research
Skill2 starsChanged 13 days agoMITView on GitHub
技术调研执行层：8 大思考接口、完整研究流程、研究计划与审计钩子三张表。做系统调用/API/架构决策/故障排查类深度技术调研、技术选型评估，或为报告呈现产出带证据链的研究素材时使用；怎么调研归本文，怎么成文归 report。触发词：技术调研/深度调研/做研究/研究方法/研究计划/快研/8接口/三维度验证/审计钩子/三张表。
189 other projects use a version of this.
Adopted by
Most recently taken up by
- Suge8/friedbuntheir own version, first seen Nov 15, 2026
- Fractera/Agent-Engineering-Infrastructuretheir own version, first seen Nov 15, 2026
- Fractera/Agentic-Engineering-Infrastructuretheir own version, first seen Nov 15, 2026
- iha2/superlitetheir own version, first seen Nov 15, 2026
- SireJeff/k0ntexttheir own version, first seen Nov 15, 2026
- quickchatai/quickreviewtheir own version, first seen Nov 15, 2026
Used with
Projects with it also use daily-arxiv, exp-eval and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
LambenthanSkilldaily-arxiv
每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新
Also in 5 projects that use this
- LambenthanSkill
exp-eval
实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
Also in 5 projects that use this
truongtv22SkillProblem-Solving Techniques
Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), scale uncertainty (scale game), and dispatch when stuck. Techniques derived from Microsoft Amplifier project patterns adapted for immediate application.
Also in 5 projects that use this
liufeng1976Skillsetup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Also in 43 projects that use this
skyllwtSkillexp-pilot-eval
Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.
Also in 4 projects that use this
- skyllwtSkill
exp-pilot-run
Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
Also in 4 projects that use this
- +5 more from Lambenthan
- +1 more from skyllwt
Other versions189 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 189
- mattpocock/skills★ 325ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- udecode/plate★ 17ksame name
- openai/plugins★ 7.8ksame name
- ArcReel/ArcReel★ 6.6ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.8ksame name
- withcoral/coral★ 4.9ksame name
179 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- skills/iso/light/CLAUDE.mdCLAUDE.md
- ai-code-reviewSkill
- api-design-reviewSkill
- architecture-support-briefSkill
- class-design-reviewSkill
- comment-policySkill
- cpp-exemplarsSkill
- error-code-classificationSkill
- essential-tool-installSkill
- isoSkill
- notion-diagramSkill
- reportSkill
- incident-reviewSkill
- routerSkill
- test-naming-and-structureSkill
The file
Files
技术调研框架（研究执行层）
从问题到方案、从原理到工程、从过去到未来。一次完整的技术研究覆盖五件事：问题导向、原理深入、工程实践、生态融合、持续迭代——缺任何一件，研究要么退化为文档摘抄，要么退化为无法落地的原理分析。
溯源：2026-08-11 创建于 system() 深度研究实践；2026-10-24 增审计钩子；2026-10-31 由单文件拆分立技能。
分工边界
| 层 | 技能 | 管什么 |
| 研究执行层 | 本文 | 怎么调研：8 接口、流程、研究计划、审计钩子 |
| 呈现层 | skills/report/ | 怎么成文：可读、可落地、可追溯的正式报告 |
接口：研究过程中按本文「审计钩子」产出三张表，报告期由 report 直接引用，不回炉重查。
触发场景与深度选择
系统调用研究（system / fork / epoll）、API 设计分析、架构决策研究、故障排查与根因分析、技术选型评估、性能优化研究、安全风险评估、开源项目代码分析。
快研不铺满：一小时级、单一问题的调研只走接口 4（问题驱动）+ 审计钩子三张表；多维度研究才走完整 8 接口。判据是「结论要支撑什么决策」——支撑选型与设计的走全流程，回答一个疑问的走快研。
8 大思考接口（一览）
| # | 接口 | 一句话 |
| 1 | 三维度验证 | 理论 + 实践 + 工具 = 完整理解 |
| 2 | 渐进式深度 | 入门级 → 原理级 → 故障级 → 工程级 |
| 3 | 多视角验证 | 用户 + 开发者 + 架构师三视角 |
| 4 | 问题驱动研究 | 目标与现象 → 原因 → 解决方案 → 预防 |
| 5 | 技术生态融合 | 单技术 → 技术关联 → 生态融合 |
| 6 | 实战导向工程 | 可用性 + 可维护性 + 可扩展性 |
| 7 | 安全优先工程 | 风险识别 → 攻击理解 → 防御策略 |
| 8 | 历史演进思维 | 现状 → 原因 → 替代方案 → 未来趋势 |
各接口的操作步骤与模板见 references/interfaces.md；8 步如何串成完整流程、研究计划与风险管理、epoll 应用示例见 references/workflow.md。
硬纪律：审计钩子（三张表边做边填）
研究过程中就地产出三张表，报告期直接引用。事后补的表只能证明「我记得」，不能证明「当时查过」——这是本技能唯一的强制项，也是与呈现层对接的全部接口。
G.1 数据源登记表（每引一源即登记一行）
| # | 名称 | URL | 抓取日期 | 本地缓存路径 | 类型(规范/文档/代码/工具) |
| 1 | 示例 | https://… | 2026-10-24 | sources/… | 代码 |
G.2 证据清单（每个结论挂证据定位 + 徽章）
| 结论# | 结论 | 证据定位(文件:行/测试名/条目号) | 徽章[TV/HV/LA] | 置信度(GROUNDED/INFERRED/SPECULATIVE) |
| C1 | … | src/…:120 | TV | GROUNDED |
徽章规则：[TV] 工具验证 / [HV] 人工复核 / [LA] 模型推断待复核（默认）。
G.3 数字登记表（每个进报告的数字先入表）
| # | 数值 | 口径（必须成完整一句） | 出处 | verified |
| D1 | 1567 | diff v3.2.2..v3.4.3 RPC 域新增行数 | git diff --stat | Y |
研究计划（动手前一段话）
研究初期形成简短计划：目标范围、成功指标、里程碑、风险清单——关键假设区分「事实」与「待验证」。研究过程中定期复盘，更新假设与输出预期。要素清单见 references/workflow.md。
按需读
| 需要 | 读 |
| 某个接口的完整步骤与模板 | references/interfaces.md |
| 完整流程 / 研究计划 / 应用示例 | references/workflow.md |
| 研究产出的章节骨架 | references/output-template.md |
| Mermaid 跨平台渲染规范 | references/mermaid.md |
| 证据三表（数据源 / 证据 / 数字） | references/three-tables.md |
| 结论如何组织成正式报告 | skills/report/（另一技能） |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.