CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cross-modal-review

Quality gate via second model. Spawn a different AI model to review work before committing. Includes refusal routing: if one model refuses, switch silently to the next. Extended in v0.25.1 with structured review-mode gating (when to invoke vs not) and a Codex code-review handoff for the diff-review case.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/cross-modal-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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-structured orchestration skill with genuinely operational gating criteria, output templates, refusal-routing loops, and user-sovereignty rules. Its weaknesses are localized: version-changelog tokens scattered through the body, a conformance-test stub section and duplicate Output Format heading, and core mechanics delegated to conventions files that are absent from the bundle.

Suggestions

Strip version annotations ('v0.25.1 gating', 'v0.25.1 extension', 'v0.27.x') from section headers and prose, or consolidate them in a short changelog/deprecated section.

Delete the trailing '## Output Format' conformance-test stub section and the duplicate of the existing '## Output format' section; merge related skills and output formatting into one place.

Resolve the dangling references: either ship the conventions files (cross-modal.yaml, model-routing.md) inside the skill bundle or inline the minimal routing-chain and model-selection details the workflow needs to execute, and use one consistent path format (currently '../conventions/...' and 'conventions/...' both appear).

DimensionReasoningScore

Conciseness

Most sections are tight operational bullets (gating thresholds, refusal-routing steps, anti-patterns), but there is real padding: version annotations appear in three places ('When to invoke (v0.25.1 gating)', 'Code-review handoff (v0.25.1 extension)', 'gbrain eval cross-modal command (v0.27.x)'), a multi-paragraph blockquote digresses on the sibling command's role, and a stub section at the end ('The literal section header here exists for the conformance test') is pure test-satisfying noise. More than 'minor instances' of over-explanation, so not 4; but it never explains concepts Claude already knows, so not 2.

3 / 5

Actionability

Concrete, usable guidance throughout: quantified gating criteria ('5+ files or 100+ lines', '2+ iterations'), verbatim output templates with the exact framing blocks, numbered phases, and explicit do/don't lists. Not 5 because the core mechanics — how to actually spawn the second model and what review prompt to send — are fully delegated to conventions files that are not present in this bundle, and the 'Agreement: X% (N/M findings overlap)' template gives no method for computing the percentage.

4 / 5

Workflow Clarity

The five phases are clearly sequenced with an explicit pass/fail grading checkpoint ('Pass / fail with specific citations'), a refusal-routing feedback loop (refuse → switch silently → escalate when all refuse), a dedicated 'When it fails' section, and invoke/do-not-invoke checklists. Not 5 because phase 3 ('Spawn review model') depends entirely on an external model-routing.md that does not exist in the bundle, and only refusal — not malformed or unusable reviewer output — has a defined recovery path.

4 / 5

Progressive Disclosure

Good structure with clearly signaled, one-level-deep markdown links ([conventions/cross-modal.yaml], [conventions/model-routing.md], [conventions/test-before-bulk.md]) and well-organized sections. Not 5 because the actual bundle is a single SKILL.md with no referenced files present — the routing chain and model-selection details live entirely in dangling external paths, section headers are duplicated ('## Output format' at line 138 vs '## Output Format' at line 202), and the ~40-line Codex/adversarial mode detail plus the conformance-test stub section could live in a reference file.

4 / 5

Total

15

/

20

Passed

Description

66%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 states a clear, concrete 'what' with recognizable niche terms, but omits any 'use when' trigger guidance, spending its closing sentence on version-changelog detail ('Extended in v0.25.1 with...') instead of usage conditions. It is serviceable but reads like release notes in its second half rather than a capability-and-trigger summary.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the user asks for a second opinion, to double-check significant or security-sensitive changes, or before committing substantial diffs').

Replace the version-changelog sentence ('Extended in v0.25.1 with structured review-mode gating...') with the actual capabilities it introduced (review-mode gating, Codex diff-review handoff) stated as present-tense actions.

Fold one or two natural user phrasings ('second opinion', 'double check') from the triggers list into the description text itself.

DimensionReasoningScore

Specificity

Concrete actions named: 'Spawn a different AI model to review work before committing', 'refusal routing: if one model refuses, switch silently to the next', and 'a Codex code-review handoff for the diff-review case'. Falls short of 5 because the final sentence is version-changelog framing ('Extended in v0.25.1 with structured review-mode gating') that names meta-features rather than capabilities, and coverage gaps exist (e.g., adversarial challenge mode is absent).

4 / 5

Completeness

The 'what' is clear ('Spawn a different AI model to review work before committing'), but there is no 'Use when...' clause or equivalent explicit trigger guidance in the description — 'structured review-mode gating (when to invoke vs not)' references that gating exists without stating when to invoke. Per the rubric guideline, a missing 'Use when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Contains several natural, relevant terms users would say: 'review', 'second model', 'quality gate', 'code review', 'diff-review'. Not 5 because the most natural user phrasages ('second opinion', 'double check', 'get another perspective') appear only in the triggers list, not in the description itself; not 3 because multiple relevant keywords are clearly present.

4 / 5

Distinctiveness Conflict Risk

The cross-model framing ('second model', 'refusal routing', 'Codex handoff') carves a recognizable niche distinct from single-model code-review skills. Not 5 because generic phrases like 'review work before committing' and 'second opinion'-type usage overlap with ordinary code-review and testing skills — overlap the body itself acknowledges via the /codex and testing skill cross-references.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 4 suspicious

Warning

Total

14

/

16

Passed

Repository

garrytan/gbrain

Path

skills/cross-modal-review/SKILL.md

Reviewed

Table of Contents

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.