Menu

#884 by GitHub stars

tenfoldmarc/llm-council-skill

Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test

Engineering

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

SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

0dc03275b0dd → 0dc03275b0dd

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 0dc03275b0dd

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 0dc03275b0ddf542545da3a9684510fff31df353

1kGitHub stars
27stars in 7 days
1skill in this repository
0commits in 30 days

Heat

6.4
  • Star growth, last 7 daysAhead of 93% of tracked repositories
  • Star growth, last 24 hoursAhead of 96% of tracked repositories
  • Rank movement, last 7 daysAhead of 56% 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 7, 20261,018

Individual skills in this repository

How it works

llm-council

When your agent uses it

Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.

What it loads into context

Frontmatter

223 tokens

Always available to the agent

SKILL.md

3,678 tokens

When the skill is activated

Reference documents

855 tokens

Loaded on request

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

The playbook

  1. when to run the council
  2. the five advisors
  3. how a council session works
  4. output format
  5. example: counciling a product decision
  6. important notes

Files

  • .gitignoreasset88 bytes
  • README.mddoc3,486 bytes
  • SKILL.mdcore17,005 bytes

No excerpt is shown for this license. Read the source on GitHub.

View the complete source on GitHub

Skills included

  • llm-council

Repository facts

License
No license detected
Created
Apr 18, 2026
Last pushed
Apr 18, 2026
Forks
187
Open issues
1
Project activity
Slowing

Rank over the last 12 weeks

Now #884 · best #693 · down 44 in 30 days

  1. #878 on Oct 31
  2. #876 on Nov 1
  3. #879 on Nov 2
  4. #883 from Nov 3 to Nov 5
  5. #882 on Nov 6
  6. #884 since Nov 7
74 earlier periods
  1. #706 on Aug 2
  2. #694 on Aug 8
  3. #705 on Aug 9
  4. #731 on Aug 10
  5. #735 on Aug 11
  6. #730 on Aug 12
  7. #729 on Aug 13
  8. #724 on Aug 14
  9. #695 on Aug 15
  10. #719 on Aug 16
  11. #722 on Aug 17
  12. #738 on Aug 18
  13. #721 on Aug 20
  14. #726 on Aug 21
  15. #693 on Aug 22
  16. #725 on Aug 23
  17. #750 on Aug 24
  18. #755 on Aug 25
  19. #739 on Aug 26
  20. #752 on Aug 27
  21. #777 on Aug 28
  22. #711 on Aug 29
  23. #718 on Aug 30
  24. #754 on Aug 31
  25. #770 on Sep 1
  26. #757 on Sep 3
  27. #736 on Sep 4
  28. #718 on Sep 5
  29. #747 on Sep 6
  30. #757 on Sep 7
  31. #782 on Sep 8
  32. #763 on Sep 9
  33. #771 on Sep 10
  34. #746 on Sep 11
  35. #744 on Sep 13
  36. #771 on Sep 14
  37. #760 on Sep 15
  38. #769 on Sep 16
  39. #757 on Sep 18
  40. #735 on Sep 19
  41. #747 on Sep 20
  42. #798 on Sep 22
  43. #786 on Sep 23
  44. #753 on Sep 24
  45. #732 on Sep 25
  46. #733 on Sep 26
  47. #761 on Sep 27
  48. #787 on Sep 28
  49. #813 on Sep 29
  50. #798 on Sep 30
  51. #742 on Oct 1
  52. #761 on Oct 2
  53. #737 on Oct 3
  54. #764 on Oct 4
  55. #775 on Oct 5
  56. #780 on Oct 6
  57. #796 on Oct 7
  58. #840 on Oct 8
  59. #803 on Oct 9
  60. #785 on Oct 11
  61. #811 on Oct 12
  62. #815 on Oct 13
  63. #825 on Oct 14
  64. #798 on Oct 17
  65. #768 on Oct 18
  66. #801 on Oct 19
  67. #800 from Oct 20 to Oct 21
  68. #775 on Oct 22
  69. #773 on Oct 23
  70. #738 on Oct 24
  71. #882 on Oct 25
  72. #879 on Oct 28
  73. #883 on Oct 29
  74. #882 on Oct 30

Before you install

Instructions only

Automated signals, not a guarantee

Checked Nov 4, 2026

  • No broad tool permissions
  • No dangerous shell commands
  • 5 network referencesin 2 files: README.md:5 SKILL.md:314
  • No hidden or obfuscated text
  • No instruction overrides
  • No executable scripts
  • No access to secrets
  • No requests to vote in Hot
Show all 5 signals by file

README.md

  • Network accessline 5
    Based on [Andrej Karpathy's LLM Council](https://x.com/karpathy/status/1962263486196867115) methodology, adapted to run entirely inside Claude Code using sub-agents with different thinking styles.
  • Network accessline 40
    git clone https://github.com/tenfoldmarc/llm-council-skill ~/.claude/skills/llm-council
  • Network accessline 97
    - Methodology: [Andrej Karpathy's LLM Council](https://x.com/karpathy/status/1962263486196867115)
  • Network accessline 98
    - Adapted for Claude Code sub-agents by [@olelehmann](https://x.com/olelehmann)

SKILL.md

  • Network accessline 314
    Methodology by [Andrej Karpathy](https://x.com/karpathy). Claude Code adaptation inspired by [@olelehmann](https://x.com/olelehmann). Published by [@tenfoldmarc](https://instagram.com/tenfoldmarc) — follow for daily AI automation builds.

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.

Signal confidence: 2 facts
  • Network access in prose of documentationREADME.md:5Low confidence
  • Network access in code of documentationREADME.md:40Low confidence

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md 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.

You might also use

mattpocock/skills

Skills for Real Engineers. Straight from my .agents directory.

316.8kGitHub stars

obra/superpowers

An agentic skills framework & software development methodology that works.

313.7kGitHub stars

NousResearch/hermes-agent

The agent that grows with you

261.2kGitHub stars

multica-ai/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions,…

230.3kGitHub stars

anthropics/skills

Public repository for Agent Skills

188.2kGitHub stars

DietrichGebert/ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

185.9kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

tenfoldmarc/llm-council-skill: #884 on hotskills, 1k stars

[![tenfoldmarc/llm-council-skill on hotskills](https://hotskills.dev/badge/tenfoldmarc-llm-council-skill.svg)](https://hotskills.dev/skill/tenfoldmarc-llm-council-skill/)