Stats Integrity
Use whenever you run statistical analysis for the social sciences (regression, hypothesis tests, econometrics) or read Stata (.dta) / SPSS (.sav) data in this workspace. Enforces an execute-don't-interpret boundary (surface estimates, don't volunteer causal claims), checks the analysis against a preregistration plan for HARKing, verifies reproducible seeds, and reproduces .dta/.sav estimates via R. Flags integrity risks; never certifies the analysis is sound.
Install
npx skills add ai4s-research/open-science --skill stats-integritygit clone --depth 1 https://github.com/ai4s-research/open-science.git /tmp/open-science
mkdir -p ~/.claude/skills
cp -r /tmp/open-science/runtime/skills/core/stats-integrity ~/.claude/skills/stats-integrityPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Analysis integrity (social science) Social science's decisive risk is not a crashing script — it is a **confident, provocative misreading** of a correct number, silent p-hacking, and results that don't replicate. Your job here is to **run analyses and surface raw output**, and to **withhold interpretation the design doesn't support**. Pepinsky's rule: *use the agent for tasks that follow rules; do not use it for tasks that generate answers, arguments, or interpretations.* ## Execute — don't interpret - Report the **estimate and its uncertainty** — coefficients, standard errors, confidence intervals, test statistics, p-values, N — exactly as the software produced them. - Do **not** volunteer causal or "provocative" claims. Regression and correlation are **associational**. Say "X is associated with Y", not "X causes / drives / leads to / increases Y", unless the *design* (RCT, IV, DiD, RDD, panel FE with a credible identification strategy) supports it — and then name the design. - Do not tell the user what they want to hear. If the result is null or ambiguous, say so plainly. ## Reproducible execution (fixed seeds + traceability) - Any randomised step (bootstrap, permutation, train/test split, resampling, MCMC) **must fix a seed**: `np.random.seed(...)`, `random_state=...`, or R `set.seed(...)`. - Every numeric claim in a report must be traceable to a **script + line + output** (provenance records this automatically when you write files).
Details
- Skill name
stats-integrity- Repository
- ai4s-research/open-science
- Path
runtime/skills/core/stats-integrity/SKILL.md- Repo updated
- 17 November 2026
FAQ
What does the Stats Integrity skill do?
Use whenever you run statistical analysis for the social sciences (regression, hypothesis tests, econometrics) or read Stata (.dta) / SPSS (.sav) data in this workspace. Enforces an execute-don't-interpret boundary (surface estimates, don't volunteer causal claims), checks the analysis against a preregistration plan for HARKing, verifies reproducible seeds, and reproduces .dta/.sav estimates via R. Flags integrity risks; never certifies the analysis is sound.
How do I install the Stats Integrity skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add ai4s-research/open-science --skill stats-integrity. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Stats Integrity popular?
It lives in ai4s-research/open-science, which has 2,105 GitHub stars and 231 forks.
Related skills
Computer Use
2.1kai4s-research/open-science
Use when a task needs an app on the user's own screen — a native desktop application (instrument control software, Origin, GraphPad, ImageJ, a reference manager, a spreadsheet), or a desktop browser window that needs window-level control. Read before the first `computer` call. Covers the observe-act-observe loop, why element indexes go stale, which action to prefer for which control, what "unverified" means and why it must never be reported as success, and the recovery for each error code. Not for page-level web automation (use the browser connector) and not for anything that can be done from
Domain Check
2.1kai4s-research/open-science
Use ONLY when the user asks to check, validate, review or audit analysis code for scientific correctness, or when you are the reviewer agent running its checks. Never run it unprompted as part of ordinary analysis work. Covers physics, earth/geo, biology, chemistry, social science and bioprocess/fermentation. Runs a deterministic domain-correctness gate that catches code which runs but is scientifically wrong (unit/dimension mismatch, Euclidean distance on lat/lon without a CRS, 0-based/1-based coordinate and strand errors, impossible SMILES valence, uncorrected multiple comparisons, averaging
Large File
2.1kai4s-research/open-science
Use BEFORE reading any data file that could be large (CSV/TSV, Parquet, HDF5, FITS, NetCDF, NDJSON, genomics FASTQ/FASTA/VCF/BAM, GRIB, ROOT, or big text/simulation logs like VASP OUTCAR). Returns a compact memory pointer — header/schema/shape/sample/key numbers — by introspection and sampling in bounded memory, so you never load a file bigger than the context window into the model. Reference data via the pointer; read specific ranges deterministically.
A B Test Design
3.4kOwl-Listener/designer-skills
Design an A/B experiment — hypothesis, variants, primary metric, and sample size. Use when a change can be measured quantitatively at scale. For observing behaviour qualitatively, use `test-scenario`.
Steve Jobs Design Review
2.7kwondelai/skills
Review designs, products, and features with Steve Jobs' standards: ruthless simplicity, focus, and end-to-end excellence. Use when the user mentions "Steve Jobs review", "design review", "product review", "what would Steve do", "insanely great", "this feels too complicated", "too many features", "product taste", "saying no", or "is this good enough to ship". Also trigger when critiquing a UI, feature, or roadmap for focus and simplicity, cutting scope to the essential, or pressure-testing the whole experience from first run to daily use. Covers the simplicity audit, the no list, design-is-how-
Accessibility Test Plan
3.4kOwl-Listener/designer-skills
Plan accessibility testing — assistive technologies, participant criteria, WCAG coverage, and session protocol. Use when scheduling testing with real AT users. Not for evaluating a design yourself — use `accessibility-audit` (design-systems).
Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.