NimblewayNimbleway/agent-skills/skills/seo-intel/SKILL.md

seo-intel

Skill61 starsChanged 3 months agoMITView on GitHub

SEO intelligence toolkit covering the full lifecycle via live web data: keyword research, rank tracking, site audits, content gap analysis, competitor keyword reverse-engineering, AI visibility across five platforms (ChatGPT, Perplexity, Google AI, Gemini, Grok), and GitHub repo SEO. Crawls real sites and SERPs via Nimble CLI — no fabricated metrics.

In this repository25 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- account-briefSkill
- account-discoverySkill
- account-enrichmentSkill
- account-signalsSkill
- brand-mention-monitorSkill
- company-deep-diveSkill
- competitor-intelSkill
- competitor-positioningSkill
- credit-riskSkill
- deal-sourcingSkill
- decision-maker-identificationSkill
- due-diligenceSkill
- healthcare-providers-enrichSkill
- healthcare-providers-extractSkill
- healthcare-providers-verifySkill
- kyc-screeningSkill
- launch-monitorSkill
- local-placesSkill
- market-finderSkill
- meeting-prepSkill
- nimble-databricks-data-productsSkill
- nimble-web-expertSkill
- portfolio-monitoringSkill
- talent-sourcingSkill

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
If unclear, present the options with AskUserQuestion:
line 85
Distinctive:
After completing a workflow, suggest natural next steps using sibling workflows.
line 106
Distinctive:
When chaining, read the next workflow file and continue.
line 113

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

SEO Intelligence Toolkit

All-in-one SEO intelligence: keyword discovery, rank tracking, technical audits, content gaps, competitor analysis, AI visibility, and GitHub SEO.

User request: $ARGUMENTS

Before running any commands, read references/nimble-playbook.md for Claude Code constraints (no shell state, no &/wait, sub-agent permissions, communication style). Tag all nimble CLI calls: nimble --client-source nimble-agent-skills <subcommand>. MCP requests are attributed at the transport level — see references/nimble-playbook.md.

Workflow Router

Detect the user's SEO intent from $ARGUMENTS and route to the appropriate workflow. If the intent is ambiguous or generic ("help me with SEO"), ask which workflow to run.

Available Workflows

Workflow	Triggers	Reference
Keyword Research	keyword opportunities, topic clusters, difficulty, what to rank for	`references/wf-keyword-research.md`
Rank Tracker	track rankings, keyword positions, ranking delta, position check	`references/wf-rank-tracker.md`
Site Audit	SEO audit, technical SEO, meta tags, schema, crawl for issues, CWV	`references/wf-site-audit.md`
Content Gap	content gap, keyword gap, compare coverage, missing topics	`references/wf-content-gap.md`
Competitor Keywords	competitor keywords, reverse-engineer SEO, competitor title tags	`references/wf-competitor-keywords.md`
AI Visibility	AI visibility, ChatGPT presence, Perplexity, AI Overview, GEO	`references/wf-ai-visibility.md`
GitHub SEO	github seo, repo discoverability, optimize readme, repo audit	`references/wf-github-seo.md`

Intent Detection

Map the request to one workflow:

Keywords / topics / difficulty / clusters / "what to rank for" → Keyword Research
Rankings / positions / tracking / delta / monitoring → Rank Tracker
Audit / crawl / technical / meta / schema / links / CWV → Site Audit
Gap / missing topics / coverage comparison / "what should I write" → Content Gap
Competitor site crawl / reverse-engineer / on-page at scale → Competitor Keywords
AI visibility / ChatGPT / Perplexity / AI Overview / GEO → AI Visibility
GitHub / repo / README / discoverability → GitHub SEO

If unclear, present the options with AskUserQuestion:

Which SEO workflow should I run?
Keyword Research — discover keyword opportunities and topic clusters
Rank Tracker — check and track keyword positions over time
Site Audit — full technical SEO crawl with JS rendering
Content Gap — compare content coverage against competitors
Competitor Keywords — reverse-engineer competitor on-page SEO at scale
AI Visibility — measure brand presence across 5 AI platforms
GitHub SEO — audit repository discoverability and README quality

Execution

Once a workflow is identified:

Read the corresponding references/wf-{name}.md
Follow its instructions from Step 0 (Preflight) through to the output format
All references/ paths inside workflow files are relative to this skill's directory

Workflow Chaining

After completing a workflow, suggest natural next steps using sibling workflows. Common chains:

Site Audit → Keyword Research → Content Gap → Rank Tracker
Keyword Research → Competitor Keywords → Content Gap
AI Visibility → Content Gap → Keyword Research

When chaining, read the next workflow file and continue. Context from the previous run (discovered domains, keyword lists, profile data) carries forward — do not re-run preflight or re-ask onboarding questions.

Shared Configuration

All workflows use:

Business profile + onboarding: references/profile-and-onboarding.md
Data persistence: references/memory-and-distribution.md
CLI patterns + constraints: references/nimble-playbook.md
AI platform agent discovery: references/ai-platform-profiles.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free