source-outranker

Use this skill whenever a user wants to understand which external sources are being cited by AI models on topics relevant to their brand, and wants to create content that will outrank those sources — whether they say "what sources are AI models citing", "why is [third-party site] being cited instead of us", "we want to be the definitive source on X", "build something that gets cited more than G2 or TechRadar", "create an authoritative asset", or any variation where the goal is producing a new reference asset (definition page, benchmark, methodology, glossary, comparison hub) designed to beat existing top-cited sources. This skill analyzes AI Visibility source data, reverse-engineers what makes top-cited pages authoritative, and produces a superior source asset — then pushes it to CMS as a draft. Trigger on any mention of "sources", "third-party citations", "authoritative content", "definitional pages", or "outrank".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, highly actionable multi-step workflow with clear sequencing and checkpoints, but it is monolithic with no bundle files and carries a dangling cross-reference plus a redundant conceptual closing section that hurts token efficiency.

Suggestions

Move the three asset-type templates (Definitive Guide, Benchmark Report, Comparison Hub) into a references file (e.g. references/asset-templates.md) and link to it from Step 4, keeping SKILL.md a lean overview.

Delete or fold the closing "What makes a source authoritative to AI models" section into Step 2's audit criteria to remove the conceptual restatement and redundancy.

Resolve the `prompt-gap-to-publish` reference — either ship that guidance as a real bundle file or remove the pointer so the body references only files that exist.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and instructional, but the closing "What makes a source authoritative to AI models" section restates concepts and overlaps heavily with the Step 2 audit criteria (answer structure, data, comprehensiveness, freshness, authority), adding redundant conceptual padding Claude could largely infer.	2 / 3
Actionability	Highly actionable for an instruction-only skill: names specific MCP tools (list_ai_visibility_org_brands, get_ai_visibility_sources, web_fetch, create_documents_from_markdown, create_entry, etc.), concrete fields, per-CMS draft parameters, and detailed asset templates with section counts and meta-field specs — copy-paste ready guidance.	3 / 3
Workflow Clarity	A clearly sequenced Step 0–5 flow with explicit checkpoints: Step 0 prevents a copy-paste dead end, Step 3 says "Wait for their pick", and Step 5 confirms the draft push. No destructive/batch operations are involved (CMS pushes are drafts), so the absence of validate→fix loops does not cap the score.	3 / 3
Progressive Disclosure	Sections are well-organized, but the skill is monolithic (~240 lines) with long inline asset-type templates that could live in reference files, and it cites `prompt-gap-to-publish` which has no corresponding file in references/, scripts/, or assets/ — an unverifiable/dangling reference against an empty bundle.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that explicitly covers both capability and trigger conditions with natural user phrasings and a distinct niche. It is slightly verbose for a description but every clause carries specific triggers or actions rather than fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "analyzes AI Visibility source data, reverse-engineers what makes top-cited pages authoritative, and produces a superior source asset — then pushes it to CMS as a draft" — going well beyond a single vague verb. The "Use this skill whenever..." imperative follows the accepted third-person trigger form rather than first/second person, so no specificity penalty applies.	3 / 3
Completeness	Clearly answers both what (analyze visibility data, reverse-engineer authority, build a superior asset, push to CMS as draft) and when ("Use this skill whenever a user wants to understand..." and "Trigger on any mention of...") with explicit trigger guidance, satisfying the top anchor.	3 / 3
Trigger Term Quality	Embeds many natural user phrasings ("what sources are AI models citing", "why is [third-party site] being cited instead of us", "build something that gets cited more than G2 or TechRadar") plus an explicit trigger list ("sources", "third-party citations", "authoritative content", "definitional pages", "outrank") giving strong coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The AI-citation/outranking niche is specific and the triggers (AI Visibility, cited sources, outrank, definitional pages) are unlikely to fire for unrelated content skills, giving it a clear distinct niche.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: amplitude/builder-skills
Commit: 22b0634

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.