competitor-scan skillA
competitor-scan is agent-read markdown (skill) from naveedharri/benai-skills: Set someone up, from scratch, with their own weekly Competitor Radar dashboard. Use when a user wants to start tracking competitors, build their own competitor dashboard, monitor rivals' socials/SEO/subscribers, or "set me up with something like the competitor radar." Runs an interactive Q&A (niche, competitors, which platforms), can auto-discover and recommend competitors, wires up Apify + Firecrawl connectors, builds a branded HTML dashboard, deploys it to a stable Vercel URL, and schedules a .
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Competitor Radar Setup Turns "I want to track my competitors" into a live, self-refreshing, branded dashboard in one guided session. This skill sets up the machine; the `competitor-radar` skill is the machine. ## Step 1: Discovery Q&A (interactive) Ask, one topic at a time, adapting to answers: 1. **Niche / what they do** (so competitor discovery and framing are accurate). 2. **Competitors**, three modes: - They name them, or - They ask you to find and recommend competitors: search YouTube, the web, and their niche communities, propose 5-8 with a one-line why each, and let them confirm/trim, or - A mix (they name a few, you fill the rest). 3. **Platforms to track**: which of YouTube, Instagram, LinkedIn, TikTok, community (Skool/Circle), SEO. Only track what matters to their niche (a local business cares about Google reviews + local SEO; a creator cares about YouTube + shorts platforms). 4. **Brand**: colors, fonts, logo. If they have a design system or a site, extract from it; else use sensible defaults and confirm. 5. **Cadence**: weekly (default, Monday) or monthly (1st). And where to post it (Slack channel, email). …
Read the whole file at its exact version.
How to install
mdr add naveedharri/benai-skills/competitor-scan@git:20260720.71f54edmdr add naveedharri/benai-skills/competitor-scan@sha256:41f932af339884b5Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_gb3auj3ncycvdlba)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260720.71f54ed latest | 2026-07-20 | 71f54ed | 4,283 B | A | view · diff |
| git:20260720.898cddf | 2026-07-20 | 898cddf | 4,383 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4283 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
naveedharri/benai-skills · 65 stars · license MIT · pushed 2026-09-16 · branch develop
API
GET https://markdownregistry.com/api/v1/artifacts/art_gb3auj3ncycvdlba GET https://markdownregistry.com/api/v1/resolve?ref=naveedharri/benai-skills/competitor-scan GET https://markdownregistry.com/api/v1/blob/41f932af339884b5e14aa2faf259a008602da67b076ba20c8ece4f9dc3039c6a
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.