analyze
只读深度分析:回答「为什么/怎么回事/影响面」类问题,输出带置信度排序的综合结论,显式区分证据/推断/未知。用户说「analyze / investigate / 为什么会 / 是什么导致」或需要跨文件解释时使用。
Skill by hatsuyuki0103
Chalk Labs
Need help deploying analyze?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hatsuyuki0103-analyze
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/analyze
What's inside
- Skill name
analyze- Description
- 只读深度分析:回答「为什么/怎么回事/影响面」类问题,输出带置信度排序的综合结论,显式区分证据/推断/未知。用户说「analyze / investigate / 为什么会 / 是什么导致」或需要跨文件解释时使用。
- License
- MIT
- Instructions
- 81 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Analyze(只读深度分析) ## 何时使用 / 何时不用 使用:用户要的是有据解释而非改代码;答案需要跨多文件/跨边界追踪;有多个合理解释需要排序;置信度应反映证据强度;改动之前想先理解架构/行为/因果/影响/取舍。 不用:用户明确要改代码/修复/执行;要新计划或验收标准(plan / ralplan);简单单文件事实查询(直接读文件回答)。 ## 不可协商的契约 **Analyze 只读**: - 不编辑文件; - 不把答案写成实现计划; - 不以修复建议作为主要输出; - 不悄悄转入执行工作; - 不夸大确定性;不编造仓库证据之外的事实; - 不用超出证据的评判性/规范性/推测性语言。 如给下一步建议,只给一个能降低不确定性的**判别式只读探针**(如"看 X 文件的 Y 方法可确认")。 ## 问题对齐综合 先答用户真正问的问题;不以通用调试模板起手;深度匹配请求规模——简单问题直接答,广问题扩搜索面但最终综合保持紧凑。 ## 证据规则(证据 vs 推断 vs 未知) 每个实质论断必须标注三选一: 1. **Evidence**:仓库工件直接支撑(代码路径/契约/测试/生成物/配置/文档 + 具体文件引用); 2. **Inference**:从证据推理出的结论; 3. **Unknown**:当前仓库证据无法裁决的问题。 推断不得冒充直接证据;猜测不得冒充推断;证据不裁决时显式声明不确定。 证据强度排序:直接代码路径/契约/测试/配置(强)> 多独立文件同向印证 > 良好代码结构的局部行为推断 > 明确标记为暂定的弱上下文线索。无支撑的猜测不是证据。 ## 并行探查(可选、有界) 简单问题直接读。复杂问题时可用后台 subagent 并行探查,每路回答一个具体子问题/子系统,默认三路拆分:主代码路径与契约 / 配置与编排面 / 测试与文档佐证。 ## 工作方法 1. 一句话重述问题; 2. 圈定最可能回答它的最小文件集; 3. 先读直接证据; 4. 必要时开有界并行探查; 5. 比较竞争解释; 6. 按支撑度排序; 7. 返回明确分离证据与推断的综合结论。 ## 输出契约 ``` ## Question <一句话> ## Answer(先答问题) ## Ranked Explanations 1. <解释 A> — 支撑:<证据 file:line> — 置信度:高/中/低 2. <解释 B> — ... ## Evidence vs Inference - Evidence: <有直接支撑的论断> - Inference: <推理结论(标注从哪些证据推出)> - Unknown: <仓库证据无法裁决的问题> ## Discriminating Probe(可选) - <一个能降低不确定性的只读检查> ``` ## 最终清单 - [ ] 回答了用户实际的问题 - [ ] 每个实质论断标注 证据/推断/未知 - [ ] 竞争解释按支撑度排序 - [ ] 未编辑任何文件、未输出实现计划 - [ ] 置信度与证据强度一致
From hatsuyuki0103/oh-my-deepseek-harness, MIT.
Signals
- Stars
- 5
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 17, 2026 (2 months ago)
- Last release
- Oct 12, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get analyze running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
analyze skill. Agent Mart. https://agentmart.dev/skills/hatsuyuki0103-analyze (last updated 2026-10-24)