Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add j4flmao/agent-skills --skill report-generationgit clone --depth 1 https://github.com/j4flmao/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/j4flmao/agent-skills/report-generation)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/report-generation"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/report-generation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/j4flmao/agent-skills/report-generation"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/report-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.06031 |
| Opus 5 | $0.00028 | $0.03016 |
| Sonnet 5 | $0.00011 | $0.01206 |
| Haiku 4.5 | $0.00006 | $0.00603 |
Grade A, and why
backend-report-generation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 648 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report Generation Skill
Purpose
Generate complex reports in multiple formats (PDF, Excel, CSV) from large datasets with async processing, scheduling, and reliable delivery.
Architecture Decision Trees
Format Selection
| Criterion | Excel (XLSX) | CSV | HTML | |
|---|---|---|---|---|
| Human readability | Excellent (fixed layout) | Good (tabular) | Poor (raw data) | Excellent (responsive) |
| Machine parsability | Poor | Good | Excellent | Poor |
| Page size control | Full control | Print layout | N/A | CSS print |
| File size (10K rows) | ~5-10MB (rendered) | ~1-2MB | ~500KB | ~2-3MB |
| Streaming support | No (full render) | Partial (worksheet) | Yes (row-by-row) | Yes |
| Interactive features | No | Formulas, filters | No | Links, JS |
| Accessibility | Poor (screen reader limited) | Moderate | Excellent | Excellent |
| Best for | Invoices, contracts, compliance | Financials, data analysis | Data export, ETL | Dashboards, email |
Decision: PDF for presentation/output. CSV for data export. Excel for analysis. HTML for screen display.
Rendering Strategy
| Criterion | Puppeteer/Chrome | wkhtmltopdf | PDFKit/jsPDF | Server-side lib (iText, TCPDF) |
|---|---|---|---|---|
| CSS support | Full (Chrome) | Limited (WebKit) | None (manual) | Limited |
| JavaScript rendering | Yes | No | No | No |
| Page headers/footers | Full HTML templates | Basic HTML | Manual | Built-in |
| Performance | Slow (~2s/page) | Medium | Fast | Fast |
| Memory | High (~200MB per browser) | Medium | Low | Low |
| Dependency | Chromium binary | wkhtmltopdf binary | Pure JS | Language-specific |
Decision: Puppeteer for complex visual reports. PDFKit for programmatic simple PDFs. wkhtmltopdf only if Puppeteer is too heavy.
Async Processing Decision
| Condition | Sync | Background Queue | Streaming |
|---|---|---|---|
| Rows < 1K | Yes | No | No |
| Rows 1K-100K | No (timeout risk) | Yes | For CSV only |
| Rows > 100K | No | Yes (chunked) | Yes (CSV only) |
| Format = PDF | No (slow) | Yes | No |
| Format = CSV | Possible | Overkill | Yes (preferred) |
| Scheduled reports | No | Yes | No |
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/excel-csv-export.md 16 KB
- references/pdf-generation.md 17 KB
- references/report-distribution.md 12 KB
- references/report-generation-advanced.md 12 KB
- references/report-generation-fundamentals.md 11 KB
- references/report-scheduling.md 23 KB
- references/report-templates.md 21 KB
- references/report-visualization.md 8.2 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 648 lines · 57 tokens per session scan A 4411c64f8a39
backend-report-generation is a skill published in the GitHub repository j4flmao/agent-skills (22 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 6,031 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
document-generation
Generate Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) documents and fill existing PDF forms, from real NetClaw data, with per-element provenance and no fabrication. Use when someone needs a deliverable rather than an answer — a change record to attach to a CR, an audit workbook for a compliance reviewer, a…
network-report-documents
The four standard NetClaw document compositions — a change-record Word document from a real ServiceNow CR plus device state, an interface/config audit workbook from real device queries, an executive summary deck with an embedded topology diagram, and a required PDF form filled from real data. Use when an operator asks…
document-processing-expert
Read, generate and modify office documents and PDFs from code: PDF extraction and forms, Word documents, Excel workbooks and PowerPoint decks. Use when the user mentions PDF, DOCX, XLSX, PPTX, Word, Excel, PowerPoint or spreadsheets, wants data extracted from documents, needs a report or invoice generated as a file…
cc-api-design-safety
A safety guide for designing REST API responses and creating downstream files such as Excel, CSV, PDF, or reconciliation files.
add-responder
Return a non-standard HTTP response (PDF, XLSX, stream, binary) instead of the default HTML template.
file-handling
File handling patterns — S3/R2/Vercel Blob storage, PDF generation, CSV/Excel import-export, file streaming, presigned URLs, multipart upload. Use when implementing file uploads to cloud storage, generating documents, processing large files, or building download endpoints.