Crucible
Self-evolving research methodology: 18 universal principles for LLM-driven investigation, distilled from a 376-turn session with 1 positive + 17 null campaigns. Covers epistemic foundations (causality, nulls, record-keeping), investigation patterns (multi-lens agents, adversarial gates, per-trade enrichment), decision layer (constraint-pivot, supersede-not-rewrite), and emergent resurrection (fail
Skills in this plugin
5- ▌ Crucible Navigator · terrylica bundlestarting a new research campaign, entering a new Claude Code session on a research repo, or when unsure which methodology.
- ▌ Crucible Meta Governance · terrylica bundledeciding whether to pivot or persist, whether to ship or hold, whether to scope-narrow a partial pass, how to manage.
- ▌ Crucible Research Foundations · terrylica bundleValidate findings, design shuffled nulls, check label leakage, review causal features. TRIGGERS - shuffled null, label leakage
- ▌ Crucible Emergent Resurrection · terrylica bundlea hypothesis has failed and needs archiving with resurrection conditions, when reviewing dormant ideas for possible revival, when.
- ▌ Crucible Investigation Methodology · terrylica bundleactively investigating a hypothesis — running a sweep, dispatching multi-agent analysis, designing serial adversarial gates,