--- name: Data Analysis Loop slug: data-analysis-loop category: Data description: Data Analysis Loop performs iterative exploratory analysis on a dataset, testing one hypothesis at a time and only keeping findings that reproduce with a meaningful effect size. Use it for open-ended discovery when every claim needs a computed number behind it. github: "https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/data-analysis" language: Python stars: 166 forks: 19 install: "npx degit https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/data-analysis ~/.claude/skills/data-analysis" installs_to: ~/.claude/skills/data-analysis source_path: loops/data-analysis/SKILL.md collection_size: 25 category_size: 812 collection_url: "https://dirskills.com/collections/gaasher/Agent-Loop-Skills" added: 2026-09-08T05:34:40.988Z last_synced: 2026-09-08T05:34:40.988Z canonical_url: "https://dirskills.com/skills/data-analysis-loop" --- # Data Analysis Loop Data Analysis Loop performs iterative exploratory analysis on a dataset, testing one hypothesis at a time and only keeping findings that reproduce with a meaningful effect size. Use it for open-ended discovery when every claim needs a computed number behind it. **Install:** ```bash npx degit https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/data-analysis ~/.claude/skills/data-analysis ``` ## README # Data Analysis Loop A **hypothesis → verify** reflection loop over a dataset. The artifact is a findings report; the feedback signal is **verification** — a finding only counts if re-running the computation confirms it at a meaningful effect size. The discipline this enforces: **no insight without a number behind it.** A plausible claim the data does not support is discarded, not softened; every line in the report can be reproduced from the dataset. ## When to use Use this for open-ended, self-checking exploration of a bound dataset where each finding must survive an independent re-computation. Default to broad exploration across the columns; if the user gives a focus question, let it steer the hypotheses. Not for diagnosing one known anomaly or for checking an external claim against the literature. ## Setup Resolve bindings interactively. If `loop.run.yaml` exists in the working dir, load it, confirm the values in one line, and skip to the loop. Otherwise: on Claude Code (the `AskUserQuestion` tool is available) infer a likely value for each binding and present it as the recommended option; on other hosts ask each as a quoted plain-text prompt. Then write `loop.run.yaml` (format: `examples/run.example.yaml`) and confirm the values before creating any other files. | binding | meaning | default | how to infer | |---|---|---|---| | `` | data file to analyze (CSV/TSV/Parquet/…); read-only ground truth | — | scan the working dir for a data file | | `` | optional analysis focus; omit to explore broadly | — | ask the user; else leave unbound | | `` | output findings file | `/findings.md` | — | | `` | interpreter that runs analysis snippets in the user's env | `python3` | `pyproject.toml`/`.venv`/`uv` in the working dir | | `` | where snippets + ledger live | `./sandbox` | — | | `` | max iterations | 8 | — | | `` | stop after N consecutive iters with no new verified finding | 2 | — | Analysis snippets run in the **user's environment** via ``, so they may use whatever the user has installed. Keep helper code **stdlib-first** (`csv`, `statistics`): if a snippet needs `pandas`/`numpy`, probe with `try/except ImportError` and degrade to a stdlib path, or offer a consented `uv pip install "pandas=="` — never assume the package is installed. ## The loop Copy this checklist and tick items off: - [ ] Iteration 0 — profile `` (shape, types, ranges, missingness); record nothing as a finding. - [ ] Propose one specific, checkable hypothesis (steered by ``; not already settled). - [ ] Compute it: write `/iter/analysis.py`, run with ``, redirect to `out.txt`. - [ ] Verify: re-derive the key number a second way; judge against a stated effect-size bar. - [ ] Supported → append finding to `` (`verified`); else log `refuted`, do not add it. - [ ] Append a ledger row; stop on plateau (``) or ``. **Iteration 0 — profile.** Write and run a snippet that reports the shape of ``: columns, inferred types, row count, and a quick summary (ranges, category counts, missingness). This grounds the hypotheses; record nothing as a finding yet. **Then, until stop (dry or budget):** 1. **Propose one hypothesis.** A single, specific, checkable claim — e.g. "enterprise orders average higher value than consumer", "mobile has a higher return rate than other channels", "order value rises with signup tenure". Let `` steer it; do not repeat a hypothesis already settled. 2. **Compute it.** Write `/iter/analysis.py` that loads `` and computes the relevant statistic **plus an effect size** (a group-mean difference, a rate gap, a correlation — not just a yes/no). Run it with ``, redirecting output to `/iter/out.txt` (never flood your context). 3. **Verify — the gate.** Re-derive the key number a second, independent way (a different grouping, a recount, or a sanity cross-check) and confirm the two agree. Then judge honestly: does the result **support the hypothesis at a meaningful effect size**, or is it negligible / within noise? Decide "meaningful" against a bar you state up front and apply consistently — a minimum effect size scaled to the group sizes and noise (e.g. roughly |Cohen's d| ≳ 0.2, risk ratio ≳ 1.5, or |r| ≳ 0.1, tightened when groups are small) — so the keep/refute threshold does not drift between iterations. - **Supported** → append a finding to ``: the claim, the exact numbers, the effect size, and the method (so it is reproducible). Mark it `verified`. - **Not supported / negligible** → record it as `refuted` in the ledger and do **not** add it to the report. A null result is a real outcome, not a failure to hide. 4. **Log** one ledger row and continue. ## Ledger `/ledger.tsv`, tab-separated, never commas in the text. Header: ``` iter hypothesis effect status ``` `status` ∈ {`profile`, `verified`, `refuted`}. Example: ``` iter hypothesis effect status 0 dataset profile - profile 1 enterprise orders average higher value than consumer 185 vs 109 (+70%) verified 2 returns differ by region North 0.16 vs South 0.14 (negligible) refuted 3 mobile has a higher return rate than web/store 0.30 vs 0.10 verified ``` Report the **best** outcome: the `` path, the count of verified findings, and the hypotheses refuted (so the user sees what was checked and ruled out, not just what survived). ## Constraints - **No claim without a computed number.** Every finding in `` carries the figures and the method that produced it; if you cannot compute it, you cannot claim it. - **Verify before recording.** The independent re-derivation in step 3 is the gate — a finding that does not reproduce, or whose effect is within noise, does not enter the report. - **Report effect sizes, not just direction**, and do not inflate a correlation into a causal claim — say "associated with", and note confounders when the data cannot separate them. - **One hypothesis per iteration**, so each finding is attributable, and skip hypotheses already settled. - **Only read ``** — never modify it, because it is the ground truth every finding is checked against. The sandbox is self-contained (no `../` escapes). - Do not pause the loop to ask whether to continue; run until it goes dry or hits the budget. ## Stops - **Dry** — `` consecutive iterations add no new verified finding. - **Budget** — `` iterations reached.