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 superamped/ai-marketing-skills --skill competitor-discoverygit clone --depth 1 https://github.com/superamped/ai-marketing-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/superamped/ai-marketing-skills/competitor-discovery)<a href="https://agentmods.dev/skills/superamped/ai-marketing-skills/competitor-discovery"><img src="https://agentmods.dev/badge/skills/superamped/ai-marketing-skills/competitor-discovery/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/superamped/ai-marketing-skills/competitor-discovery"><img src="https://agentmods.dev/badge/skills/superamped/ai-marketing-skills/competitor-discovery.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 | $0.00053 | $0.01141 |
| Opus 5 | $0.00026 | $0.00571 |
| Sonnet 5 | $0.00011 | $0.00228 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
competitor-discovery 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 12d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitor Discovery
Usage
Use when you don't know who your competitors are, when entering a new market, or when refreshing the competitor list after a pivot or market shift.
Process
Step 1: Gather Inputs
Ask the user for:
- Product description — what it does, what category it's in, key features
- Target audience — who buys or uses the product (role, industry, company size)
- Known competitors (optional) — names or URLs to include without searching
- Number to find (optional) — default: 5-7
Step 2: Build Search Queries
Construct 4-6 search queries mixing these angles:
- Category: "[category] tools 2025 2026" or "[category] software"
- Alternative: "[product name] alternatives" or "tools like [product name]"
- Problem: "[primary use case] solution" or "[pain point] tool"
- Audience: "best [category] for [target company type]" or "[category] for [target role]"
- Comparison: "best [category] compared" or "top [category] platforms"
- Review sites: "[category] G2" or "[category] Capterra" (to mine company names from lists)
Tailor queries to the product type. A B2B SaaS product needs different queries than a marketplace or agency service.
Step 3: Search and Collect
Run web searches for each query. For each result:
- Extract company names and domains that appear across multiple results
- Pull companies listed on review/comparison sites (G2, Capterra, etc.) — these are strong signals
- Skip aggregator sites themselves, job boards, news articles about funding, and clearly unrelated results
Compile a candidate list of 8-12 companies. For each, note:
- Name
- URL (homepage)
- How found — which search queries surfaced them
Rank candidates by frequency — companies appearing in 3+ different searches are almost certainly direct competitors.
Step 4: Quick Profile Each Candidate
For each candidate, fetch their homepage (and pricing page if easily accessible) and extract:
- One-liner — what they say they do, in their own words
- Target audience signals — who the site speaks to
- Overlap — how directly they compete (direct / adjacent / tangential)
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.
- 12d ago First seen · 123 lines · 53 tokens per session scan A a13c2361ab1f
competitor-discovery is a skill published in the GitHub repository superamped/ai-marketing-skills (67 stars, last pushed 25d ago), licensed MIT. It adds 53 tokens to every session and 1,141 once invoked, about $0.0003 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
newsjack-detector
Monitor current news and reaction signals, then decide which are credible newsjacking opportunities for a client. Uses the local monitoring engine for evidence, but the skill owns PR judgment, brand safety, standing, decay, angle fit, and handoff.
crisis-holding
Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).
voice-extractor
Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta function-word vector, MATTR lexical diversity, sentence-length burstiness, Biber Dimension-1 register…
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
fact-check
Extract factual claims from PR copy, verify each claim independently, attach concrete citations, and warn when certainty is low. Runs each claim through proven newsroom verification methods (lateral reading, source-tier climbing, provenance pillars, triangulation, calibrated rating) and puts the burden of proof on the…
pr-calendar
Turn the Medialyst PR calendar feed into a brand-specific, lead-time-aware plan. Pull source-backed upcoming moments, keep only the few a brand has real standing to own, schedule backward from the event date, screen out tone-deaf hooks, and hand selected moments to angle and journalist prep ahead of time. The planned…