agentsclimarketplace

Pg analysis approval

Skill Exekiel179/pingouin-psych-stats/skills/pg-analysis-approval

Skill plugin for Claude Code, Codex & other AI agents: small, safety-first Pingouin workflows for psychology statistics — assumption checks, S0–S5 supervision gates, reproducible Python, and APA-style reporting.

Install
npx -y skills add Exekiel179/pingouin-psych-stats --skill pg-analysis-approval

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Review and approve Pingouin psychology analyses before final reporting. Use after data screening or statistical output and before interpretation to catch common problems: wrong test, ignored repeated measures, missing assumption checks, multiple-comparison errors, unsupported causal claims, incomplete reporting, or output-format mismatches.

SKILL.md

2.7 KB, 549 tokens by cl100k_base, as published. Nobody here has run it

PG Analysis Approval

Use as the final statistical checkpoint before writing conclusions or deliverables.

Load

Read:

  • ../../references/supervision-gates.md
  • ../../references/workflow-index.md
  • ../../references/apa-output-template.md if checking report prose.
  • ../../references/archive-contract.md when reviewing an archived run.

Read ../../references/pingouin-api-quickref.md only if an API/function choice is questionable.

Inputs

Review whatever is available:

  • User request and research question.
  • Dataset screening summary.
  • Pingouin code.
  • Pingouin result tables.
  • Draft interpretation/report.
  • Requested output format and figure/table requirements.

Approval Checklist

Check:

  • S0 Scope: design, outcome scale, unit of analysis, dependency structure.
  • S1 Data: columns, missingness, group sizes, repeated IDs, long/wide shape.
  • S2 API: current Pingouin function signature, no deprecated function, correct parameters.
  • S3 Assumptions: normality/homogeneity/sphericity/linearity/independence as relevant.
  • S4 Result: values come from output; df, p, CI, effect size, correction are present when needed.
  • S5 Interpretation: no unsupported causal, clinical, or construct-level overclaim.
  • Deliverable: requested format, language, tables, figures, and reproducibility needs are addressed.
  • Archive: exact code, numerical output, report source, and audit record are stored under one run directory.

Decision Labels

Use one label:

  • APPROVED: ready to report.
  • APPROVED_WITH_NOTES: acceptable but caveats must be included.
  • REVISE: fixable issue before reporting.
  • BLOCKED: missing data/design information or wrong model family.

Output Format

Decision: <APPROVED / APPROVED_WITH_NOTES / REVISE / BLOCKED>
Critical issues: <none or concise list>
Required fixes: <none or exact actions>
Reporting notes: <effect size, CI, correction, caveat, format>
Audit: S0 <status>; S1 <status>; S2 <status>; S3 <status>; S4 <status>; S5 <status>.

Hard Stops

Return BLOCKED if:

  • Outcome scale or dependency structure makes the selected test invalid.
  • Repeated/nested data were analyzed as independent rows.
  • A causal mediation/causal conclusion is requested from unsuitable data without caveat.
  • Required numerical output is absent but the user asks for final result prose.
  • The correct method is outside Pingouin's scope.

Gives 0 of the 12 instructions most research analysis skills give in 549 tokens

Counted across 1,063 of the 1,754 authors here whose files we hold, read 2026-08-06

  • generate a markdown reportin 32 of 1063, across 17 files
  • cite each claim's sourcein 31 of 1063, across 14 files
  • define the ideal customer profilein 20 of 1063, across 2 files
  • search for companies matching the criteriain 20 of 1063, across 2 files
  • assign a fit score from one to tenin 20 of 1063, across 2 files
  • format results in a scannable markdown templatein 20 of 1063, across 2 files
  • analyze the codebase to understand the productin 19 of 1063, across 1 file
  • ask clarifying questions about the value propositionin 19 of 1063, across 1 file
  • look for signals of immediate needin 19 of 1063, across 1 file
  • identify the target decision maker rolein 19 of 1063, across 1 file
  • suggest a personalized contact strategyin 19 of 1063, across 1 file
  • provide conversation starters for outreachin 19 of 1063, across 1 file

Said here and by no other author read

  • use before writing conclusions or deliverables
  • read the supervision gates reference
  • read the workflow index reference
  • check analysis scope and design
  • check data columns and shapes
  • check pingouin api signatures and parameters

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.