Add falsify: scientific thinking protocol skill 🤖🤖🤖

[263311487-ux]

Add falsify as an Agent Skill

falsify is the scientific thinking protocol for AI agents — axioms → hypothesis → adversarial test → evidence → calibrated verdict. It stops agents from giving confident answers they cannot falsify.

What it does

• Forces a falsification-first reasoning loop: before any verdict, the agent must write down what would prove it wrong
• Ships a bias catalog (cognitive biases agents fall into), mental models (Galef, Snowden, Boyd, Kahneman), and a thinking ledger template for transparent reasoning trails
• Works with 20+ agents (Codex, Claude Code, Cursor, Gemini CLI, ...) as a single Markdown skill
• Also on npm: npx falsify-skill (automatically installs into Codex/Claude skill directories)

Quality

• npm run skill:validate ✅ — all 415 skills valid (including this one)
• npm run build ✅ — README table regenerated
• 28 evaluation cases + 4/4 external dogfood cross-validation passed
• MIT license

This is a high-signal addition: no existing skill in this collection covers scientific falsification / hypothesis testing as a general agent reasoning discipline.

[github-actions]

🔴 Contributor Reputation Check: HIGH risk

Check	Risk
Profile	HIGH
Credential audit	NONE

Maintainers: please review this contributor before merging.
See the workflow run for full details.
Automated check powered by AGT.

[github-actions]

🔒 PR Risk Scan Results

Scanned 8 changed file(s).

Severity	Count
🔴 High	0
🟠 Medium	0
ℹ️ Info	0

✅ No matching risk patterns were detected in changed files.

This is an automated soft-gate report. Findings indicate review targets and do not block merge by themselves.

[github-actions]

🔍 Vally Lint Results

✅ All checks passed

Scope	Checked
Skills	1
Agents	0
Total	1

Severity	Count
❌ Errors	0
⚠️ Warnings	0
ℹ️ Advisories	0

Summary

Level	Finding
ℹ️	✅ falsify (2/2 checks passed)
ℹ️	✓ [spec-compliance] All 1 skill(s) are spec-compliant.
ℹ️	✓ spec-compliance: All spec checks passed.
ℹ️	✓ [valid-refs] All file references across 1 skill(s) are valid.
ℹ️	✓ valid-refs: All file references resolve to existing files within the skill directory.
ℹ️	1 skill(s) linted, 1 passed

Full linter output

### Linting skills/falsify
✅ falsify (2/2 checks passed)
    ✓ [spec-compliance] All 1 skill(s) are spec-compliant.
        ✓ spec-compliance: All spec checks passed.
    ✓ [valid-refs] All file references across 1 skill(s) are valid.
        ✓ valid-refs: All file references resolve to existing files within the skill directory.

1 skill(s) linted, 1 passed