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 customer-intelligence-reportgit 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/customer-intelligence-report)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/customer-intelligence-report"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/customer-intelligence-report/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/customer-intelligence-report"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/customer-intelligence-report.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 Memory Poisoning · line 79 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00000 | $0.01373 |
| Opus 5 | $0.00000 | $0.00687 |
| Sonnet 5 | $0.00000 | $0.00275 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
customer-intelligence-report 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Intelligence Report
Turn a period of Fireflies meetings and Circle community posts into a recurring intelligence
report: what themes keep coming up, where people are in pain, which technical patterns recur,
and who is stuck. The deliverable is a BenAI-branded instant-ui HTML dashboard rendered from
a data file, so it is customizable and never static (see references/report-config.md).
Secrets: the Circle and Fireflies connectors authenticate through the MCP connection.
Never put an API key, token, space id, or email into the skill as a hardcoded secret, all
targeting values come from the run config. If you add publishing, use an env-var token and a
gitignored deploy dir (see report-config.md, Secrets and safety).
Steps
Track progress:
Task Progress:
- [ ] 1. Scope: confirm scope, cadence, sections (checkpoint)
- [ ] 2. Collect: pull the period from Fireflies and Circle
- [ ] 3. Analyze: cluster transcripts into themes
- [ ] 4. Assemble: build the WEEKS + LEXICON data
- [ ] 5. Build: render the instant-ui dashboard
1. Scope (checkpoint, before any heavy pull)
Confirm the run with the user. Present the options and wait for a pick, do not assume.
Read references/report-config.md for the choices. Confirm: sources (Fireflies, Circle, or
both, plus their targeting: organizer emails and Circle space ids), scope
(all / person / team), cadence (weekly / daily / custom), the trailing recurring window, and
which sections to include. Offer the default section catalog plus 3 to 5 optional sections
so they can shape it. Targeting values are config, never hardcoded secrets.
2. Collect
Pull the period from the configured sources. Both are optional and degrade gracefully: if one errors, continue with the other and note the outage.
- Fireflies meetings: read
references/fireflies-guide.md. - Circle posts: read
references/circle-guide.md. List meetings and posts first and report the counts to the user, then fan the transcript and post reading out to subagents that return small structured notes.
What ships with it
10 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/analysis-framework.md 3.9 KB
- references/circle-guide.md 2.5 KB
- references/dashboard-template.html 19 KB
- references/data-schema.md 4.3 KB
- references/fireflies-guide.md 3.5 KB
- references/instant-ui/build-rules.md 3.7 KB
- references/instant-ui/components.md 21 KB
- references/instant-ui/design-tokens.md 3.0 KB
- references/instant-ui/page-shell.md 5.5 KB
- references/report-config.md 4.9 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.
- 7d ago First seen · 96 lines · 0 tokens per session scan A d4eb64a05eaf
customer-intelligence-report is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,373 tokens. 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.