Run any Skill in Manus with one click

council-review-karpathy

Stars1

Forks0

UpdatedApril 28, 2026 at 12:18

Run a multi-persona LLM-council review using Andrej Karpathy's original llm-council Python implementation. Clones the repo into a temp scratch dir, configures it for the user's idea, runs it, and copies outputs back into the idea workspace. Use when the user explicitly wants the canonical implementation rather than the native subagent variant.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

danielrosehill

danielrosehill/Claude-Business-Idea-Eval-Plugin

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	council-review-karpathy
description	Run a multi-persona LLM-council review using Andrej Karpathy's original llm-council Python implementation. Clones the repo into a temp scratch dir, configures it for the user's idea, runs it, and copies outputs back into the idea workspace. Use when the user explicitly wants the canonical implementation rather than the native subagent variant.

Council Review (Karpathy)

Wraps the upstream https://github.com/karpathy/llm-council implementation. We do not vendor the code — we clone it on demand into a scratch directory and run it from there.

Steps

Verify prerequisites: python3, git, and an LLM API key the upstream tool supports (typically OPENAI_API_KEY or ANTHROPIC_API_KEY — check upstream README at clone time).

Choose a scratch directory:

SCRATCH="${CLAUDE_USER_DATA:-${XDG_DATA_HOME:-$HOME/.local/share}/claude-plugins}/business-idea-eval/scratch/llm-council"
mkdir -p "$(dirname "$SCRATCH")"

Clone (or pull) the upstream repo into $SCRATCH. Don't commit it anywhere; this is throwaway.
Read $SCRATCH/README.md (it may have changed since this skill was written) and follow its current setup steps. Do not assume specific commands — read what's there.
Prepare the prompt input from the idea workspace:
- Concatenate idea.md + the formatted summary version (if present) + a short user-context paragraph
- Save as the input file in whatever format the upstream tool expects
Configure the council personas to match the six in reference/council-deliberation.md. The upstream tool typically accepts custom persona prompts via a config file.
Run the council deliberation per upstream instructions.

Copy outputs into the idea workspace:

<workspace_path>/ideas/<slug>/council-karpathy/
  <whatever-files-the-tool-produces>

Optionally write a small index file listing the outputs and the run metadata (model used, timestamp, persona config).

Notes

The upstream tool may require API costs the user should be aware of — show the rough request count before running.
Do not commit the scratch clone to any repo. It exists only for the run.
If the upstream tool's interface has drifted, fall back to council-review-subagents and report the drift to the user.
Output schema differs from the subagent variant; downstream skills (synthesize-analysis, internal-pdf) handle both folder layouts.

More from this repository

same repository

assumptions-and-objections

danielrosehill/Claude-Business-Idea-Eval-Plugin

Surface the load-bearing assumptions in a captured idea and the most likely objections an investor, customer, or skeptical advisor would raise. Produces an assumption-validation plan and an objection-handling brief. Use when the user wants to pressure-test an idea before committing time or capital.

2026-04-281

b2b-b2c-fit

danielrosehill/Claude-Business-Idea-Eval-Plugin

Explore B2B vs B2C (and B2B2C, prosumer, marketplace, dev-tool) routings for a captured idea. Lays out pros and cons of each viable model and recommends the best fit given the idea, user context, and capital appetite. Use when the user is unsure which customer segment to target.

2026-04-281

brainstorm-pivots

danielrosehill/Claude-Business-Idea-Eval-Plugin

Brainstorm tweaks, additions, or pivots that could improve an idea's feasibility, market readiness, capital efficiency, defensibility, or speed-to-revenue. Produces a ranked list of variants with the trade-off each one buys. Use when an idea has been analysed and the user wants suggestions for how to make it stronger.

2026-04-281

capture-idea

danielrosehill/Claude-Business-Idea-Eval-Plugin

Capture a new business idea from text input into a structured workspace. Always preserves the raw input verbatim and offers optional formatted versions — executive summary, elevator pitch, technical deep-dive, and timeline/project plan. Use when the user wants to start a new idea workspace from a written description, brain-dump, or pasted text.

2026-04-281

capture-voice-idea

danielrosehill/Claude-Business-Idea-Eval-Plugin

Capture a business idea from a voice memo / audio file. Transcribes the recording, preserves the raw transcript, then hands off to capture-idea so the user can optionally generate executive summary, elevator pitch, technical deep-dive, and timeline variants. Use when the user has an audio file or recording of an idea pitch.

2026-04-281

compare-ideas

danielrosehill/Claude-Business-Idea-Eval-Plugin

Compare multiple captured ideas head-to-head across explicit dimensions — commercial prospect, speed to first revenue, capital intensity, fit-to-user, defensibility, social impact — and produce a ranked recommendation. Use when the user has 2+ ideas in the workspace and wants help choosing where to focus.

2026-04-281

name	council-review-karpathy
description	Run a multi-persona LLM-council review using Andrej Karpathy's original llm-council Python implementation. Clones the repo into a temp scratch dir, configures it for the user's idea, runs it, and copies outputs back into the idea workspace. Use when the user explicitly wants the canonical implementation rather than the native subagent variant.

Council Review (Karpathy)

Wraps the upstream https://github.com/karpathy/llm-council implementation. We do not vendor the code — we clone it on demand into a scratch directory and run it from there.

Steps

Verify prerequisites: python3, git, and an LLM API key the upstream tool supports (typically OPENAI_API_KEY or ANTHROPIC_API_KEY — check upstream README at clone time).

Choose a scratch directory:

SCRATCH="${CLAUDE_USER_DATA:-${XDG_DATA_HOME:-$HOME/.local/share}/claude-plugins}/business-idea-eval/scratch/llm-council"
mkdir -p "$(dirname "$SCRATCH")"

Clone (or pull) the upstream repo into $SCRATCH. Don't commit it anywhere; this is throwaway.
Read $SCRATCH/README.md (it may have changed since this skill was written) and follow its current setup steps. Do not assume specific commands — read what's there.
Prepare the prompt input from the idea workspace:
- Concatenate idea.md + the formatted summary version (if present) + a short user-context paragraph
- Save as the input file in whatever format the upstream tool expects
Configure the council personas to match the six in reference/council-deliberation.md. The upstream tool typically accepts custom persona prompts via a config file.
Run the council deliberation per upstream instructions.

Copy outputs into the idea workspace:

<workspace_path>/ideas/<slug>/council-karpathy/
  <whatever-files-the-tool-produces>

Optionally write a small index file listing the outputs and the run metadata (model used, timestamp, persona config).

Notes

The upstream tool may require API costs the user should be aware of — show the rough request count before running.
Do not commit the scratch clone to any repo. It exists only for the run.
If the upstream tool's interface has drifted, fall back to council-review-subagents and report the drift to the user.
Output schema differs from the subagent variant; downstream skills (synthesize-analysis, internal-pdf) handle both folder layouts.