agentleFS
Sign inStart free
wxhouwxhou/deepthink/SKILL.md

deepthink

Skill0 starsChanged 21 days agoMITView on GitHub

Adaptive deep reasoning skill that automatically adjusts analysis depth based on question complexity. Uses sequential thinking, multi-path tree-of-thought exploration, Socratic questioning, first-principles verification, and iterative validation to produce high-confidence answers. Quick mode for simple queries, deep mode for complex problems. Bilingual: auto-detects Chinese vs English from prompt.

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. okikusan-public/stock_skills_2★ 32same name
    2. lacerbi/dotclaude★ 2same name
    3. TheNight-Watch/deepthink-skill★ 2same name
    4. KeyArgo/skills-my-hermes★ 1same name

    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 repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the user's prompt:

    line 19
  2. Very specific:

    Claude Code: Use sequentialthinking MCP if available.

    line 52
  3. Distinctive:

    Cursor / Copilot / Others: Use whatever search/clarification tools the platform provides.

    line 53

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

DeepThink

Trigger: /deepthink (Claude Code / Claude.ai) or deepthink: prefix (Cursor / Copilot) or always-on rule (per-platform).

When to Use

  • User invokes the skill
  • Complex problem solving, research, step-by-step thinking
  • User wants high-confidence, well-reasoned answers

Language Detection

Read the user's prompt:

  • Contains Chinese characters (CJK) → load core/protocol.zh.md
  • Otherwise → load core/protocol.en.md

Core Protocol

The full protocol lives in core/. Read the appropriate language version above and follow it. Key sections:

  1. Quick Mode Check — if answerable directly (possibly conditionally) in ≤3 sentences, answer in 1-3 plain sentences and stop — no template, no section headers
  2. Problem Decomposition + Assumption Statement — mandatory assumption list
  3. Socratic Questioning — clarify, assumptions, evidence, counterexamples, alternatives, consequences
  4. Multi-Level Analysis — compare multiple paths when warranted (high effort) → Understand → Plan → Execute → Verify
  5. Verification — Reflection / First Principles / Backward / Self-Consistency
  6. Iteration — if confidence is Low/Medium or problem spans subsystems
  7. Completeness Check — before output, confirm all steps done

Output Format

Deep-mode answers only. Quick-mode answers stay plain — 1-3 sentences, never wrapped in this template.

---
## 🤔 DeepThink Analysis
### Core Problem
### Key Assumptions
### Conclusion
### One-Sentence Summary
### Confidence: [High/Medium/Low]
---

Tool Notes

  • Claude Code: Use sequentialthinking MCP if available; use AskUserQuestion for clarifications; dispatch subagent for parallel exploration
  • Cursor / Copilot / Others: Use whatever search/clarification tools the platform provides; the protocol's "conditioned" wording handles graceful degradation

See core/protocol.en.md or core/protocol.zh.md for the canonical, platform-agnostic version.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free