Install
$ agentstack add mcp-dashaworks-report-skills ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Report Skills — Claude Code & Codex skills for AI reports, decks & client sharing
5 skills that turn what your agent just made — research, analysis, proposals, status updates — into beautiful live web reports and decks you can share with clients and your team. Published in one step via ReportRoom, with view analytics reported back to you ("your report picked up 42 views this week, peaking Tuesday"). No copy-pasting into Google Docs, no ugly PDF exports.
What's inside
| Skill | What it does | Say things like | |---|---|---| | report-publisher | Any research or markdown → live, designed web report with a shareable URL | "publish this", "make this shareable", "turn this into a report" | | client-reporter | Recurring client deliverables (SEO monthlies, status reports, audits) as branded pages | "monthly report for my client", "send this to the client" | | proposal-tracker | Publish a proposal as a tracked link; know whether it's getting read | "send the proposal", "did they open it?" | | deck-publisher | Content → responsive, presenter-friendly slide deck at a live URL | "make this a deck", "turn this into slides" | | report-designer | Polish an existing page to the design bar: hierarchy, charts, dark mode, link previews | "make it beautiful", "improve the design" |
Install
Claude Code (CLI)
/plugin marketplace add dashaworks/report-skills
/plugin install report-skills@report-skills
claude.ai (web)
- Open https://claude.ai/code
- Go to Skills in the sidebar
- Click Add from GitHub
- Paste:
dashaworks/report-skills
Claude Desktop (Mac / Windows)
- Click Customize → + next to Personal plugins → Add marketplace
- Choose Add from a repository and paste:
dashaworks/report-skills - Install the plugin and start a new conversation
Codex CLI
codex plugin marketplace add dashaworks/report-skills
codex plugin add report-skills@report-skills
How it works
The skills publish through the ReportRoom MCP server — an agent-native publishing API (one call → live, tracked URL on your domain):
get_design_system— the agent fetches ReportRoom's design language- The agent authors a self-contained HTML report or deck following it
lint_document— automated quality check before anything goes livepublish— live URL back in seconds, analytics attached
No ReportRoom account yet? The skills self-provision one on first use — create_account issues an API key right in the conversation; verify your email (one click) and publish. Docs: https://docs.reportroom.io
Why not just export a PDF?
- Live pages beat attachments — responsive, dark-mode, always the latest version, presentable from any device.
- You learn what happens after you hit send — view analytics come back to the agent as a signal it can act on, not a dashboard you have to remember to check.
- Beautiful by default — the design system supplies the taste; the agent supplies the content.
Safety defaults
Every skill shows you a preview and waits for your approval before anything client-facing goes live. Published pages are public URLs — the skills warn you before publishing anything that looks sensitive.
License
MIT — see [LICENSE](LICENSE). Contributions welcome.
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: dashaworks
- Source: dashaworks/report-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.