Tessl • The management layer for AI agent skills

SkillPublic

cro

Use when optimizing landing pages, signup flows, checkout processes, or any user-facing page for higher conversion rates - before A/B testing.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/cro/SKILL.md

Quality

Content

81%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 strong, highly actionable skill body: a clear six-step audit workflow backed by executable search commands, concrete checklists, a prioritized recommendation format, and an explicit verification checklist before completion. The main gaps are the undefined $TARGET variable used throughout the commands and some inline content (anti-rationalization table, persuasion detail) that could be trimmed or split out to reduce token load.

Dimension	Reasoning	Score
Conciseness	The body is dominated by tight tables and copy-paste grep/find commands with almost no explanation of concepts Claude already knows; benchmark statistics ("+1s load time = -7% conversion") add real value. Not 5 because the 7-row Anti-Rationalization table is user-psychology padding rather than task guidance, and a few asides ("Users won't. They'll leave. Average attention span is 8 seconds.") could be trimmed.	4 / 5
Actionability	Concrete executable grep/find commands with precise --include filters, specific checklists (friction types, Cialdini implementations, CTA best practices), and a fully templated output format. Not 5 because the commands reference a $TARGET variable that is never defined - the skill only defines $ARGUMENTS - so the commands fail as written without inference.	4 / 5
Workflow Clarity	Six clearly sequenced steps with numbered substeps, plus a dedicated "Verification Protocol" section with an 8-item checklist to run "Before claiming the CRO audit is complete" - matching the anchor-5 pattern of explicit validation steps and checklists. The audit is read-only, so the destructive/batch feedback-loop cap does not apply, and no error-recovery loop is needed.	5 / 5
Progressive Disclosure	No bundle files exist and the single ~230-line file is well-organized with clear section headers, with all content (friction tables, persuasion checklist, output template) directly used in the core workflow. Not 5 because the file runs long - the Cialdini detail table and Anti-Rationalization section are candidates for a separate reference file to keep SKILL.md a leaner overview.	4 / 5
	Total	17 / 20 Passed

Description

70%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 solid description with an explicit, well-scoped 'Use when' trigger covering the main CRO surfaces and a useful pre-A/B-testing boundary. Its main weakness is that it describes when to use the skill but only vaguely what the skill does, relying on a single generic verb ("optimizing").

Suggestions

State the concrete actions the skill performs, e.g. "Audits pages and flows for conversion friction - drop-off points, persuasion gaps, technical blockers - and produces prioritized recommendations with testable A/B hypotheses".

Add common synonyms users would naturally say - "CRO", "conversion rate optimization", "conversions", "drop-off" - to broaden trigger coverage.

Tighten the broad catch-all "or any user-facing page" to conversion-focused contexts (e.g. "any user-facing page meant to drive a conversion action") to reduce overlap with general design or copy review skills.

Dimension	Reasoning	Score
Specificity	Names specific domain objects ("landing pages, signup flows, checkout processes") but the only action is the generic verb "optimizing" - it never states what the skill actually does (audit pages, identify friction, produce prioritized recommendations). This matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) rather than 4, which requires several distinct specific actions.	3 / 5
Completeness	Has an explicit "Use when" clause with concrete contexts and a timing boundary ("before A/B testing"), so the 'when' is well specified. The 'what' is present but thin - only "optimizing ... for higher conversion rates" with no mention of auditing, friction analysis, or recommendations - fitting anchor 4 (both present, one could be stronger) rather than 5.	4 / 5
Trigger Term Quality	Includes natural phrases users would say - "landing pages", "signup flows", "checkout processes", "conversion rates", "A/B testing" - giving good keyword coverage. Not 5 because common synonyms like "CRO", "conversions", "drop-off", or "bounce" are missing.	4 / 5
Distinctiveness Conflict Risk	The conversion-rate framing carves out a clear niche distinct from general page or code review skills. Not 5 because "any user-facing page" is a broad catch-all that creates minor overlap risk with design-review or copywriting skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/specialist-agent
Path: skills/cro/SKILL.md
Revision: cd716d9

Reviewed: 8 days ago

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.

cro

Table of Contents

Is this your skill?