#330 by GitHub stars

HughYau/qiushi-skill

Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done. 求是Skill——从经典唯物辩证法与实践哲学中提炼出一条总原则和九大方法论工具武装AI大脑。

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/arming-thought/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

5ace7173b2d7 → 5ace7173b2d7

Compare on GitHub

skills/concentrate-forces/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

5ace7173b2d7 → 5ace7173b2d7

Compare on GitHub

skills/contradiction-analysis/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

5ace7173b2d7 → 5ace7173b2d7

Compare on GitHub

skills/criticism-self-criticism/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

5ace7173b2d7 → 5ace7173b2d7

Compare on GitHub

skills/investigation-first/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

5ace7173b2d7 → 5ace7173b2d7

Compare on GitHub

skills/mass-line/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

5ace7173b2d7 → 5ace7173b2d7

Compare on GitHub

skills/overall-planning/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

5ace7173b2d7 → 5ace7173b2d7

Compare on GitHub

skills/practice-cognition/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

5ace7173b2d7 → 5ace7173b2d7

Compare on GitHub

skills/protracted-strategy/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

5ace7173b2d7 → 5ace7173b2d7

Compare on GitHub

skills/spark-prairie-fire/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

5ace7173b2d7 → 5ace7173b2d7

Compare on GitHub

skills/workflows/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

5ace7173b2d7 → 5ace7173b2d7

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 5ace7173b2d71fa7848c56a29f74b39d611c6cb3

git clone --filter=blob:none --no-checkout https://github.com/HughYau/qiushi-skill.git .hotskills/hughyau-qiushi-skill && git -C .hotskills/hughyau-qiushi-skill checkout --detach 5ace7173b2d71fa7848c56a29f74b39d611c6cb3 # Copy each selected skill directory from .hotskills/hughyau-qiushi-skill into .claude/skills/<skill-name>/
3.9kGitHub stars
7stars in 7 days
11skills in this repository
0commits in 30 days

Heat

3.9
  • Star growth, last 7 daysAhead of 51% of tracked repositories
  • Star growth, last 24 hoursAhead of 70% of tracked repositories
  • Rank movement, last 7 daysAhead of 36% of tracked repositories
  • Commits, last 30 daysAhead of 0% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 2, 2026Nov 6, 20263,852

Individual skills in this repository

How it works

arming-thought

When your agent uses it

求是方法论的入口与总原则。在每次新的顶层会话开始时加载一次,用「实事求是」约束全部判断,并只在明确适用时把任务路由到对应的方法论 skill;被派遣执行单一具体任务的子 agent 直接跳过。 English: Entry point and governing principle of the Qiushi methodology. Load once at the start of a top-level session to enforce "seek truth from facts" and route to a downstream skill only when it clearly helps. Delegated sub-agents on narrow tasks should skip it.

What it loads into context

Frontmatter

132 tokens

Always available to the agent

SKILL.md

844 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 总原则:实事求是(四条硬规则)
  2. 路由:什么时候用哪件武器
  3. 指令优先级

Files

  • ../../.claude-plugin/marketplace.jsonasset606 bytes
  • ../../.claude-plugin/plugin.jsonasset131 bytes
  • ../../hooks/hooks.jsonasset305 bytes
  • SKILL.mdcore3,079 bytes
Read SKILL.md

# 武装思想

> "'实事'就是客观存在着的一切事物,'是'就是客观事物的内部联系,即规律性,'求'就是我们去研究。" —— 《改造我们的学习》

**子 agent 执行单一具体任务时:跳过本 skill。**

## 总原则:实事求是(四条硬规则)

| 规则 | 做法 | 违反信号 |
|---|---|---|
| 结论跟着证据走 | 每个判断标出依据:读了什么、跑了什么、看到了什么 | 有判断,无依据 |
| 分清三种话 | 区分「已核实的事实」「推断」「未知」;未知就写"不知道,需确认" | 用猜测填空 |
| 验证过才算完成 | 声称完成前先跑一遍、看输出、比对预期,并写出验证动作 | 写完即宣布完成 |
| 遇阻先诊断 | 失败时先说清原因,再补调查或换路径;不在第一次受阻就停 | "超出能力范围"式放弃 |
View the complete source on GitHub

Skills included

  • arming-thought
  • concentrate-forces
  • contradiction-analysis
  • criticism-self-criticism
  • investigation-first
  • mass-line
  • overall-planning
  • practice-cognition
  • protracted-strategy
  • spark-prairie-fire
  • workflows

Repository facts

License
MIT
Created
Mar 25, 2026
Last pushed
Oct 1, 2026
Forks
286
Open issues
21
Project activity
Active

Rank over the last 12 weeks

Now #330 · best #244 · down 44 in 30 days

  1. #320 on Nov 1
  2. #321 on Nov 2
  3. #324 on Nov 3
  4. #325 from Nov 4 to Nov 5
  5. #327 on Nov 6
  6. #330 since Nov 7
69 earlier periods
  1. #235 on Aug 2
  2. #237 on Aug 8
  3. #236 on Aug 9
  4. #245 on Aug 10
  5. #240 on Aug 11
  6. #243 on Aug 13
  7. #244 on Aug 14
  8. #243 on Aug 15
  9. #245 on Aug 16
  10. #244 on Aug 17
  11. #251 on Aug 18
  12. #249 on Aug 19
  13. #246 on Aug 21
  14. #244 on Aug 22
  15. #249 on Aug 23
  16. #251 from Aug 24 to Aug 25
  17. #254 on Aug 26
  18. #255 on Aug 27
  19. #251 on Aug 28
  20. #254 from Aug 29 to Aug 30
  21. #256 on Aug 31
  22. #260 on Sep 1
  23. #256 on Sep 2
  24. #263 on Sep 3
  25. #256 on Sep 4
  26. #258 on Sep 5
  27. #256 on Sep 6
  28. #261 on Sep 7
  29. #259 from Sep 8 to Sep 9
  30. #260 on Sep 10
  31. #261 on Sep 11
  32. #262 on Sep 12
  33. #267 on Sep 13
  34. #269 on Sep 14
  35. #268 on Sep 15
  36. #267 on Sep 16
  37. #266 on Sep 17
  38. #268 on Sep 18
  39. #266 on Sep 19
  40. #271 on Sep 20
  41. #272 on Sep 22
  42. #273 on Sep 23
  43. #275 on Sep 24
  44. #270 on Sep 25
  45. #271 on Sep 26
  46. #273 on Sep 27
  47. #279 on Sep 29
  48. #277 on Sep 30
  49. #279 on Oct 1
  50. #283 on Oct 2
  51. #276 on Oct 3
  52. #274 on Oct 4
  53. #281 on Oct 5
  54. #286 from Oct 7 to Oct 8
  55. #289 on Oct 9
  56. #285 on Oct 11
  57. #290 on Oct 12
  58. #289 on Oct 14
  59. #290 from Oct 15 to Oct 16
  60. #292 on Oct 18
  61. #296 on Oct 20
  62. #300 on Oct 21
  63. #301 on Oct 22
  64. #299 on Oct 23
  65. #305 on Oct 25
  66. #309 on Oct 28
  67. #311 on Oct 29
  68. #317 on Oct 30
  69. #319 on Oct 31

Before you install

Instructions only

Automated signals, not a guarantee

Checked Nov 2, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 1 note
  • skills/mass-line/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • No broad tool permissions
  • No dangerous shell commands
  • 3 network referencesin 1 file: .claude-plugin/marketplace.json:3
  • No hidden or obfuscated text
  • No instruction overrides
  • No executable scripts
  • No access to secrets
  • No requests to vote in Hot
Show all 3 signals by file

.claude-plugin/marketplace.json

  • Network accessline 3
    "owner": {     "name": "HughYau",     "url": "https://github.com/HughYau"
  • Network accessline 4
    "name": "HughYau",     "url": "https://github.com/HughYau"   },
  • Network accessline 5
    "url": "https://github.com/HughYau"

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 3 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/arming-thought/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/arming-thought/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/arming-thought/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/arming-thought/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/arming-thought/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

HughYau/qiushi-skill: #330 on hotskills, 3.9k stars

[![HughYau/qiushi-skill on hotskills](https://hotskills.dev/badge/hughyau-qiushi-skill.svg)](https://hotskills.dev/skill/hughyau-qiushi-skill/)