csv-to-report
Skill10 starsChanged 27 days agoMITView on GitHub
Convert a raw CSV into a structured, business-ready report using a 3-step framework — load + label, define rules, request structured deliverables. Trigger when the user says "csv to report", "report from this csv", "summarize this spreadsheet", "training log report", "compliance report", "turn this data into a report", or uploads a CSV and wants narrative output rather than raw numbers.
In this repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- blast-promptSkill
- client-outreachSkill
- content-draftSkill
- copywritingSkill
- design-accessibilitySkill
- design-buildSkill
- design-croSkill
- design-dimensionsSkill
- design-motionSkill
- design-researchSkill
- design-system-genSkill
- design-system-persistSkill
- design-tokens-emitSkill
- design-visual-qaSkill
- html-extractSkill
- parallel-buildSkill
- portable-html-portSkill
- qa-gateSkill
- route-codex-reviewSkill
- route-gemini-contextSkill
- route-three-brainSkill
- seo-auditSkill
- seo-backlinksSkill
- seo-clusterSkill
- seo-competitor-pagesSkill
- seo-content-briefSkill
- seo-contentSkill
- seo-dataforseoSkill
- seo-driftSkill
- seo-ecommerceSkill
- seo-firecrawlSkill
- seo-geoSkill
- seo-googleSkill
- seo-hreflangSkill
- seo-image-auditSkill
- seo-image-genSkill
- seo-local-unifiedSkill
- seo-pageSkill
- seo-programmaticSkill
- seo-schemaSkill
- seo-sitemapSkill
- seo-strategySkill
- seo-sxoSkill
- seo-technicalSkill
The file
Files
csv-to-report
Family: content-and-data Status: Stable
Purpose
Turn raw CSV data into a structured, narrative report. A small Python helper does the deterministic profiling/filtering/grouping; the skill adds the human layer — what the columns mean and what the business rules are.
The 3-step framework: Load + label → Define rules → Request the structured deliverable, then iterate (same data, new lenses). Common uses: training compliance, staff scheduling, billing audits, inventory snapshots.
Triggers
- "csv to report" / "report from this csv"
- "summarize this spreadsheet"
- "training log report" / "compliance report"
- "turn this data into a report"
Inputs
- CSV file (path or pasted)
- Column meanings (labels the agent needs to interpret correctly)
- Business rules (what counts as overdue, complete, required, etc.)
- Desired deliverable format
Steps
- Profile the data mechanically:
Returns row/column counts, per-column type + fill rate + distinct values, numeric stats, and top categories — so labeling is grounded in real data.python3 "${CLAUDE_PLUGIN_ROOT}/scripts/workflow/csv_to_report.py" --in <file.csv> --human # use `py` on Windows if python3 is absent - Load + label. Confirm what each non-obvious column means (abbreviations, joined fields, date formats). Flag data-quality issues the profile reveals (blanks, mixed types, totals rows mixed into data rows).
- Define rules. Capture explicit business rules ("annual training expires 365 days after Completion_Date"; "overdue = past expiration AND status != complete").
- Slice as needed using the helper's
--filter,--group-by, and--selectflags to answer specific questions deterministically. - Render the deliverable — table, grouped lists, narrative summary, or an exported sub-CSV — applying the business rules to the profiled data.
- Offer an iteration menu — filter, group, export, re-summarize on the same data ("now only clinical staff", "now group by training type").
Outputs
- Structured report (Markdown or HTML)
- Optional filtered sub-CSV(s) for downstream use
Dependencies
scripts/workflow/csv_to_report.py(required) — Python 3.10+, standard library only (no pandas)
Notes
Output quality scales with input quality: the helper surfaces clean-CSV issues
(inconsistent dates, merged cells, totals rows) so they're flagged before the
report is generated. Data stays local — see PRIVACY.md.
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
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.

