Individual skill
falsification-first-audit
Convert a sharp scientific claim into the cheapest decisive falsification program. Steelman the claim into a precise testable form, specify observations/computations that could break it, execute the most informative probes first, and return only BROKEN, CORROBORATED, or UNFALSIFIABLE rather than a resilience score.
skills/falsification-first-audit/SKILL.md
Source commit 41f752b8444ed9030dd9dc223c302ce874e51f83
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Instructions only
- Last checked
- Nov 10, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 511
- Repository last updated
- Oct 23, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- academic-research Repository topic
- deep-research Repository topic
- literature-review Repository topic
- mcp Repository topic
- skill Repository topic
- ai-scientist Repository topic
- auto-research Repository topic
- claude-code Repository topic
- research-agent Repository topic
- scientific-discovery Repository topic
- security Derived category
- research Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
Read excerpt
# falsification-first-audit
## Purpose
Convert a sharp claim into the cheapest decisive falsification program and return BROKEN, CORROBORATED, or UNFALSIFIABLE.
## Input contract
```yaml
mode_contracts:
sharp-claim: &falsification_input
required: [claim, scope, available_evidence]
optional: [mechanism, candidate_tests]
constraints: [claim_must_expose_observable_consequences_and_boundary_conditions]
truthseeking-debate: *falsification_input
truthseeking-red-team: *falsification_input
```
## Execution protocol