icp-website-audit

End-to-end website audit through ICP eyes. Builds synthetic personas (if they don't already exist), runs a structured scorecard review of the client's site, then runs a head-to-head competitive comparison against top competitors. Produces a single consolidated report with persona feedback, competitive positioning, and prioritized recommendations. The complete "how do our buyers actually experience our site vs the competition?" workflow.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/lead-generation/composites/icp-website-audit/SKILL.md

Quality

Content

63%Weight 40%Scale 1-5

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

A well-sequenced, largely actionable orchestration skill with clear phases, concrete file conventions, and a useful deliverable template. Its weaknesses are an oversized inlined report template with no reference files, a circular self-reference to 'icp-website-audit' as a sub-skill, and noticeable duplication/padding in the intro and Tips sections.

Suggestions

Move the consolidated report template to a references/ file (e.g. references/report-template.md) and keep only a short outline in SKILL.md, creating one-level-deep progressive disclosure.

Resolve the circular reference: Phase 2/3 say 'Run icp-website-audit in scorecard mode' — the skill's own name — so either name the actual sub-skill/script to invoke or reframe as 'run the scorecard pass below'.

Delete the intro paragraph that duplicates the frontmatter description and trim editorializing in Tips to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The core phases and template earn their tokens, but the intro paragraph repeats the frontmatter description nearly verbatim and the Tips section carries editorial padding ('That should drive urgency', 'Buyers always compare — your audit should too'). Mostly efficient with several instances that could be tightened, matching anchor 3.	3 / 5
Actionability	Concrete file paths (clients/<client>/personas/personas.json, icp-reviews/<date>-scorecard.md), exact scoring dimensions, and a full report template make the guidance mostly executable. The gap is the circular instruction 'Run icp-website-audit in scorecard mode' — the skill's own name — with no separate sub-skill file to invoke.	4 / 5
Workflow Clarity	Four phases are clearly sequenced with per-phase outputs, a parallelization diagram, and a Phase 1 checkpoint ('confirm they look current'). Validation is light (no verification that crawls succeeded or that the consolidated report is complete), so it does not reach anchor 5; this is a research/writing skill, so the destructive/batch cap does not apply.	4 / 5
Progressive Disclosure	No bundle files exist and the ~190-line consolidated report template is inlined directly in the body — content that clearly belongs in a separate reference file. Section headers provide structure, matching anchor 3 ('content that should be separate is inline') rather than anchor 2, since the sections are well-labeled and navigable.	3 / 5
	Total	14 / 20 Passed

Description

71%Weight 40%Scale 1-5

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 specific, well-scoped description that clearly conveys what the skill does with concrete actions and a distinct niche. Its main weakness is the complete absence of 'when to use' trigger guidance, which caps completeness and leaves trigger-term coverage short of comprehensive.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to audit their website from the buyer's perspective, compare their site against competitors, or evaluate messaging for their ICP.'

Include natural trigger variations such as 'competitive analysis', 'website review', and 'competitor comparison' so users' phrasing matches without exact wording.

Trim the closing tagline sentence ('The complete... workflow.') in favor of the trigger guidance, since it repeats the what without adding when.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Builds synthetic personas', 'runs a structured scorecard review', 'runs a head-to-head competitive comparison', 'Produces a single consolidated report with persona feedback, competitive positioning, and prioritized recommendations' — covering the workflow comprehensively, matching the top anchor.	5 / 5
Completeness	The 'what' is explicit and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance — the closing sentence is a framing tagline, not a when-to-use trigger, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes natural terms users would say — 'website audit', 'personas', 'scorecard', 'competitive comparison', 'buyers' — but misses common variations like 'competitive analysis', 'website review', or 'competitor research'. Not a 5 because synonym coverage is incomplete; not a 3 because the keywords present are natural, not jargon.	4 / 5
Distinctiveness Conflict Risk	The ICP/persona/scorecard framing carves a distinct niche with minimal conflict risk, but it overlaps with closely related skills it itself references (buyer-persona-generator, SEO content audit). Not a 5 because those adjacent skills could plausibly trigger for similar requests.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: gooseworks-ai/goose-skills
Path: skills/lead-generation/composites/icp-website-audit/SKILL.md
Commit: cc3e518

Reviewed: 7 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.