Root Cause Investigation
garrytan/gstack
Debugs in four phases (investigate, analyze, hypothesize, implement) under one rule: no fix is made until the root cause is found.
调查研究：在下判断、做决策、给建议之前，先用第一手材料弄清现状，产出「事实 / 推断 / 未知」三栏调查结论。当上下文不完整、证据薄弱、领域陌生、用户说"先别动手"、或你发现自己在凭印象作答时触发；已充分调查后的执行阶段不要重复触发。
MITAuto-check passed
Install Investigation First
$ npx skills add HughYau/qiushi-skill --skill investigation-first -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install HughYau/qiushi-skill investigation-first --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/HughYau/qiushi-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/investigation-first .claude/skills/investigation-first && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "investigation-first" agent skill from https://github.com/HughYau/qiushi-skill/tree/main/skills/investigation-first into .claude/skills/investigation-first/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigation-first", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/HughYau/qiushi-skill/tree/main/skills/investigation-firstType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add HughYau/qiushi-skill --skill investigation-first -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install HughYau/qiushi-skill investigation-first --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HughYau/qiushi-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/investigation-first .agents/skills/investigation-first && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "investigation-first" agent skill from https://github.com/HughYau/qiushi-skill/tree/main/skills/investigation-first into .agents/skills/investigation-first/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigation-first", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add HughYau/qiushi-skill --skill investigation-first -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install HughYau/qiushi-skill investigation-first --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HughYau/qiushi-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/investigation-first .cursor/skills/investigation-first && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "investigation-first" agent skill from https://github.com/HughYau/qiushi-skill/tree/main/skills/investigation-first into .cursor/skills/investigation-first/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigation-first", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/HughYau/qiushi-skill.git --path skills/investigation-first--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add HughYau/qiushi-skill --skill investigation-first -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install HughYau/qiushi-skill investigation-first --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HughYau/qiushi-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/investigation-first .gemini/skills/investigation-first && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "investigation-first" agent skill from https://github.com/HughYau/qiushi-skill/tree/main/skills/investigation-first into .gemini/skills/investigation-first/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigation-first", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install HughYau/qiushi-skill investigation-firstInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add HughYau/qiushi-skill --skill investigation-first -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/HughYau/qiushi-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/investigation-first .github/skills/investigation-first && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "investigation-first" agent skill from https://github.com/HughYau/qiushi-skill/tree/main/skills/investigation-first into .github/skills/investigation-first/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigation-first", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add HughYau/qiushi-skill --skill investigation-first -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install HughYau/qiushi-skill investigation-first --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HughYau/qiushi-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/investigation-first .opencode/skills/investigation-first && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "investigation-first" agent skill from https://github.com/HughYau/qiushi-skill/tree/main/skills/investigation-first into .opencode/skills/investigation-first/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigation-first", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
investigation-first- GitHub stars
- 3.8k
- Token cost
- ~425 tokens
- SKILL.md length
- 58 words
- Files
- 2
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- MIT
At a glance
调查研究：在下判断、做决策、给建议之前，先用第一手材料弄清现状，产出「事实 / 推断 / 未知」三栏调查结论。当上下文不完整、证据薄弱、领域陌生、用户说"先别动手"、或你发现自己在凭印象作答时触发；已充分调查后的执行阶段不要重复触发。
- Works in 6 steps: 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 → 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。 → …
- Context is incomplete
- SKILL.md covers 用 / 不用, 操作规程, 输出模板 and 纪律, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Investigation First is an agent skill from HughYau/qiushi-skill. 调查研究：在下判断、做决策、给建议之前，先用第一手材料弄清现状，产出「事实 / 推断 / 未知」三栏调查结论。当上下文不完整、证据薄弱、领域陌生、用户说"先别动手"、或你发现自己在凭印象作答时触发；已充分调查后的执行阶段不要重复触发。 English: Investigate before judging. Gather firsthand facts and produce a fact / inference / unknown ledger before any recommendation. Trigger when context is incomplete, evidence is thin, the domain is unfamiliar, the user says "look first", or you notice yourself answering from impression; skip when investigation is already done and the task is pure execution.
Its SKILL.md is about 430 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `original-texts.md`).
The repository describes itself as: Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done… The licence is MIT.
When your agent uses it
- Context is incomplete
- Evidence is thin
- The domain is unfamiliar
- The user says look first
Example prompts
- “look first”
- “/investigation-first”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- 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
- 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"。
What it can do on your machine
Read from SKILL.md and the folder at commit 5ace717. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Investigation First loads about 425 tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 58 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from HughYau/qiushi-skill at commit 5ace717, republished under its MIT licence (© HughYau). 58 words, ~425 tokens.
Download SKILL.mdSave it as
.claude/skills/investigation-first/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- investigation-first
- description
- 调查研究：在下判断、做决策、给建议之前，先用第一手材料弄清现状，产出「事实 / 推断 / 未知」三栏调查结论。当上下文不完整、证据薄弱、领域陌生、用户说"先别动手"、或你发现自己在凭印象作答时触发；已充分调查后的执行阶段不要重复触发。 English: Investigate before judging. Gather firsthand facts and produce a fact / inference / unknown ledger before any recommendation. Trigger when context is incomplete, evidence is thin, the domain is unfamiliar, the user says "look first", or you notice yourself answering from impression; skip when investigation is already done and the task is pure execution.
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
© HughYau, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skills/investigation-first of HughYau/qiushi-skill.
- SKILL.md
- original-texts.md
Open the folder on GitHubat commit 5ace717
Compare with similar skills
Investigation First next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Investigation First this skillHughYau/qiushi-skill | 3.8k | — | ~425 | Automated safety check: Pass | MIT | |
| Root Cause Investigationgarrytan/gstack | 136k | — | ~13k | Automated safety check: Notes | MIT | |
| Osint Investigationaffaan-m/ECC | 276k | — | ~5.7k | Automated safety check: Pass | CC-BY-SA-4.0 | |
| Investigate CIClickHouse/ClickHouse | 50k | — | ~11k | Automated safety check: Notes | Apache-2.0 | |
| Investigate Issuevideojs/video.js | 40k | — | ~318 | Automated safety check: Pass | Custom licence | |
| Investigating ReplayPostHog/posthog | 40k | — | ~2.4k | Automated safety check: Pass | Custom licence |
Similar skills
Osint Investigation
affaan-m/ECC
Sparse-clue OSINT investigation methodology for extracting overlooked leads, connecting fragmented evidence, and testing explanations across sources.
Investigate CI
ClickHouse/ClickHouse
Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL.
Investigate Issue
videojs/video.js
Investigate GitHub issues without changing code. An agent skill from videojs/video.js.
- Official
Investigating Replay
PostHog/posthog
Investigates a session recording by gathering metadata, person profile, same-session events, and linked error tracking issues in one pass.
- Official
Investigating Logs
PostHog/posthog
Investigate logs in a PostHog project: verify a service or deployment is healthy, explain an error spike, triage an incident, or understand what a log stream is saying.
More from HughYau/qiushi-skill
All 11 skills in this repoConcentrate Forces
HughYau/qiushi-skill
集中兵力：多件事同时争抢时间、注意力或预算时，列出全部待办，选定唯一主攻目标并公开锁定，彻底解决、验证后再转向下一个。当待办过多、推进分散、"每件都做了一点但都没做完"、需要决定先做什么时触发；只有一个任务、任务彼此独立可并行、用户明确要求同时推进时不触发。
Contradiction Analysis
HughYau/qiushi-skill
矛盾分析法：把复杂问题拆成若干对立面，找出规定其他矛盾的主要矛盾及其主要方面，判定对抗性 / 非对抗性，并据此选择处理方式。当问题头绪多、多个因素互相牵制、优先级不清、根因不明、反复修不好、trade-off 说不清时触发；直接执行类任务或用户已定方案时不触发。
Criticism Self Criticism
HughYau/qiushi-skill
批评与自我批评：在工作完成、阶段验收、收到批评或同类错误反复出现时，对成果和过程做诚实、具体、基于事实的审视，输出可执行的改进项，并处理外来批评而不辩解。触发信号包括 review、复盘、审查、"帮我看看有没有问题"、"你确定吗"；任务刚开始或只是单步查询时不触发。
Mass Line
HughYau/qiushi-skill
群众路线：从持有真实情况的多方（用户、使用者、代码库、日志、运行结果）收集分散意见，系统化为方案，再带回去对齐与检验，循环改进。当多方意见分歧、需要汇总零散反馈、方案要拿回给真实使用者确认、或你发觉自己在闭门造车时触发；信息源单一且完整、处于执行阶段时不触发。
Overall Planning
HughYau/qiushi-skill
统筹兼顾：当多个目标、指标或利益方相互制约、优化一项会伤害另一项时，识别全部辩证关系对，检查片面性，为每对关系定出当前阶段的侧重与底线，评估系统性影响，并设失衡预警。触发信号包括 trade-off、目标冲突、速度 vs 质量、短期 vs 长期、"顾此失彼"；只有单一目标、用户已定取舍、或属硬性二选一时不触发。
Practice Cognition
HughYau/qiushi-skill
实践认识论：把方案、假说或判断放回实践中检验，按「实践 → 认识 → 再实践」螺旋迭代，并在开始前写明循环终止条件。当你提出了假说要验证、一次尝试失败要复盘再来、发现自己只想不做或只做不想时触发；一次性输出、答案可直接查阅、还没形成假说（先调查）时不触发。
Questions about Investigation First
What does Investigation First do?
调查研究：在下判断、做决策、给建议之前，先用第一手材料弄清现状，产出「事实 / 推断 / 未知」三栏调查结论。当上下文不完整、证据薄弱、领域陌生、用户说"先别动手"、或你发现自己在凭印象作答时触发；已充分调查后的执行阶段不要重复触发。. Investigation First is an agent skill from HughYau/qiushi-skill. 调查研究：在下判断、做决策、给建议之前，先用第一手材料弄清现状，产出「事实 / 推断 / 未知」三栏调查结论。当上下文不完整、证据薄弱、领域陌生、用户说"先别动手"、或你发现自己在凭印象作答时触发；已充分调查后的执行阶段不要重复触发。 English: Investigate before judging.
When should I use Investigation First?
Investigation First fits situations like: context is incomplete; evidence is thin; the domain is unfamiliar; the user says look first.
How do I install Investigation First in Claude Code?
Run `npx skills add HughYau/qiushi-skill --skill investigation-first -a claude-code`. Or copy the skill folder (skills/investigation-first in HughYau/qiushi-skill) into .claude/skills/investigation-first in your project. Claude Code loads it when a task matches its description.
How do I install Investigation First in Codex?
Run `npx skills add HughYau/qiushi-skill --skill investigation-first -a codex`. Or copy the skill folder (skills/investigation-first in HughYau/qiushi-skill) into .agents/skills/investigation-first in your project. Codex loads it when a task matches its description.
Can I use Investigation First in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HughYau/qiushi-skill --skill investigation-first -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/investigation-first, .gemini/skills/investigation-first, .github/skills/investigation-first and .opencode/skills/investigation-first in your project.
What does Investigation First need to run?
SKILL.md names no scripts, command-line tools or credentials: Investigation First is instructions for the agent only.
Does Investigation First access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Investigation First safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Investigation First use?
Investigation First is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Investigation First use?
About 425 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Investigation First?
Skills that share tags, products or a category with Investigation First: Root Cause Investigation (garrytan/gstack, 136k stars), Osint Investigation (affaan-m/ECC, 276k stars), Investigate CI (ClickHouse/ClickHouse, 50k stars) and Investigate Issue (videojs/video.js, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Investigation First?
HughYau (a GitHub user) maintains it in HughYau/qiushi-skill, which has 3,812 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 1, 2026.
Source: HughYau/qiushi-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.