search-discoverability
Skill2 starsChanged 28 days agoMITView on GitHub
Assess buyer search coverage across traditional SEO, AI/answer engines and programmatic search. Use for SEO audits, rankings, AI citations, visibility gaps, scaled page opportunities, indexation and search/listing presence. Produce recommendations and briefs; content and technical deployment have separate owners.
In this repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- account-based-marketingSkill
- acquisition-conversionSkill
- ad-creativeSkill
- analytics-trackingSkill
- aso-auditSkill
- buyer-resourcesSkill
- cold-emailSkill
- community-marketingSkill
- competitor-alternativesSkill
- competitor-profilingSkill
- content-strategySkill
- customer-marketingSkill
- customer-researchSkill
- email-sequenceSkill
- eventsSkill
- go-to-market-strategySkill
- icp-and-buyer-personasSkill
- launch-readiness-checkSkill
- launch-strategySkill
- localization-claimsSkill
- market-entry-briefSkill
- market-entry-orchestrationSkill
- marketing-copySkill
- marketing-experimentationSkill
- market-intelligenceSkill
- messaging-consistency-auditSkill
- messaging-frameworkSkill
- objection-intelligenceSkill
- output-quality-checkSkill
- paid-adsSkill
- partner-marketingSkill
- positioning-strategySkill
- pricing-strategySkill
- product-activationSkill
- product-communicationsSkill
- product-marketing-contextSkill
- referral-programSkill
- revopsSkill
- sales-enablementSkill
- social-contentSkill
- ssot-context-loopSkill
- upgrade-conversionSkill
- website-buyer-journeySkill
- win-loss-intelligenceSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Read ../_shared/evidence-gaps.md and ../_shared/ssot-consumption.md.
- Very specific: line 14
Read ../_shared/segment-selection.md when an audience decision is needed.
- Very specific: line 16
Do not edit SSOT. Route proposed canon changes to ssot-context-loop for human review and approval.
- Distinctive: line 36
Read technical markup guidance for structured-data requirements and examples.
- Distinctive: line 37
Read listing catalogue and tracker for relevant third-party search presence.
≈ “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.
Files
Search Discoverability
Approved context and evidence
Read ../_shared/evidence-gaps.md and ../_shared/ssot-consumption.md.
Load only relevant approved manifest context and record sources in Inputs and assumptions.
Read ../_shared/segment-selection.md when an audience decision is needed; inherit accepted segments and ICP.
Separate sources, interpretation, and proposals. Missing evidence remains Assumed or Gap.
Do not edit SSOT. Route proposed canon changes to ssot-context-loop for human review and approval.
Modes
| Mode | Load and assess |
| Traditional search visibility | Traditional search: buyer query coverage, intent, on-page relevance, crawl/index diagnosis, internal linking, cannibalization and search visibility. |
| AI/answer-engine visibility | Answer engines: documented query sets, platform/date, repeated observations, answer/citation visibility, citation-source analysis, extractable patterns and third-party presence. |
| Scaled/programmatic opportunities | Scaled search: defensible data, unique buyer value, template briefs, cannibalization, pilot selection and indexation monitoring. |
Workflow
- Map accepted buyers and evaluation questions to query sets and existing content. Distinguish branded, category, use-case and competitive discovery. Record platform, date, method and observation limits; one answer is not universal visibility.
- Diagnose coverage, citations and technical impediments separately. Cite actual evidence; mark unavailable ranking/indexation data as Gap. Do not promise ranking or AI inclusion.
- Prioritize recommendations by buyer value, confidence, cost and dependencies. For scale, require unique value and defensible data before a small pilot; stop expansion if quality, cannibalization or indexation guardrails fail.
- Brief
content-strategy,marketing-copyorcompetitor-alternativesfor content;website-buyer-journeyfor buyer paths; web/SEO engineering for deployment. PMM approves truth and claims, not markup mechanics. - Specify leading coverage metrics and qualified acquisition outcomes with
analytics-tracking, owner and review cadence.
Conditional references
Read technical markup guidance for structured-data requirements and examples. Engineering checks current eligibility, implements and validates.
Read listing catalogue and tracker for relevant third-party search presence. Treat catalogue costs, traffic and policies as unverified leads until checked. No universal directory quota.
Launch-platform coordination belongs to launch-strategy, customer review programs to customer-marketing, integration marketplaces to partner-marketing, and approved listing descriptions to marketing-copy.
Required output
Inputs and assumptions; mode/query scope; sourced visibility diagnosis; buyer-coverage and citation gaps; prioritized content/technical briefs; scale pilot and safeguards where applicable; owner handoffs; measurement plan; ranked Evidence gaps. Final content passes originating requirements and independent messaging review. This skill does not deploy pages or silently redefine strategy.
Related skills
content-strategy, marketing-copy, competitor-alternatives, website-buyer-journey, analytics-tracking, launch-strategy, customer-marketing, partner-marketing.
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
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.