Skip to content
Skill

brain-in-the-fish

by fabio-rovai

AI Summary

Brain in the Fish evaluates documents (essays, policies, contracts, clinical reports, surveys) against evaluation criteria using a panel of AI agents. Each agent's mental state exists as OWL ontology. Scoring is grounded in an Evidence Density Scorer (EDS) that makes hallucination mathematically det

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to install the "brain-in-the-fish" skill in my project.

Please run this command in my terminal:
# Install skill into your project
mkdir -p .claude/skills/brain-in-the-fish && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/brain-in-the-fish/SKILL.md "https://raw.githubusercontent.com/fabio-rovai/brain-in-the-fish/main/SKILL.md"

Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.

Description

Universal document evaluation engine — evaluate any document against any criteria using cognitively-modelled AI agents with ontology-grounded scoring

MCP Tools Available

| Tool | Purpose | When to Call | |------|---------|-------------| | eval_status | Check server status and session state | First — verify server is running | | eval_ingest | Ingest a document (PDF/text) | Step 1 | | eval_criteria | Load evaluation framework | Step 2 | | eval_align | Align document sections to criteria | Step 3 | | eval_spawn | Generate evaluator agent panel | Step 4 | | eval_scoring_tasks | Get all scoring prompts for subagents | Step 5 | | eval_score_prompt | Get scoring prompt for one agent/criterion pair | Step 5 (per-task) | | eval_record_score | Record a score from an agent | Step 6 | | eval_debate_status | Check disagreements and convergence | Step 7 | | eval_challenge_prompt | Get challenge prompt for debate | Step 7 (per-challenge) | | eval_report | Generate final evaluation report | Step 8 | | eval_whatif | "What if" re-scoring with modified text | Optional |

What This Does

Brain in the Fish evaluates documents (essays, policies, contracts, clinical reports, surveys) against evaluation criteria using a panel of AI agents. Each agent's mental state exists as OWL ontology. Scoring is grounded in an Evidence Density Scorer (EDS) that makes hallucination mathematically detectable.

Quick Mode (deterministic, no subagents needed)

` eval_ingest → eval_criteria → eval_align → eval_spawn → eval_report ` The server runs evidence scoring internally. eval_report produces a complete evaluation with deterministic scores.

Full Mode (with Claude subagent scoring)

` • eval_ingest(path, intent) • eval_criteria(framework_or_intent) • eval_align() • eval_spawn(intent) • eval_scoring_tasks() → get all tasks • For each task: • Read the scoring prompt • Evaluate the document content against the criterion as the agent persona • eval_record_score(agent_id, criterion_id, score, justification, evidence, gaps) • eval_debate_status() → check for disagreements • If disagreements: • eval_challenge_prompt(challenger, target, criterion) • Generate challenge argument • eval_record_score() with revised score • Repeat until converged • eval_report() → final report `

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 16d ago
Active
AdoptionUnder 100 stars
53 ★ · Niche
DocsREADME + description
Well-documented

GitHub Signals

Stars53
Forks14
Issues0
Updated16d ago
View on GitHub
MIT License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Claude Code