agentleFS
AndreasADLAndreasADL/ai-papermill/.claude/skills/analysis-plan/SKILL.md

analysis-plan

Skill0 starsChanged 47 days agoMITView on GitHub

Write a preregistration-style analysis plan before any confirmatory analysis. Use after literature scan and data scouting, before touching outcome data. Output is the GATE 1 document the user approves.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. CHU-Brest/skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write analysis/plan.md BEFORE running any model on the outcome.

    line 8
  2. Very specific:

    If N is fixed by the dataset: sensitivity analysis — smallest effect detectable at 80% power (e.g., via statsmodels.stats.power).

    line 28
  3. Distinctive:

    No outcome-involving analysis before approval.

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Analysis Plan (preregistration-style)

Write analysis/plan.md BEFORE running any model on the outcome. Structure:

1. Research question & hypotheses

  • Numbered, directional where justified by literature (H1, H2…). Each with a one-line rationale citing lit_review.md.
  • Explicitly separate confirmatory hypotheses from planned exploratory questions.

2. Data

  • Dataset(s), N, unit of analysis, years. Inclusion/exclusion criteria (defined BEFORE looking at outcomes).
  • Exact variable operationalizations: name in dataset, coding, transformations (e.g., log income), scale handling (sum vs. mean score, reliability via Cronbach's alpha if items available).

3. Missing data

  • Expected mechanism, planned handling (complete cases if <5% missing; otherwise multiple imputation or explicit justification). Report sensitivity either way.

4. Statistical models

For each hypothesis: the exact model (e.g., "OLS: outcome ~ predictor + age + sex + education, HC3 robust SEs"; "Pearson r with Fisher CI"; "multilevel model, random intercept for country"). Specify:

  • Estimator, covariates and why (confounders from literature, not outcome-driven selection)
  • Effect size metric + 95% CI (r, standardized beta, Cohen's d, OR…)
  • Inference criterion: alpha; multiple-comparison correction across hypotheses (Holm or FDR — state which)

5. Power / sensitivity

  • If N is fixed by the dataset: sensitivity analysis — smallest effect detectable at 80% power (e.g., via statsmodels.stats.power). State whether literature-typical effects are detectable. If not, flag at GATE 1.

6. Assumption checks & contingencies

  • Which diagnostics (linearity, heteroscedasticity, influential points, distributional checks) and pre-specified fallbacks (e.g., "if residuals heavy-tailed → Spearman + robust regression as sensitivity").

7. Robustness checks

  • 2–4 planned: alternative operationalizations, subsets, added/removed covariates, alternative estimators.

Rules

  • No outcome-involving analysis before approval. Descriptives of predictors/demographics for planning are OK; anything involving the outcome is not.
  • Any post-approval deviation goes in a "Deviations" section of plan.md with justification, and is labeled in results.
  • At GATE 1, present the user a ≤15-line summary and ask for approval or edits.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.