data-master

In the author's own words, from each skill's SKILL.md.

• data-master

  Analyze datasets with preserved raw inputs, explicit cleaning decisions, reproducible figures and PDF reports. Full statistics for one tabular file; descriptive time-series analysis; integrity profiling for text, image, audio, geographic and mixed inputs. Use for data cleaning, EDA, group comparisons, statistical reports, 跑数据 or 数据分析 with a traceable evidence trail.

  SKILL.md on GitHub (opens in a new tab)

• data-cleaner

  Turn profile.json into a deterministic cleaning plan, execute only the planned operations, and prove byte-for-byte reproducibility. Additive-only.

  skills/data-cleaner/SKILL.md on GitHub (opens in a new tab)

• data-explorer

  Descriptive analysis and EDA on cleaned data: distributions, missingness mechanism screen, correlations, categorical structure. No p-values for group comparisons.

  skills/data-explorer/SKILL.md on GitHub (opens in a new tab)

• data-profiler

  Profile a dataset without changing it: shape, dtypes, missingness, duplicates, distributions, anomalies, candidate group/target/time columns. Emits profile.json.

  skills/data-profiler/SKILL.md on GitHub (opens in a new tab)

• data-router

  Classify any input path into one of eight modalities and emit a route manifest. First stage of data-master; no statistics, no cleaning.

  skills/data-router/SKILL.md on GitHub (opens in a new tab)

• data-transformer

  Derive analysis variables from cleaned data under an explicit, reversible transformation ledger. No silent recoding, no leakage.

  skills/data-transformer/SKILL.md on GitHub (opens in a new tab)

• data-validator

  Run the 8 Nature statistical gates and the journal checklist against the finished artifacts. Writes audit/final_audit.md and refuses the label submission-ready on a mandatory FAIL.

  skills/data-validator/SKILL.md on GitHub (opens in a new tab)

• deep-analyzer

  Optional modelling stage: regression, mixed effects, clustering, dimensionality reduction, forecasting. Only runs when the design supports it; every model carries diagnostics.

  skills/deep-analyzer/SKILL.md on GitHub (opens in a new tab)

• report-generator

  Assemble report.md, executive_summary.md and report.pdf from the artifacts. Every number is registered against its source; the PDF is the primary deliverable and the Markdown is the citable source.

  skills/report-generator/SKILL.md on GitHub (opens in a new tab)

• statistical-analyzer

  Choose and run the inferential test from the data structure, with effect sizes, CIs, multiplicity correction and explicit rejected alternatives. Refuses to report a p-value it cannot estimate.

  skills/statistical-analyzer/SKILL.md on GitHub (opens in a new tab)

• visualizer

  Decide and render one figure per argument: chart type chosen against alternatives, title states the finding, caption defines the encoding, body gives fact -> interpretation -> implication.

  skills/visualizer/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• beautify-github-readmeby oil-oil README design skill for Claude Code & Codex. 帮你把 GitHub README 做得好看又好懂。 1.9k stars · 1 skill
• female-portrait-directorby liyue-aigc A modular Codex Skill for directing and expanding detailed AI female portrait prompts. 1.7k stars · 2 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 412k stars · 5 skills
• agent-skillsby addyosmani Production-grade engineering skills for AI coding agents. 112k stars · 25 skills
• paperclipby paperclipai The open-source app everyone uses to manage agents at work 109k stars · 30 skills
• taste-skillby Leonxlnx Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages 106k stars · 1 skill