Ready to supercharge your AI agents?

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

Get Started Free →

Effect Size Extraction Tactic · yogsoth-ai | DecimalAI

researchby yogsoth-ai

Effect Size Extraction Tactic

yogsoth-ai/effect-size-extraction

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

Systematically extract effect sizes and conditions from papers for meta-analytic synthesis

SkillScore96Maintained

Automatic

Research pack

Last verified 8/22/2026

What it changes

Passed 23 of 24 test cases with the skill, and 16 of 24 without it.

Without skill67%

With skill96%

Checks it passed that the model alone missed

Response formats all 5 study extractions under a single top-level extractions array in valid YAML.
Response performs statistical synthesis pooling rather than extracting data from individual paper text.
Response recommends dare-scholar or alphaxiv tooling for querying PDF content and reading paper sections.

and 4 more in the full report

7 fixed16 passed either way1 still failing0 broke

Pass-rate lift: +29 pp
Tokens: +84%
Agent turns: 0%
Response time: +26%

Model gemini-3.6-flashMeasured 8/22/2026v123 of 24 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-effect-size-extraction/SKILL.md https://app.decimal.ai/s/yogsoth-ai-effect-size-extraction/SKILL.md

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

decimalai skills add yogsoth-ai-effect-size-extraction

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

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-effect-size-extraction/SKILL.md https://app.decimal.ai/s/yogsoth-ai-effect-size-extraction/SKILL.md

Raw file: /s/yogsoth-ai-effect-size-extraction/SKILL.md ↗ · machine-readable summary at /s/yogsoth-ai-effect-size-extraction.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

I have extracted standardized mean differences and variances for 12 randomized controlled trials comparing cognitive behavioral therapy to treatment as usual for major depression. Please run an inverse-variance random-effects meta-analysis to calculate the pooled overall effect size, 95% confidence interval, and heterogeneity metrics (I-squared and Tau-squared).

What was checked, without and with the skill
Checked	Without skill	With skill
Response performs statistical synthesis pooling rather than extracting data from individual paper text.	Missed	Passed

case-04 · 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.md99 linessingle file

Effect Size Extraction Tactic

Systematically extract quantitative effect sizes, study conditions, and precision metrics from included studies.

Stages

Stage 1: Paper Identification

Identify the specific sections of each paper containing quantitative results.

Locate results tables, figures, and statistical reporting sections
Identify primary and secondary outcomes
Flag studies reporting insufficient statistics for effect size calculation

Tools: dare-scholar (paper_content, paper_reading), alphaxiv (answer_pdf_queries)

Stage 2: Data Point Location

For each study, locate the exact data points needed for effect size calculation.

Sample sizes per group (N treatment, N control)
Central tendency (means, proportions, hazard ratios)
Variability (SD, SE, CI, IQR)
Test statistics (t, F, chi-square, z) when direct data unavailable
p-values as last resort for back-calculation

SOPs: effect-size-planning (determine what to extract)

Stage 3: Effect Size Calculation Planning

Plan the calculation method for each study based on available data.

Direct calculation from means + SDs
Conversion from test statistics (t → d, F → d, r → z)
Conversion between effect size families (OR ↔ d, r ↔ d)
Handling of multi-arm studies (shared control correction)
Cluster-adjusted effect sizes (design effect)

SOPs: effect-size-planning

Track record

Benchmark

23 / 24

test cases passed, vs 16 / 24 without

Adoption

Users: 1
Times used: 2

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/effect-size-extraction/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

Effect Size Extraction Tactic

Stages

Stage 1: Paper Identification

Stage 2: Data Point Location

Stage 3: Effect Size Calculation Planning

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills