bdistill-export
When to use
- Make your AI tool domain-reliable — paste validated rules into Claude Project/Cursor/Copilot
- Feed rules to a deterministic agent — export as Python module with RULES + build_prompt()
- Export JSON for bdistill-operationalize to contrast against live data
- Generate fine-tuning JSONL for LoRA training (alpaca/sharegpt/openai formats)
- Share with non-technical team — Excel with quality color-coding or audit checklist CSV
Input contract
required:
domain: string # Knowledge base domain name (e.g. "aml-compliance")
format: enum # prompt | harness-json | harness-python | excel | checklist | training-jsonl
optional:
platform: enum # claude-project | cursor-rules | copilot-instructions | chatgpt-custom | generic
training_format: enum # alpaca | sharegpt | openai
min_quality: float # Minimum quality score threshold (default: 0.7)
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-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.
1bdistill-abstract
Extract structural rules from one domain, abstract to bare skeletons at three granularity levels, then re-instantiate in other domains to discover non-obvious cross-domain correspondences. Filters with mandatory web-grounded novelty check AND adversarial validity challenge AND reverse round-trip validation. Triggers on "abstract rules", "cross-domain", "structural analogy", "what pattern in X applies to Y", "transfer rules between domains". Outputs validated cross-domain rule correspondences with structured testable predictions.
1