Skip to main content
affpapa.org
RU EN
skill CX Codex

reporting-pipelines — Claude Code skill: CSV/JSON/Markdown reports

A skill that fixes one pattern for report exports: collect data, normalize it, write CSV/JSON/Markdown with timestamped names into reports/.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add bobmatnyc/claude-mpm-skills --skill reporting-pipelines -a claude-code
Open on GitHub

What reporting-pipelines does

The skill lays out a repeatable reporting flow. A CLI or script produces structured data, then the output goes to CSV, JSON or Markdown with a date suffix in the filename and lands in reports/ or tests/results/. Five steps cover it: collect base data, normalize into rows and records, export with timestamps, print key metrics to stdout, store the files.

Two worked examples come with it. gitflow-analytics runs with a config and a week count, emitting CSV plus a Markdown narrative report with a date suffix. The script edgar/scripts/create_csv_reports.py reads a JSON results file and writes three outputs: executive_compensation_<timestamp>.csv, top_25_executives_<timestamp>.csv and company_summary_<timestamp>.csv; it uses pandas for sorting and percentile calculations.

Naming rules are plain: YYYYMMDD or YYYYMMDD_HHMMSS suffixes, one output directory per repo, an explicit prefix such as narrative_report_. When a file never shows up, check whether the output directory exists and is writable — that is the usual culprit. For large CSVs the skill advises filtering or aggregating before export and keeping a summary CSV around for a quick read.

What it helps with

  • export a timestamped CSV report from script output
  • standardize export paths and filenames across repos
  • sort rows and compute percentiles before writing the file
  • print key metrics to stdout without opening the report
  • split one JSON results file into several themed CSVs

Example prompts for the agent

  • build the report for the last 8 weeks and drop a timestamped CSV into reports/
  • export results to CSV and Markdown with YYYYMMDD_HHMMSS suffixes
  • read the JSON results file and write three summary CSVs into tests/results/

How to install reporting-pipelines

1Skills CLI (Vercel)

npx skills add bobmatnyc/claude-mpm-skills --skill reporting-pipelines -a claude-code

2Manually: put the files in place

~/.claude/skills/reporting-pipelines/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/reporting-pipelines/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about reporting-pipelines

How do I install reporting-pipelines in Claude?

Run npx skills add bobmatnyc/claude-mpm-skills --skill reporting-pipelines -a claude-code. The skill lands at ~/.claude/skills/reporting-pipelines/SKILL.md.

What does reporting-pipelines do?

It defines a reporting flow: collect data, normalize it, export CSV/JSON/Markdown with timestamped filenames, summarize metrics, and store outputs in reports/ or tests/results/.

What does create_csv_reports.py need to run?

It reads a JSON results file and uses pandas for sorting and percentile calculations. It writes three CSVs: executive compensation, top 25 executives, and a company summary.

Source text

SKILL.md · MIT 
---
name: reporting-pipelines
description: Reporting pipelines for CSV/JSON/Markdown exports with timestamped outputs, summaries, and post-processing.
user-invocable: false
disable-model-invocation: true
version: 1.0.0
category: universal
author: Claude MPM Team
license: MIT
progressive_disclosure:
  entry_point:
    summary: "Generate CSV/JSON/markdown reports with timestamped filenames and summary outputs."
    when_to_use: "Building reporting flows, exporting analytics results, or standardizing CSV/JSON/markdown outputs across projects."
    quick_start: "1. Run the CLI that produces base data 2. Export CSV/JSON/markdown with timestamps 3. Save to reports/"
tags:
  - reporting
  - csv
  - json
  - markdown
  - analytics
---

# Reporting Pipelines

## Overview

Your reporting pattern is consistent across repos: run a CLI or script that emits structured data, then export CSV/JSON/markdown reports with timestamped filenames into `reports/` or `tests/results/`.

## GitFlow Analytics Pattern

```bash
# Basic run
gitflow-analytics -c config.yaml --weeks 8 --output ./reports

# Explicit analyze + CSV
gitflow-analytics analyze -c config.yaml --weeks 12 --output ./reports --generate-csv
```

Outputs include CSV + markdown narrative reports with date suffixes.

## EDGAR CSV Export Pattern

`edgar/scripts/create_csv_reports.py` reads a JSON results file and emits:

- `executive_compensation_<timestamp>.csv`
- `top_25_executives_<timestamp>.csv`
- `company_summary_<timestamp>.csv`

This script uses pandas for sorting and percentile calculations.

## Standard Pipeline Steps

1. **Collect base data** (CLI or JSON artifacts)
2. **Normalize** into rows/records
3. **Export** CSV/JSON/markdown with timestamp suffixes
4. **Summarize** key metrics in stdout
5. **Store** outputs in `reports/` or `tests/results/`

## Naming Conventions

- Use `YYYYMMDD` or `YYYYMMDD_HHMMSS` suffixes
- Keep one output directory per repo (`reports/` or `tests/results/`)
- Prefer explicit prefixes (e.g., `narrative_report_`, `comprehensive_export_`)

## Troubleshooting

- **Missing output**: ensure output directory exists and is writable.
- **Large CSVs**: filter or aggregate before export; keep summary CSVs for quick review.

## Related Skills

- `universal/data/sec-edgar-pipeline`
- `toolchains/universal/infrastructure/github-actions`

© Claude MPM Team · MIT · bobmatnyc/claude-mpm-skills

Similar skills

All skills for Data and databases →
scenario-admin-analytics scenario-labs A skill that answers Scenario admin analytics questions: Creative Unit consumption, most-used models, usage by user or project. CX Codex +1 345installs business-analytics-reporter ailabs-393 Reads a CSV of sales and revenue, finds weak spots and suggests improvement strategies. Useful when you need a business performance report without manual math. CX Codex +1 2,200installs firecrawl-dashboard-reporting firecrawl Reads metrics from public or signed-in web dashboards through Firecrawl and turns them into reports, summaries, or date-range tables. CX Codex +1 31,600installs receipts official Anthropic Generates a personal Claude Code activity report from local session transcripts — for justifying spend to a manager or self-review. 2,052installs finance-manager ailabs-393 Turns bank statements in PDF or CSV into a savings rate, category breakdown and an HTML report with charts. Useful when you want to see where the money goes. CX Codex +1 2,500installs cargo-analytics getcargo This skill downloads Cargo run results and exports segment data to CSV or JSON. Use it to retrieve output files or check run and batch counts. CX Codex +1 9,900installs

From the same set65

testing-anti-patterns A skill for spotting tests that verify mock behavior, add test-only production methods, or use incomplete mocks. CX Codex +1 368installs vercel-deployments-builds Walks through the Vercel deployment lifecycle: builds, previews, release phases and rollback. Useful when you configure build output or control releases. CX Codex +1 368installs stacked-prs A skill that walks the agent through building stacks of dependent pull requests, where each branch grows from the previous one instead of main. Useful when a large feature is split into phases. CX Codex +1 362installs better-auth-core A skill for wiring Better Auth into TypeScript apps: the instance, server handlers, client, and sessions. Useful when you need auth running without digging through docs. CX Codex +1 358installs fastapi-local-dev A runbook skill for FastAPI: Uvicorn with reload during development, Gunicorn with UvicornWorker in production. CX Codex +1 347installs headlessui A skill covering Headless UI: unstyled React and Vue components with keyboard navigation and ARIA built in. Useful when you want your own design without losing accessibility. CX Codex +1 345installs vercel-networking-domains A skill that walks the agent through Vercel domains, redirects, rewrites, headers and edge cache. Useful when you change traffic behavior rather than app code. CX Codex +1 344installs svelte Get Svelte 5 guidance for reactive components and SvelteKit apps. Use it when building UI state, bindings, routes, or data-loading flows. CX Codex +1 343installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor