Pg workflow

Skill Exekiel179/pingouin-psych-stats/skills/pg-workflow

Run and resume the stateful Pingouin psychology statistics workflow. Use when the user wants an end-to-end, auditable analysis from intake through screening, analysis, approval, reporting, and archive, or asks to continue an existing analysis run.From its SKILL.md

Install

npx -y skills add Exekiel179/pingouin-psych-stats --skill pg-workflow

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.

SKILL.md

2.0 KB, 404 tokens by cl100k_base, as published. Nobody here has run it

PG Workflow

Use this skill as the cross-platform orchestration entry point. Claude Code users may use the /pg-* commands; Codex and other agents should invoke this skill directly.

Load

Read these references in order:

../../references/workflow-contract.md
../../references/archive-contract.md
../../references/intake-checklist.md when starting a new run
../../references/supervision-gates.md before approval
../../references/pingouin-optimization.md before generating Pingouin code

Use ../../scripts/workflow_engine.py for every state transition. Never edit run-manifest.json status by hand.

Dispatch

Find the active run under archive/analysis-runs/, or initialize one with scripts/init_analysis_run.py.
Read the manifest status.
Execute only the next allowed stage from workflow-contract.md.
Save the stage artifacts before advancing the state.
If approval returns REVISE, repair and return to analyzed; if BLOCKED, stop and explain the missing decision or data.
Finish only after workflow_engine.py check <run> passes at complete.

Required Handoff Block

Before each stage, return:

Run: <run-id>
State: <current>
Next: <target state and stage>
Inputs: <files/data available>
Outputs: <files this stage will create>
Guardrail: <highest-risk issue>

Hard Rules

Do not run inferential analysis before screening artifacts exist.
Do not report conclusions before an approved or approved_with_notes state.
Do not claim results from code that has not produced stored numerical output.
Do not copy raw participant data into an archive unless the user explicitly confirms the privacy handling.
Keep the S0-S5 audit line in the final handoff.

What ships with it: 1 file

271 B alongside SKILL.md

agents/

openai.yaml271 B