Ready to supercharge your AI agents?

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

Get Started Free →

AHP Weighting · yogsoth-ai | DecimalAI

scienceby yogsoth-ai

AHP Weighting

yogsoth-ai/ahp-weighting

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

SOP: Use the AHP (Analytic Hierarchy Process) to determine scoring-dimension weights, outputting a weight vector

SkillScore86Maintained

Automatic

Data Analyst pack

Last verified 8/22/2026

What it changes

Passed 19 of 22 test cases with the skill, and 12 of 22 without it.

Without skill55%

With skill86%

Checks it passed that the model alone missed

The boolean key cr_acceptable is set to false.
The field warnings is present in the JSON as an empty list.
The response includes a top-level boolean field named cr_acceptable.

and 9 more in the full report

9 fixed10 passed either way1 still failing2 broke

Pass-rate lift: +32 pp
Tokens: +31%
Agent turns: 0%
Response time: -3%

Model gemini-3.6-flashMeasured 8/22/2026v119 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-ahp-weighting/SKILL.md https://app.decimal.ai/s/yogsoth-ai-ahp-weighting/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add yogsoth-ai-ahp-weighting, 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-ahp-weighting/ and pins it in .decimal/skills.lock

decimalai skills add yogsoth-ai-ahp-weighting

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

Calculate AHP weights for exactly two factors: Feasibility and Risk. Feasibility is 3 times as important as Risk. Return the JSON object with matrix and weights.

What was checked, without and with the skill
Checked	Without skill	With skill
The output contains a valid weight distribution where Feasibility equals 0.75 and Risk equals 0.25.	Passed	Passed
The JSON contains the field comparison_matrix structured as a 2x2 matrix.	Missed	Passed

case-09 · 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.md38 linessingle file

AHP Weighting

Use the AHP (Analytic Hierarchy Process) to determine scoring-dimension weights, outputting a weight vector.

HARD-GATE

Pipeline

Precondition check: verify the dimension list is non-empty and its count is in the range [2, 9]
Dimension list confirmation: output the dimension list for the caller to confirm; if a comparison matrix is already provided, skip to step 4
Pairwise comparison matrix construction: for each pair of dimensions (i, j) assign a Saaty scale value (1-9); the matrix must satisfy a[j][i] = 1/a[i][j]
Eigenvector computation: normalize each column then take row means to obtain the priority vector (weights)
Consistency ratio check: compute the largest eigenvalue λ_max → consistency index CI = (λ_max - n)/(n-1) → CR = CI/RI (look up the Saaty RI table); CR < 0.1 is acceptable
Output: return the AHPWeights object; if CR > 0.1 attach revision suggestions

Output Format

{
  "dimensions": ["importance", "feasibility", "novelty", "impact"],
  "comparison_matrix": [[1, 3, 2, 2], [0.33, 1, 0.5, 0.5], [0.5, 2, 1, 1], [0.5, 2, 1, 1]],
  "weights": { "importance": 0.40, "feasibility": 0.15, "novelty": 0.23, "impact": 0.22 },
  "lambda_max": 4.02,
  "ci": 0.007,
  "ri": 0.90,
  "cr": 0.008,
  "cr_acceptable": true,
  "warnings": [],
  "revision_suggestions": []
}

Track record

Benchmark

19 / 22

test cases passed, vs 12 / 22 without

Adoption

Users: 1
Times used: 14

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/ahp-weighting/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

AHP Weighting

HARD-GATE

Pipeline

Output Format

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills