Qiushi-Skill is a collection of agent skills that turn dialectical materialist and practical philosophy into methods for investigating problems, identifying their central contradiction, testing conclusions, and continuing work. It is intended to guide AI agents through analysis and task execution. The catalogue entries are its skills, commands, hook, plugin, and agent components.
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 HughYau/qiushi-skill --skill investigation-firstgit clone --depth 1 https://github.com/HughYau/qiushi-skillWrote 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/hughyau/qiushi-skill/investigation-first)<a href="https://agentmods.dev/skills/hughyau/qiushi-skill/investigation-first"><img src="https://agentmods.dev/badge/skills/hughyau/qiushi-skill/investigation-first/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/hughyau/qiushi-skill/investigation-first"><img src="https://agentmods.dev/badge/skills/hughyau/qiushi-skill/investigation-first.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 | $0.00160 | $0.00918 |
| Opus 5 | $0.00080 | $0.00459 |
| Sonnet 5 | $0.00032 | $0.00184 |
| Haiku 4.5 | $0.00016 | $0.00092 |
Grade A, and why
investigation-first 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 4d 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
调查研究
"没有调查，没有发言权。" —— 《反对本本主义》
调查研究是落实「实事求是」的入口：不是为既定结论找材料，而是让事实规定判断。
用 / 不用
用：
- 要做决策，但对实际情况了解不够
- 面对陌生的代码库、系统或领域
- 别人的方案听起来合理，但你不清楚其适用条件
- 发现自己在用"应该是""一般来说"作答
不用：
- 已经调查过，现在是执行阶段
- 用户已提供完整上下文和决策依据
- 答案可以直接跑一下验证，跑比查快
操作规程
- 一句话写出调查目的：「我要弄清楚的是：……」。没有目的的调查是漫游。
- 列调查提纲（checkbox），覆盖四个面：
- 现状：现在是什么样（读源码、配置、数据，不只看文档）
- 历史：为什么变成这样（git log、blame、变更记录）
- 关联：牵涉哪些约束（接口、依赖、调用方、部署环境）
- 多方：有哪些不同说法（文档 vs 代码 vs 运行结果 vs 用户描述）
- 亲自接触第一手材料：直接读、直接跑、直接看日志。二手总结只能作线索，不能作证据。
- 边查边记，分三栏：每条发现标注来源；把"看到的"和"推出来的"分开。
- 输出调查结论（模板见下）。结论必须先于任何行动方案；不得边查边给方案。
- 事实与预期不符时，改判断，不改事实。查不清的，诚实写"未知"。
输出模板
调查目的：……
调查范围：读了 …… / 跑了 …… / 问了 ……
已核实的事实（附来源）：
- ……（来源：文件:行 / 命令输出 / 日志）
合理推断（说明推理链）：
- ……（因为 …… 所以 ……）
未知 / 存疑：
- ……（需要 …… 才能确认）
调查结论：
- 现状是：……
- 关键约束是：……
- 我原来不知道、现在知道的是：……
- 基于以上，我的判断是：……（置信度：高 / 中 / 低）
纪律
- 禁止在"未知"栏非空且关系到结论时下定论：要么补查，要么把不确定性写进结论。
- 禁止走马观花：只看目录结构和 README 就总结的，不算调查。
- 调查有预算：先写提纲，按提纲查完即止；发现新的大问题时另开一轮，而不是无限扩张。
交接
- 调查揭示多头矛盾、抓不住重点 →
contradiction-analysis - 结论已形成、需要验证 →
practice-cognition - 范围大、可分头查 → 派遣
investigator子 agent 并行调查，主线只汇总三栏
原著依据：original-texts.md
What ships with it
1 file 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.
- 4d ago Changed · -76 lines · +56 tokens per session 8acf90776bd0
- 12d ago First seen · 149 lines · 104 tokens per session scan A ca338d720e29
investigation-first is a skill published in the GitHub repository HughYau/qiushi-skill (3,774 stars, last pushed 5d ago), licensed MIT. It adds 160 tokens to every session and 918 once invoked, about $0.0008 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
pentest-playbook
7-phase pentest pipeline from passive recon to exploitation.
to-issues
A planning aid that breaks a PRD or technical specification into small implementation issues, each covering a complete, demonstrable piece of work.
listenhub-tts
A text-to-speech tool that uses the ListenHub service to turn written text into audio, including short recordings, multi-speaker scripts, and long-form streamed speech.
article-icons
A tool that adds static inline SVG icons from itshover.com to Markdown, HTML, and similar articles.
ship-it
A GitHub workflow for finishing an implemented issue: commit the relevant changes, push a branch, create a pull request, merge it, and close the issue. GitHub is a service for hosting code and reviewing changes, and a pull request is a proposed change for review.
fix-pr-review-loop
Use when the user asks to fix a PR review and drive it to approval autonomously — "fix the PR review and loop until approved", "fix-pr-review-loop", "keep addressing review comments until this PR is approved". Takes an optional PR number/URL (defaults to the current branch's PR). Repeatedly calls fix-pr-review, waits…