check-cross-layer

Post-implementation verification across multiple code dimensions: cross-layer data flow, code reuse analysis, import path validation, and same-layer consistency checks. Identifies missed update sites, type mismatches, and duplicated constants. Use when changes span 3+ architectural layers, after modifying shared constants or configs, after batch file modifications, or when creating new utility functions.

Quality

75%

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 ./.agents/skills/check-cross-layer/SKILL.md

Quality

Content

65%

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

The content is actionable and reasonably organized but has redundancy across the code-reuse dimensions, lacks an explicit verification feedback loop for batch operations, and relies on external references that are not part of the skill bundle.

Suggestions

Add an explicit validate->fix->retry step for batch operations, e.g. re-run `rg` after fixes and only stop when zero unexpected occurrences remain.

Consolidate the overlapping Dimensions B, B2, and B3 into a single Code Reuse dimension with sub-triggers to remove redundancy.

Either move the thinking-guide detail into bundled reference files under references/ (so the links resolve) or drop the non-existent external .trellis/spec/guides/ paths.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean (checklists, tables, short commands) but Dimensions B, B2, and B3 overlap heavily with each other and with the quick-reference table, so it could be tightened; not quite 'every token earns its place'.	2 / 3
Actionability	Provides concrete commands (git status, git diff --name-only, rg 'value-to-change' src/) and specific checklist rules ('If 2+ places define same value -> Should extract to shared constant'); the placeholder search terms are clearly substitution variables, which is acceptable for an instruction skill.	3 / 3
Workflow Clarity	A clear sequence exists (Execution Steps, dimension sections, Output) but this batch/destructive-adjacent verification skill lacks an explicit validate->fix->retry feedback loop, which per the rubric caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are well-organized with a Related Documents navigation table, but the 'Detailed Guide' references point to external non-bundle paths that do not resolve, and no bundle files split the >50-line content, so it is not a clean one-level-deep structure.	2 / 3
	Total	9 / 12 Passed

Description

85%

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 specific, complete, and distinct, with both concrete capabilities and explicit use-when triggers. Its only weakness is trigger phrasing that is somewhat technical rather than naturally user-spoken.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and outputs ('cross-layer data flow, code reuse analysis, import path validation', 'Identifies missed update sites, type mismatches, and duplicated constants') rather than vague language, matching the score-3 anchor.	3 / 3
Completeness	Clearly answers both what ('Post-implementation verification across multiple code dimensions...') and when with an explicit 'Use when...' clause listing several triggers, matching the score-3 anchor.	3 / 3
Trigger Term Quality	Explicit triggers are present ('after modifying shared constants or configs', 'after batch file modifications') but lean technical ('3+ architectural layers', 'same-layer consistency checks'), missing more natural colloquial phrasings a user would say.	2 / 3
Distinctiveness Conflict Risk	It carves a clear niche (post-implementation multi-layer verification) with specific triggers unlikely to fire for unrelated skills, satisfying the score-3 anchor.	3 / 3
	Total	11 / 12 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: 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: zhukunpenglinyutong/desktop-cc-gui
Path: .agents/skills/check-cross-layer/SKILL.md
Commit: 5347fbb

Reviewed: about 15 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.