icp-website-review

Evaluate a website, landing page, content, or any online asset through the eyes of pre-built synthetic ICP personas. Loads personas from buyer-persona-generator output, then runs them against target URLs. Supports three modes: structured scorecard, freeform focus group, and head-to-head competitive comparison. Reusable — run against the same site after changes, or against new content anytime.

Quality

76%

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/capabilities/icp-website-review/SKILL.md

Quality

Content

71%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 highly actionable, well-sequenced instruction-only skill that gives the agent everything needed to execute all three modes, with concrete prompts, paths, and templates throughout. Its weaknesses are redundancy in the mode descriptions and the absence of any progressive disclosure — the entire output-template library lives inline in SKILL.md.

Suggestions

Move the three output templates to references/ (e.g. references/scorecard-template.md, references/focus-group-template.md, references/head-to-head-template.md) and keep one-line pointers in the body, cutting SKILL.md roughly by a third.

Merge the '## Modes' overview with the Step 3 mode details to eliminate the duplicated description of each mode's purpose and best-use cases.

Add brief error-recovery guidance for the main failure points: missing or malformed personas.json (point to buyer-persona-generator) and unreachable target URLs during the crawl.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with no explanations of concepts Claude already knows, but the three modes are described twice (## Modes 'Best for' bullets, then again in Step 3) and persuasive commentary like 'Head-to-head is the killer use case' and 'Focus group mode is underrated' is padding that could be trimmed.	3 / 5
Actionability	Fully executable for an instruction-only skill: verbatim invocation prompts, an exact persona prompt to reuse, concrete file paths, an 8-page crawl checklist, per-dimension rating criteria, and complete output templates for all three modes.	5 / 5
Workflow Clarity	Steps 1-4 are clearly sequenced with a validation checkpoint ('Confirm: personas exist and are well-formed'), but error-recovery feedback loops are missing — no guidance for malformed/missing personas.json or failed page fetches.	4 / 5
Progressive Disclosure	No bundle files exist and section structure/navigation are good, but the three full output templates (~150 lines of the ~450-line body) are inlined content that clearly belongs in separate references/ files.	3 / 5
	Total	15 / 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 in third-person voice that clearly communicates what the skill does and its three modes. Its main weakness is the absence of explicit 'Use when...' trigger guidance, which caps completeness and limits natural trigger-term coverage.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to review, audit, or critique a website/landing page through their buyer personas, run a synthetic focus group, or compare their site against a competitor.'

Include natural user phrasings as trigger terms, such as 'review my site', 'what would our customers think', 'website audit', and 'competitor comparison', so the skill triggers on how users actually ask.

Tighten 'any online asset... or any online content' to concrete asset types to further reduce overlap with generic website-review skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with comprehensive coverage of its scope: 'Loads personas from buyer-persona-generator output, then runs them against target URLs', plus three named modes ('structured scorecard, freeform focus group, and head-to-head competitive comparison') and reusability behavior.	5 / 5
Completeness	The 'what' is clear and detailed, but there is no 'Use when...' clause or equivalent explicit trigger guidance — the 'when' is only weakly implied by mentioning websites and landing pages, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Good natural-term coverage ('website', 'landing page', 'focus group', 'head-to-head', 'competitive comparison') but misses common user phrasings like 'review my site', 'persona feedback', or 'what would my customers think'.	4 / 5
Distinctiveness Conflict Risk	'Through the eyes of pre-built synthetic ICP personas' and the dependency on 'buyer-persona-generator output' carve a clear niche, but 'any online asset' and generic review framing create minor overlap risk with general website-critique skills.	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/capabilities/icp-website-review/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.