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 SupercmoHQ/superCMO-skills --skill researching-competitor-adsgit clone --depth 1 https://github.com/SupercmoHQ/superCMO-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/supercmohq/supercmo-skills/researching-competitor-ads)<a href="https://agentmods.dev/skills/supercmohq/supercmo-skills/researching-competitor-ads"><img src="https://agentmods.dev/badge/skills/supercmohq/supercmo-skills/researching-competitor-ads/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/supercmohq/supercmo-skills/researching-competitor-ads"><img src="https://agentmods.dev/badge/skills/supercmohq/supercmo-skills/researching-competitor-ads.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 | $0.00133 | $0.02380 |
| Opus 5.5 | $0.00053 | $0.00952 |
| Sonnet 5.5 | $0.00027 | $0.00476 |
| Haiku 4.5 | $0.00013 | $0.00238 |
Grade A, and why
researching-competitor-ads 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitor ads
Analyze what competitors are advertising, work out what is holding, and map what the category
covers. Research only — nothing is generated, posted or planned here. Deciding what to make
next is planning-campaigns' job.
Workflow
Step 1: Settle who the competitors are
Three ways to find out. Try them in order, and stop at the first one that works.
- Read them from
competitors.mdin./supercmo-company. Where it is absent or empty, move on. - Ask the user, for a name and a website for each competitor.
- Find candidates, only where the user doesn't know. Call
url_extractionon the user's own website to learn what they sell in their own words, thensocial_researchonmeta_ad_library/search_adsusing those words. Each ad names the advertiser who ran it. Show the user a plain list of those advertiser names with the number of ads each appeared on, most ads first — nothing else — and ask which are real competitors.
You need a name for each competitor, and a website where there is one: Step 3 uses the domain to prove the ads came from the right company. A competitor saved as "website unconfirmed" needs no question: Step 3 checks its page by what its ads sell, and takes its website from the ads.
Step 2: Scope the run
Ask once, bundled into a single message, always with a free-text way out. Skip any of these the brief already answers.
| Ask | When | How |
|---|---|---|
| The country the ads run in | The brief names no market and the user's own site implies none. | Offer the likely markets, and a way to type another. |
| How deep to go | The brief doesn't say. | Offer the quick scan first and recommend it; say a detailed analysis watches many more ads per competitor, and costs accordingly. |
| What they want to learn | Optional, and only where the brief says nothing at all about what the research is for. | One open field, no options to choose from. Ask what they want to come away knowing. |
What ships with it
5 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.
- 12d ago Changed · +1 lines c61633c75f39
- 1mo ago First seen · 160 lines · 133 tokens per session scan A f74563910f88
researching-competitor-ads is a skill published in the GitHub repository SupercmoHQ/superCMO-skills (242 stars, last pushed 6d ago), licensed Apache-2.0. It adds 133 tokens to every session and 2,380 once invoked, about $0.0005 per session on Opus 5.5. 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
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
email-lifecycle-flow-writer
Step of the email-lifecycle playbook: writes one lifecycle flow as a build sheet for the brand's email tool, every message finished in the brand voice. Run email-lifecycle instead; not for direct use.
work-with-creators-creator-vetting
Vets creators you have already named from their public pages. Covers the median views of their last 12 to 20 posts (sponsored and organic apart), a read of their comments, how often they post, audience fit with how sure it is, about 12 months of brand-safety checks, rival partnerships and rules for regulated…
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).