mschwarzmueller/ai-agents-workflows-course/create-report
Claude Code and agent skill by mschwarzmueller/ai-agents-workflows-course
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Builds polished, self-contained HTML analytics reports from provided findings using a fixed style template. Use this skill when asked for a report, HTML summary, stakeholder readout, dashboard page, or styled presentation of analysis results. Do not use to perform the underlying analysis (use data-analytics), export an existing report to PDF (use export-report-pdf), or build slide decks.
Install
npx vskill@latest install mschwarzmueller/ai-agents-workflows-course/create-reportSKILL.md
Create Report
Required resources
- Before authoring, read and copy `assets/report-template.html`. It is the reusable output skeleton and visual system.
- Before finalizing, read `references/report-quality-checklist.md`. It defines content, privacy, accessibility, standalone, and visual checks.
- Resolve `scripts/validate-report.py` relative to this
SKILL.mdand run it against every completed report.
Rules
- Analyze first. If numbers are missing, use
data-analyticsbefore writing HTML. - Copy the template to the output path, then replace every
{{TOKEN}}; keep its structure and CSS tokens. - Self-contained HTML only: inline CSS/SVG, no CDNs, remote assets, or build step. It must open via
file://. - Do not invent or recalculate metrics here; present the supplied findings.
- Omit raw PII unless the user explicitly requests it. Only then may the validator use
--allow-pii.
Workflow
- Confirm title, period, KPIs, breakdowns, and methodology notes from the analysis.
- Read and copy `assets/report-template.html` to
reports/<topic>-<period>.html; createreports/if needed. - Replace all template tokens. Fill the header, KPI cards, chart, table, takeaways, and methodology footer.
- Remove unused optional sections instead of leaving examples or placeholder content.
- Read `references/report-quality-checklist.md` and apply every relevant check.
- Run
python3 scripts/validate-report.py --input <absolute-report-path>after resolving the script from this skill directory. Fix errors and rerun until it exits0; add--allow-piionly for an explicit raw-PII request. - Open the report through
file://and visually inspect desktop and narrow layouts. If the user also needs PDF, useexport-report-pdfafter HTML validation.
Style
- Put KPIs above the fold; use one primary chart unless more are requested.
- Use tables for exact values and charts for trends or composition.
- Use the template's CSS variables; do not introduce a competing visual system.
- Keep copy sparse: labels, numbers, and one-line takeaways.
- Always include a methodology footer with source, filters, metric definitions, and caveats.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingcode/claude-data-analysis/.agents/skills/create-report/SKILL.md
Popularity
- Repository stars
- 71
- Repository forks
- 70
- 7-day trend score
- 21
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/mschwarzmueller/ai-agents-workflows-course/create-report)