Menu

#419 by GitHub stars

aiwithremy/claude-skills-llm-council

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

55ee36e89e0f → 55ee36e89e0f

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 → 55ee36e89e0f

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 55ee36e89e0f3f780099ac50332fbb3ec8d14738

3kGitHub stars
94stars in 7 days
1skill in this repository
0commits in 30 days

Heat

6.4
  • Star growth, last 7 daysAhead of 94% of tracked repositories
  • Star growth, last 24 hoursAhead of 95% of tracked repositories
  • Rank movement, last 7 daysAhead of 59% 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, 20262,951

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

224 tokens

Always available to the agent

SKILL.md

3,380 tokens

When the skill is activated

Reference documents

931 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. example: counciling a product decision
  5. important notes

Files

  • README.mddoc3,939 bytes
  • SKILL.mdcore15,661 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 25, 2026
Last pushed
Apr 26, 2026
Forks
253
Open issues
1
Project activity
Slowing

Rank over the last 12 weeks

Now #419 · best #392 · down 12 in 30 days

  1. #412 on Nov 1
  2. #411 on Nov 2
  3. #413 on Nov 3
  4. #415 from Nov 4 to Nov 5
  5. #418 on Nov 6
  6. #419 since Nov 7
79 earlier periods
  1. #450 on Aug 2
  2. #443 on Aug 8
  3. #437 on Aug 9
  4. #452 on Aug 10
  5. #451 on Aug 11
  6. #447 on Aug 12
  7. #452 on Aug 13
  8. #446 on Aug 14
  9. #436 on Aug 15
  10. #437 on Aug 16
  11. #442 on Aug 17
  12. #443 on Aug 18
  13. #442 on Aug 19
  14. #432 on Aug 20
  15. #435 on Aug 21
  16. #423 on Aug 22
  17. #437 on Aug 23
  18. #436 from Aug 24 to Aug 25
  19. #433 on Aug 26
  20. #438 on Aug 27
  21. #436 on Aug 28
  22. #431 on Aug 29
  23. #423 on Aug 30
  24. #435 on Aug 31
  25. #442 on Sep 1
  26. #433 on Sep 2
  27. #437 on Sep 3
  28. #424 on Sep 4
  29. #428 from Sep 5 to Sep 6
  30. #433 on Sep 7
  31. #436 on Sep 8
  32. #425 on Sep 9
  33. #420 on Sep 10
  34. #418 on Sep 11
  35. #416 on Sep 12
  36. #414 on Sep 13
  37. #422 from Sep 14 to Sep 15
  38. #423 on Sep 16
  39. #412 on Sep 17
  40. #417 on Sep 18
  41. #406 on Sep 19
  42. #414 on Sep 20
  43. #412 on Sep 21
  44. #416 on Sep 22
  45. #412 on Sep 23
  46. #404 on Sep 24
  47. #403 on Sep 25
  48. #400 on Sep 26
  49. #409 on Sep 27
  50. #410 on Sep 28
  51. #417 on Sep 29
  52. #411 from Sep 30 to Oct 1
  53. #409 on Oct 2
  54. #396 on Oct 3
  55. #393 on Oct 4
  56. #398 from Oct 5 to Oct 6
  57. #402 on Oct 7
  58. #407 on Oct 8
  59. #418 on Oct 9
  60. #403 on Oct 10
  61. #405 on Oct 11
  62. #412 on Oct 12
  63. #408 on Oct 13
  64. #409 on Oct 14
  65. #408 on Oct 15
  66. #415 on Oct 16
  67. #404 on Oct 17
  68. #407 on Oct 18
  69. #404 on Oct 19
  70. #407 on Oct 20
  71. #410 on Oct 21
  72. #409 on Oct 22
  73. #407 on Oct 23
  74. #392 on Oct 24
  75. #408 on Oct 25
  76. #411 on Oct 28
  77. #414 on Oct 29
  78. #416 on Oct 30
  79. #414 on Oct 31

Before you install

Instructions only

Automated signals, not a guarantee

Checked Nov 2, 2026

  • No broad tool permissions
  • No dangerous shell commands
  • 4 network referencesin 1 file: README.md:5
  • No hidden or obfuscated text
  • No instruction overrides
  • No executable scripts
  • No access to secrets
  • No requests to vote in Hot
Show all 4 signals by file

README.md

  • Network accessline 5
    Built by [Ole Lehmann](https://x.com/itsolelehmann). Based on Andrej Karpathy's [LLM Council](https://github.com/karpathy/llm-council) methodology.
  • Network accessline 61
    > Please install this Claude skill for me. The SKILL.md file lives in this GitHub repo: https://github.com/aiwithremy/claude-skills-llm-council
  • Network accessline 95
    This skill was built by [Ole Lehmann](https://x.com/itsolelehmann). Go follow him, the man cooks.
  • Network accessline 97
    The methodology is adapted from Andrej Karpathy's [LLM Council](https://github.com/karpathy/llm-council).

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: 4 facts
  • Network access in prose of documentationREADME.md:5Low confidence
  • Network access in prose of documentationREADME.md:61Low confidence
  • Network access in prose of documentationREADME.md:95Low confidence
  • Network access in prose of documentationREADME.md:97Low 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.

317.2kGitHub stars

obra/superpowers

An agentic skills framework & software development methodology that works.

313.9kGitHub stars

NousResearch/hermes-agent

The agent that grows with you

261.4kGitHub 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,…

230.5kGitHub stars

anthropics/skills

Public repository for Agent Skills

188.4kGitHub 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.

186.1kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

aiwithremy/claude-skills-llm-council: #419 on hotskills, 3k stars

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