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 naveedharri/benai-skills --skill marketing-analyticsgit clone --depth 1 https://github.com/naveedharri/benai-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/naveedharri/benai-skills/marketing-analytics)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/marketing-analytics"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/marketing-analytics/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/naveedharri/benai-skills/marketing-analytics"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/marketing-analytics.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 | $0.00185 | $0.01287 |
| Opus 5 | $0.00093 | $0.00643 |
| Sonnet 5 | $0.00037 | $0.00257 |
| Haiku 4.5 | $0.00018 | $0.00129 |
Grade A, and why
marketing-analytics 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 7d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marketing Analytics
One page, four questions: attention, conversion, revenue, retention. Every number carries its trend and its source. A scheduled task invokes this skill with a timeframe; the skill does the rest.
Mode selection
- No dashboard folder / no
config.mdfound, or the user asks to "set up" → SETUP. - A timeframe is given ("for yesterday", "for last week", a date range) and config exists → REFRESH.
- Ambiguous → ask one question, not five.
SETUP (first run)
- Locate or create the dashboard folder. Ask where it should live (default:
marketing-pulse/in the user's project folder). Copyassets/dashboard-template.htmlin asdashboard.html. - Interview for sources. Which of these does the business run, and through which tool?
- Revenue/subscriptions (Stripe, Paddle, ...)
- Site + conversion analytics (PostHog, GA4, Plausible)
- Content channels (YouTube, LinkedIn, X, ...)
- Email (Kit, Mailchimp, beehiiv)
- Community (Circle, Skool, Slack, Discord)
- Probe the connectors for each approved source (ToolSearch if deferred). For gaps: offer to connect, or mark the block
pending: true- the template renders honest placeholders. Never fake a number. - Write
config.mdin the dashboard folder: each source, the exact tool/IDs used, the metric definitions chosen, deploy target (Vercel / live artifact / local file), and anything learned probing (rate limits, missing fields).references/source-wiring.mdshows a complete worked example. - Run the first REFRESH end to end, then tell the user the one-line prompt to put in a scheduled task, e.g.:
Use the marketing-analytics skill to refresh the marketing dashboard for yesterday.
REFRESH (the scheduled run)
- Read
config.md+ the currentdata.js. Resolve the timeframe to complete days (24h = the last complete day; 7d/30d windows end on it). - Pull every configured source for the window. Follow
references/source-wiring.mdfor the field-tested access patterns and gotchas (Stripe filter shapes, PostHog queries, API lags). Oversized API responses: save to file and extract with jq/scripts - never page raw dumps through context. - Rewrite
data.jsto the contract inreferences/data-contract.md. Keep the header comments (they are the documentation). Every metric gets its delta (24h and 7d where the source allows). - Append the daily snapshot to
history/YYYY-MM-DD.json(the whole DASHBOARD_DATA object). This is the append-only DB that unlocks month-over-month. - Write the daily brief (the
briefarray): 3-5 sentences, numbers-first. Sentence 1 = the headline (revenue/net movement). Then: what drove any spike, which content converted, one retention/community observation, and at most one concrete action. No filler, no hype. - Verify: open
dashboard.htmland confirm it renders with the new data (no NaN, no empty sections that should have data). - Deploy per config (e.g.
vercel deploy --prod --yesfrom the folder, or update the live artifact). Skip silently if config says local-only. - Report: the live URL plus the 3 numbers that moved most, with deltas.
What ships with it
4 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.
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.
- 7d ago First seen · 55 lines · 185 tokens per session scan A e8f03131f88f
marketing-analytics is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed today), licensed MIT. It adds 185 tokens to every session and 1,287 once invoked, about $0.0009 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 2026-09-05.
Other skills, from other repositories
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.
media-higgsfield-explainer
A Higgsfield workflow for making non-photorealistic narrated explainer videos. It pairs each narration line with a 10-second animated clip and joins the clips into one finished video.