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 ishwarjha/claude-marketing-research-skill --skill marketing-researchgit clone --depth 1 https://github.com/ishwarjha/claude-marketing-research-skillWrote 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/ishwarjha/claude-marketing-research-skill/marketing-research)<a href="https://agentmods.dev/skills/ishwarjha/claude-marketing-research-skill/marketing-research"><img src="https://agentmods.dev/badge/skills/ishwarjha/claude-marketing-research-skill/marketing-research/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/ishwarjha/claude-marketing-research-skill/marketing-research"><img src="https://agentmods.dev/badge/skills/ishwarjha/claude-marketing-research-skill/marketing-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00179 | $0.03004 |
| Opus 5 | $0.00089 | $0.01502 |
| Sonnet 5 | $0.00036 | $0.00601 |
| Haiku 4.5 | $0.00018 | $0.00300 |
Grade A, and why
marketing-research 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marketing Research Sourcebook
A structured, practitioner-grade research system for products, avatars, markets, competitors, and positioning.
WRITING RULES (Apply to Every Module)
These rules govern ALL output. Follow them without exception.
Style:
- Never use em dashes. Use periods, commas, colons, or separate sentences instead.
- Minimize parenthetical content. If something matters, give it a full sentence. If it does not matter, cut it.
- Write in active voice. Short paragraphs. Plain language. No hedging.
- Lead every section with the sharpest insight, not setup or context. Put the point first.
- Each sentence should earn its place. Cut filler words, throat-clearing phrases, and anything that restates what the reader already knows.
- Use "not X, but Y" constructions sparingly. Once per section at most.
Structure: 7. Tables over prose. Default to tables for comparisons, feature lists, competitor maps, and multi-dimension analysis. 8. One paragraph max per competitor in landscape maps. 9. Dimensionalized benefits: 3-4 sentences. One vivid scenario, not a narrative. 10. No "Chain-Forward Summary" sections. Context carries forward internally. 11. Mechanism stories: 1 short paragraph setup + 1 short paragraph outcome. 12. Value propositions stay full-length. These are copy assets. 13. Mental model reframes: 1 example per model. Pick the strongest. 14. Target module length: 100-150 lines. Full run approximately 600-700 lines total. 15. Use web search for competitor research. Pull current data. 16. Deliver each module as a single markdown file.
STEP 0: INTAKE INTERVIEW (Always Start Here)
Ask all questions at once:
Before we dive in, I need a few details:
1. What is your product? Short description: what it is, what it does, who it serves.
2. What are the main components, features, or chapters?
3. Who is your ideal customer? Their role, situation, and what they want.
4. Do you have any named competitors? Even 2-3 is enough.
5. What stage are you at?
a) Just starting. Need everything.
b) Have a product defined. Need avatar and market research.
c) Have avatar research done. Need positioning and copy angles.
d) Have everything. Need a competitor comparison.
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 · 330 lines · 179 tokens per session scan A e192e89c8785
marketing-research is a skill published in the GitHub repository ishwarjha/claude-marketing-research-skill (49 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 179 tokens to every session and 3,004 once invoked, about $0.0009 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
market-competitors
You are the competitive intelligence engine for /market competitors . You identify competitors, analyze their marketing strategies, and produce a comprehensive comparison report that reveals positioning gaps, steal-worthy tactics, and differentiation opportunities. Output is structured for both strategic…
market-launch
Generate a complete, week-by-week launch playbook for any product, service, or feature launch. This skill produces a tactical plan with templates, checklists, email sequences, social posts, and metrics tracking -- everything needed to execute a successful launch.
market-seo
Perform a comprehensive SEO audit of a webpage or website, covering on-page SEO, content quality (E-E-A-T), keyword analysis, technical SEO, and content strategy. This skill combines automated analysis via scripts/analyzepage.py with expert-level manual review to produce an actionable SEO audit document.
market-ads
You are the advertising engine for /market ads . You generate complete ad campaigns across platforms with full copy variations, audience targeting strategies, budget recommendations, and creative specifications. Every ad is ready for production or handoff to a media buyer.
market-brand
Analyze a brand's voice, tone, and messaging across all available channels and generate a comprehensive brand voice guidelines document. This skill examines how a brand communicates, identifies patterns and inconsistencies, and produces actionable guidelines that any writer or marketer can follow to maintain brand…
market-emails
You are the email marketing engine for /market emails . You generate complete, ready-to-send email sequences with subject lines, body copy, timing, and segmentation strategies. Every sequence is built on proven email frameworks and calibrated to industry benchmarks.