danielrosehill/claude-decision-evaluation-framework-plugin/base-rates

Claude Code and agent skill by danielrosehill/claude-decision-evaluation-framework-plugin

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Apply Kahneman's outside view — define the reference class, look up the historical base rate, and benchmark the inside-view prediction against it. Produces a 0-100 score.

Install

npx vskill@latest install danielrosehill/claude-decision-evaluation-framework-plugin/base-rates

SKILL.md

Base Rates / Outside View

Single-framework analysis. Use when the user wants this lens specifically, or when called as a building block by /decision:analyze.

Inputs

  • A decision file path (markdown). If the user describes a decision verbally instead, run /decision:new-decision first.

Procedure

  1. Locate the framework guide at the plugin install dir's frameworks/base-rates.md. Read it fully.
  1. Read the decision file fully.
  1. Apply the framework exactly as the guide specifies. Don't invent additional structure. Don't merge in other frameworks — that's the orchestrator's job.
  1. Output destination:
  • If the user invoked this standalone, write the analysis inline as the response (and offer to save it to a path).
  • If invoked as a subagent by /decision:analyze, write to the fragment path the orchestrator provides (fragments/base-rates.md).
  1. End with the score line ## Score: <0-100> per the guide's scoring rubric.

Notes

  • Stay inside the framework. If you notice that a different framework would have surfaced something this one missed, note it briefly at the end (## Cross-framework note) but don't switch lenses.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
4
Repository forks
2
7-day trend score
13

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/danielrosehill/claude-decision-evaluation-framework-plugin/base-rates/badge)](https://verified-skill.com/skills/danielrosehill/claude-decision-evaluation-framework-plugin/base-rates)

Something wrong with this skill or its page? Tell us.