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 sales-rep-analyzergit 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/sales-rep-analyzer)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/sales-rep-analyzer"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/sales-rep-analyzer/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/sales-rep-analyzer"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/sales-rep-analyzer.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 68 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 | $0.00113 | $0.01358 |
| Opus 5 | $0.00056 | $0.00679 |
| Sonnet 5 | $0.00023 | $0.00272 |
| Haiku 4.5 | $0.00011 | $0.00136 |
Grade A, and why
sales-rep-analyzer 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sales Rep Performance Analyzer
Analyze a sales rep's call recordings alongside CRM data to produce a comprehensive, evidence-backed performance report with grades, real transcript quotes, and actionable coaching recommendations. The output is a single, self-contained HTML dashboard in the BenAI neo-brutalist design system (embedded instant-ui guides), published to a shareable URL. It reads like something a VP of Sales would write after shadowing the rep for a month, grounded in evidence, not generic advice.
Phase 0: Gather Context
Use AskUserQuestion before pulling any data. Question scripts and rationale: references/context-questions.md. Combine into 2-3 calls (max 4 questions per call):
- Round 1, business context: the business/ICP/sales-qualified meeting, and the rep + their targets.
- Round 2, data sources and scope: which calls to analyze (all / date range / specific), and how to determine won vs. lost deals (user-provided, CRM cross-check, or both).
- Round 3, scoring and CRM: scoring framework (BANT, MEDDIC, custom, or default), and which CRM to cross-reference.
Checkpoint: summarize your understanding back to the user in a few sentences and get confirmation before pulling any data.
Phase 1: Data Collection
Follow references/data-collection.md for the full procedure per step:
- Identify the transcription source. Fireflies, Attio call recordings, or similar MCP tools. If none is connected, stop and ask the user to connect one.
- Pull the call list per the user's scope, and present it for approval/pruning before deep analysis.
- Pull full transcripts, NOT summaries. The single most important data quality rule in this skill. Verify each transcript contains speaker-attributed dialogue; never silently fall back to summaries. If more than 10 calls, use parallel Task subagents in batches of ~10-15.
- Discover CRM structure, then pull CRM data (if the user opted in): map every list, pipeline, and attribute first (paginate through ALL of them), then pull prospect records and build a per-prospect CRM context map.
- Pull email communications per prospect (metadata + semantic search + full bodies) and build an email evidence log for deal outcome verification.
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-standards.md 7.2 KB
- references/context-questions.md 2.9 KB
- references/data-collection.md 10 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-dashboard.md 5.0 KB
- references/scoring-frameworks.md 5.1 KB
- scripts/generate_report.js 15 KB runs code
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 · 71 lines · 113 tokens per session scan A a5602a7572e8
sales-rep-analyzer is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 1,358 once invoked, about $0.0006 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.
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-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.
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.