bdistill-discover
Domain Discovery
Turn a vague description of your work into a structured extraction plan. You describe your field, the agent maps it into extractable topics with seed terms, and you pick what to extract first.
When to use
- You know your field but not what's worth extracting ("I work in insurance")
- You want a structured starting point before running bdistill-extract
- You're exploring what domain knowledge an AI model can provide
- You want to scope a large domain into focused extraction sessions
Input contract
required:
description: string # Vague domain description ("I trade grain futures", "I audit banks", "I manage clinical trials")
output:
domain: string # Suggested domain slug (e.g. "grain-trading", "aml-compliance", "pharma-regulatory")
seed_terms: string[] # Extraction-ready terms for bdistill-extract
More from francyjglisboa/bdistill-skills
bdistill-extract
Extract structured, adversarially validated domain knowledge or IF-THEN decision rules from AI training knowledge. Builds a compounding knowledge base — one file per domain, deduplicated across sessions. Triggers on "extract knowledge", "build KB", "distill", "extract rules", "decision thresholds", "what do you know about". Outputs JSONL entries to {domain}.jsonl.
1bdistill-export
Export a bdistill knowledge base into any format — system prompt for Claude Projects/Cursor/Copilot/ChatGPT, Python harness module with build_prompt(), JSON for agent consumption, Excel with quality color-coding, audit checklist CSV, or fine-tuning JSONL. Triggers on "export", "system prompt", "harness", "training data", "Excel export", "export for Claude Project". Outputs file on disk.
1bdistill-xray
Probe any AI model's behavioral patterns across 6 dimensions — tool use, refusal boundaries, formatting defaults, reasoning style, persona stability, and grounding/hallucination resistance. The model probes itself, no API key needed. Generates a visual report. Triggers on "x-ray", "probe behavior", "behavioral analysis", "model evaluation", "how does this model behave". Outputs behavioral profile with scores.
1bdistill-predict
Assemble structured predictions with decomposed evidence, adversarial self-challenge, and calibrated probability. Supports binary YES/NO mode (prediction markets, any yes/no question) and directional mode. Optionally recalls from your KB and searches the web for current data. Triggers on "predict", "forecast", "what happens if", "probability of", "will X happen". Outputs prediction card with evidence chain.
1bdistill-operationalize
Connect exported rules to live data for automated monitoring. Loads a bdistill rules export, fetches current data from free APIs or local feeds, contrasts each rule's conditions against reality, and reports which rules triggered with current values and impact estimates. Works with any domain — weather, market, compliance, clinical. Triggers on "operationalize", "monitor", "check against live data", "contrast rules", "what's triggered". Outputs decision report.
1bdistill-validate
Detect confabulated claims by re-asking entries with rephrased questions and measuring variance — both numeric stability (do the numbers stay the same?) and structural stability (do the conditions, scope, and reasoning stay the same?). Use after bdistill-extract to filter your KB before export. Triggers on "validate KB", "consistency check", "are these numbers real", "verify thresholds", "detect hallucination", "stability check". Outputs stability scores per entry.
1