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 reatlat/fullstory-claude-plugin --skill report-deckgit clone --depth 1 https://github.com/reatlat/fullstory-claude-pluginWrote 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/reatlat/fullstory-claude-plugin/report-deck)<a href="https://agentmods.dev/skills/reatlat/fullstory-claude-plugin/report-deck"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/report-deck/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/reatlat/fullstory-claude-plugin/report-deck"><img src="https://agentmods.dev/badge/skills/reatlat/fullstory-claude-plugin/report-deck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 70 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00048 | $0.00885 |
| Opus 5 | $0.00024 | $0.00443 |
| Sonnet 5 | $0.00010 | $0.00177 |
| Haiku 4.5 | $0.00005 | $0.00089 |
Grade A, and why
report-deck 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 10d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report Deck
Turn Fullstory research into a structured presentation. Works with any output format — Markdown for review, PPTX for slides, PDF for sharing.
When to Use
- "Turn this churn analysis into a deck for the board"
- "Export the funnel report as PDF"
- "Make slides from the weekly digest"
- "I need to present these findings to stakeholders"
Workflow
Step 1: Gather the findings
Use the relevant skill to pull the data first (funnel-doctor, retention-analyzer, weekly-digest, etc.). Don't skip the analysis — this skill formats, it doesn't investigate.
Step 2: Structure the narrative
Every good analytics deck follows this arc:
- Headline — the one thing to remember ("Checkout abandonment costs us $182K/year")
- The number — the metric that proves it (funnel table, trend, cohort)
- The why — session evidence, user quotes, frustration patterns
- The ask — what decision or action you need
Map each section to 1–3 slides. Never more than 3 slides per point.
Step 3: Build the deck
Write Markdown with slide breaks (---). Include:
- Slide title (the takeaway, not the topic — "Mobile users drop at payment" not "Payment Step Analysis")
- 1–2 bullet points per slide
- A table or code block for the key number
- Speaker notes (what to say, not what to read)
Example slide:
## Mobile users drop at payment
- 67% drop-off at payment step on mobile vs 22% on desktop
- 412 rage-clicks on "Apply Promo" button last 30 days
| Step | Mobile | Desktop |
|------|--------|---------|
| Cart | 10,000 | 8,000 |
| Shipping | 8,200 (82%) | 7,200 (90%) |
| Payment | 2,700 (33%) | 5,600 (78%) |
| Confirm | 2,100 (78%) | 5,200 (93%) |
> Session 84721: user taps promo button 6 times, nothing happens, force-quits app.
Speaker note: The promo button is 32px on mobile — below the 44px touch target. This isn't a pricing issue, it's a UI bug.
Step 4: Export
Ask the user which format they need, then use what's available:
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.
- 10d ago First seen · 95 lines · 48 tokens per session scan A 45a2065de96c
report-deck is a skill published in the GitHub repository reatlat/fullstory-claude-plugin (62 stars, last pushed 28d ago), licensed MIT. It adds 48 tokens to every session and 885 once invoked, about $0.0002 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
pdf-report
Generate a branded, audience-structured marketing report — executive summary, campaign report, channel deep-dive, competitor report, or monthly/quarterly review — assembled via pdf-generator.py with brand colors, logo, and fonts, and previewed for adjustments before finalizing. Pulls data from campaign-tracker.py…
honey-px
Read huge read-only text as PNG pages; big input cut.
release-sync
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.
lov-fill-form
Fill in Word document form templates (.docx) with user-provided data. Reads a template containing tables with label→value cell pairs, detects all fillable fields, and outputs a completed document. Handles CJK/Latin mixed text with proper font switching. Use this skill when the user wants to fill in a form template…
google-drive
Interact with Google Drive - search files, find folders, list contents, download files, upload files, create folders, move, copy, rename, and trash files. Use when user asks to: search Google Drive, find a file/folder, list Drive contents, download or upload files, create folders, move files, or organize Drive…
roblox-input
Use when handling Roblox keyboard, mouse, gamepad, touch, motion input, or cross-platform action binding.