Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Bridge Validation · yogsoth-ai | DecimalAI

researchby yogsoth-ai

Bridge Validation

yogsoth-ai/bridge-validation

Source yogsoth-ai/de-anthropocentric-research-engine ↗License Apache-2.0

Validate analogy depth and transfer viability. Ensures only deep structural analogies (not surface-level similarities) proceed to transfer.

SkillScore82Maintained

Automatic

Research pack

Last verified 8/22/2026

What it changes

Passed 18 of 22 test cases with the skill, and 13 of 22 without it.

Without skill59%

With skill82%

Checks it passed that the model alone missed

Applies analogy-quality-assessment as Stage 1 to classify depth.
Applies structural-mapping SOP in Stage 3 to verify structural consistency.
Formulates the core principle independently of biological source domain terminology.

and 8 more in the full report

6 fixed12 passed either way3 still failing1 broke

Pass-rate lift: +23 pp
Tokens: +21%
Agent turns: 0%
Response time: +4%

Model gemini-3.6-flashMeasured 8/22/2026v118 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-bridge-validation/SKILL.md https://app.decimal.ai/s/yogsoth-ai-bridge-validation/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add yogsoth-ai-bridge-validation, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/yogsoth-ai-bridge-validation/ and pins it in .decimal/skills.lock

decimalai skills add yogsoth-ai-bridge-validation

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-bridge-validation/SKILL.md https://app.decimal.ai/s/yogsoth-ai-bridge-validation/SKILL.md

Raw file: /s/yogsoth-ai-bridge-validation/SKILL.md ↗ · machine-readable summary at /s/yogsoth-ai-bridge-validation.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

After adapting an analogy between mechanical governor flyweights and rate-limiting algorithms, we need to verify that directional mapping holds. Which step and procedure should be used?

What was checked, without and with the skill
Checked	Without skill	With skill
Applies structural-mapping SOP in Stage 3 to verify structural consistency.	Missed	Passed

case-18 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md59 linessingle file

Bridge Validation

Validate analogy depth and transfer viability before committing resources to transfer.

Stages

Stage 1: Analogy Quality Assessment

Apply analogy-quality-assessment SOP to each candidate analogy. Classify depth:

Surface: Shared object attributes only (e.g., "both are round") — REJECT
Structural: Shared relational structure (e.g., "both use negative feedback to maintain homeostasis") — ACCEPT
Systemic: Shared higher-order constraints and causal structure — STRONG ACCEPT

Stage 2: Transfer Adaptation

For accepted analogies, test transfer viability using transfer-adaptation SOP:

Can the principle be stated independently of source domain?
Does the target domain have the necessary substrate for the principle?
What adaptations are needed to fit target constraints?

Stage 3: Structural Consistency Check

Verify the adapted transfer maintains structural consistency:

Mapped relations preserve directionality
Higher-order constraints are respected
No critical source elements are unmapped without justification
The transfer does not violate known target domain physics/logic

Minimum Yield

Metric	Floor
Analogies assessed	all candidates
Validated deep analogies	≥2
Transfer viability confirmed	≥2
Structural consistency verified	≥2

Available SOPs

| SOP | Role |

Track record

Benchmark

18 / 22

test cases passed, vs 13 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

yogsoth-ai / de-anthropocentric-research-engine

skills/bridge-validation/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Bridge Validation

Stages

Stage 1: Analogy Quality Assessment

Stage 2: Transfer Adaptation

Stage 3: Structural Consistency Check

Minimum Yield

Available SOPs

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills