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 MarcinZmuda/darn-content-gap-analyzer --skill content-gap-analyzergit clone --depth 1 https://github.com/MarcinZmuda/darn-content-gap-analyzerWrote 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/marcinzmuda/darn-content-gap-analyzer/content-gap-analyzer)<a href="https://agentmods.dev/skills/marcinzmuda/darn-content-gap-analyzer/content-gap-analyzer"><img src="https://agentmods.dev/badge/skills/marcinzmuda/darn-content-gap-analyzer/content-gap-analyzer.svg" alt="Measured on agentmods" 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 | $0.00195 | $0.06053 |
| Opus 5 | $0.00097 | $0.03027 |
| Sonnet 5 | $0.00039 | $0.01211 |
| Haiku 4.5 | $0.00019 | $0.00605 |
Grade A, and why
content-gap-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 — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Darn — Content Gap Analyzer (DataForSEO edition)
Darn is a production-grade content gap analysis skill using the DataForSEO MCP server. It replaces weeks of manual SERP inspection with targeted API calls that return exact search volumes, keyword difficulty, SERP features including AI Overview detection, and content gap detection.
Author: Marcin Żmuda · Repo: https://github.com/MarcinZmuda/darn-content-gap-analyzer · License: MIT
Two operating modes
Darn has two entry points — Claude picks automatically based on what the user provides:
Domain Mode — "my site vs competitors"
User provides their domain + competitor domains. Darn runs Domain Intersection to find keywords competitors rank for but user doesn't. Full 5-dimensional gap analysis (keyword gap, topic cluster gap, format gap, information gain gap, AI visibility gap) with funnel stage mapping and 12-week calendar. Typical cost: $1-5 per analysis (more for enterprise-scale analyses with 10+ competitors and 10k+ keywords).
Use when: established site, clear competitors, want to find what to publish to catch up / overtake.
Topic Mode — "build content plan from a keyword"
User provides a single seed keyword or topic (e.g., "rozwód", "email marketing automation", "plant-based protein"). Darn pulls the top 15 pages ranking for that keyword, extracts their full ranked-keywords footprint, filters article-worthy topics, clusters them, and produces a content plan. Typical cost: $0.40-1.50 per analysis (~$0.35-0.80 for a standard single keyword).
Use when: pre-launch site, new topic cluster, freelancer/agency scoping a niche, affiliate/content-site research, deciding whether a topic is worth entering.
Both modes share the same deliverable structure (clusters, priority scoring, funnel mapping, info-gain angles, content calendar) — just a different starting point.
Prerequisites
- DataForSEO account with API credentials
- DataForSEO MCP server connected to Claude (see
references/setup.md) - API credits — budget depends on mode:
- Domain Mode: $1-5 per standard analysis, up to $15-30 for enterprise-scale (10+ competitors, 10k+ keywords)
- Topic Mode: $0.40-1.50 per analysis
- Optional but recommended (Domain Mode only): project context prepared (see
references/project-context.mdfor template — pasted into chat, saved as artifact, or stored in memory). Topic Mode works without project context.
What ships with it
17 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/api-templates.md 6.3 KB
- references/competitor-validation.md 2.7 KB
- references/dimensions.md 6.1 KB
- references/domain-mode-workflow.md 8.8 KB
- references/endpoints.md 11 KB
- references/funnel-analysis.md 4.9 KB
- references/gsc-integration.md 7.8 KB
- references/information-gain.md 6.5 KB
- references/market-specifics.md 3.2 KB
- references/prioritization.md 6.4 KB
- references/project-context.md 6.2 KB
- references/report-template.md 10 KB
- references/setup.md 5.9 KB
- references/topic-mode-filtering.md 9.8 KB
- references/topic-mode-workflow.md 11 KB
- references/troubleshooting.md 5.0 KB
- references/worked-examples.md 11 KB
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 · 455 lines · 0 tokens per session scan A 57d22a6cf5ec
content-gap-analyzer is a skill published in the GitHub repository MarcinZmuda/darn-content-gap-analyzer (2 stars, last pushed 2mo ago), licensed MIT. It adds 195 tokens to every session and 6,053 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
seo-sxo
Search Experience Optimization: reads Google SERPs backwards to detect page-type mismatches, derives user stories from search intent signals, and scores pages from multiple persona perspectives. Identifies why well-optimized pages fail to rank by analyzing what Google rewards for each keyword. Use when user says…
seo-flow
FLOW framework integration: evidence-led SEO using the Find → Leverage → Optimize → Win loop. Surfaces stage-specific AI prompts from the FLOW knowledge base (41 prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "seo flow", "evidence-led SEO", "find leverage optimize win", or wants stage-specific SEO…
seo-page
Deep single-page SEO analysis covering on-page elements, content quality, technical meta tags, schema, images, and performance. Use when user says "analyze this page", "check page SEO", "single URL", "check this page", "page analysis", or provides a single URL for review.
newsletter-monetization-planner
Use when the user asks to "monetize my newsletter", "build a sponsorship rate card", or "model paid-subscription revenue"; produces a revenue model (paid tiers, ad/sponsorship inventory + CPM/flat rate card, referral/boost loops), a list-growth ↔ revenue projection, and honest-offer / disclosure checks for the SEND-D…
audience-mapper
Use when the user asks to "analyze my target audience", "build an audience profile for influencer targeting", "research a niche community", or "deep-dive a subculture before partnering with creators"; in audience mode produces demographic/psychographic profiles, a platform-priority matrix, named personas, and an…
narrative-drift-monitor
Use when the user asks to "check if our surfaces have drifted from the canon", "watch for competitor repositioning", or "define when we should reposition"; produces a drift report — self-drift per flagship surface vs the narrative-registry canon over time (via wayback.py, change history Measured with as-of dates)…