Build and validate a durable CLAIM ledger for documentary, historical, technical, educational, press-kit, festival, and campaign facts, preserving sources, uncertainty, disagreement, adoption state, and downstream use.
Scanned 9/9/2026
Install to Claude Code
Skills Directorynpx -y skills add badgids/Story-Film-Skills --skill evidence-research --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Evidence Research?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/badgids-evidence-research)More formats (shields.io, HTML) on the badges page.
---
name: evidence-research
description: Build and validate a durable CLAIM ledger for documentary, historical, technical, educational, press-kit, festival, and campaign facts, preserving sources, uncertainty, disagreement, adoption state, and downstream use.
disable-model-invocation: true
author: Alan Guice (Badgids)
license: Apache-2.0
---
# Evidence Research
1. Read `../../references/RESEARCH_RULES.md` and `../../references/EVIDENCE_RESEARCH.md`.
2. Define the research question and current project assumption.
3. Research with source quality appropriate to the claim.
4. Add or update `CLAIM-###` records in `01_story/research/claims.jsonl`.
5. Preserve disagreement and uncertainty instead of forcing consensus.
6. Connect adopted claims to scenes, narration, documents, or campaign records through `used_by`.
7. Run `scripts/claim_ledger.py PROJECT` before public-facing use.
8. Do not let a research note silently alter canon.
Done when every material public claim has traceable evidence or an explicit unresolved/creative status.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
