研产出将以 REF-EXT 形式补充到对应 L1 维度知识库若未找到相关 L1 文档： → 正常执行调研，调研完成后评估是否有 L2 碎片价值
调研架构前置三原则（执行前必读）
执行任何调研任务前，先完成「调研骨架」——这三条原则是 Phase 1-4 的提炼，违反任意一条会导致调研表面化：
原则1「关键词图谱先行」：列出 5-10 个种子词 → 扩展同义词/上下位词 → 按主题聚类 → 形成搜索骨架 （跳过此步骤 = 后续搜索在随机游走，无法保证覆盖完整性；对应 Phase 1）
原则2「WebFetch 读原文强制」：WebSearch 摘要只用于发现 URL，不可直接引用作为知识来源
正确路径：WebSearch 发现 URL → WebFetch 读原文 → 提炼知识点 违反 = 知识节点来自搜索引擎摘要，可靠性无法保证（对应 Phase 2 读原文标准）
原则3「知识网络三层合成」：核心（直接回答问题的）/ 中间（支撑背景）/ 外围（相关但非核心） 最终产出按三层组织，来源层级标注清楚（对应 Phase 4）
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 · 759 lines · 97 tokens per session scan A 64b0229fd3ad
research-output is a skill published in the GitHub repository TashanGKD/tashan-writing-system (2 stars, last pushed 5mo ago), licensed MIT. It adds 97 tokens to every session and 9,343 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to research-output, differing in 0 lines, and is treated as a copy.
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…