Name: cross-eval
Rating: 67.2 (1 reviews)
Author: alirezarezvani

cross-eval

/cs:cross-eval <memo> — Multi-model consensus on a board memo or strategy brief. Claude + Codex + Gemini cross-review with graceful degradation. Use when a high-stakes memo needs an independent sanity check before the boardroom — e.g. a bet-the-company pivot or fundraise terms.

Quality

81%

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

The canonical home for this skill is cross-eval in alirezarezvani/claude-skills

Quality

Content

75%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.

The body is a well-structured, actionable instruction skill with a concrete workflow, copy-paste prompt, and clear output template. It earns solid marks across all dimensions, with small room to tighten the rationale prose and add explicit per-provider invocation commands.

Suggestions

Trim or move the 'Why This Matters' model-bias generalizations; keep only claims that change what Claude does.

Add concrete invocation snippets for the Codex and Gemini CLIs/APIs (alongside the Claude path) so the 'probe environment' step is fully executable.

Consider extracting the output-format template into a reference file to shorten the main body, since it is the longest inline block.

Dimension	Reasoning	Score
Conciseness	Mostly lean with concrete prompt prefixes and templates, but the 'Why This Matters' section generalizes per-model biases (e.g. 'Claude trends helpful') that could be trimmed without losing actionable value.	4 / 5
Actionability	Provides a copy-paste prompt prefix, a full output-format template, and a concrete adversarial-degradation mode, but stops short of giving exact CLI invocation commands for each model provider.	4 / 5
Workflow Clarity	A clear 6-step sequence (read → probe → review per model → collect → reconcile → surface) with GO/PAUSE/STOP recommendation rules acting as checkpoints; minor validation gaps around external-model failure beyond graceful degradation.	4 / 5
Progressive Disclosure	Single SKILL.md with well-organized sections and one-level-deep links to related skills; the inline output-format template is reasonably placed though it is a sizeable block that could optionally live in a reference.	4 / 5
	Total	16 / 20 Passed

Description

87%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.

The description is well-crafted: it states the capability, names the models used, and gives an explicit 'Use when' clause with concrete high-stakes trigger examples. Minor gaps in action comprehensiveness and synonym coverage keep specificity and trigger_term_quality just below the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain (multi-model consensus on a board memo) and several concrete actions — 'cross-review', 'graceful degradation', 'Claude + Codex + Gemini' — but the actions describe the approach rather than a comprehensive list of operations.	4 / 5
Completeness	Explicitly answers both what ('Multi-model consensus... Claude + Codex + Gemini cross-review with graceful degradation') and when ('Use when a high-stakes memo needs an independent sanity check before the boardroom') with concrete trigger examples.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('board memo', 'strategy brief', 'high-stakes memo', 'bet-the-company pivot', 'fundraise terms'), with good coverage though a few synonymous trigger terms are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (multi-model consensus on board memos) with distinct triggers (fundraise terms, bet-the-company pivot) that minimize overlap with other skills.	5 / 5
	Total	18 / 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
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/cross-eval/SKILL.md
Commit: 19392f7

Reviewed: ~2 hours 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.