Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agent-sh/enhance-cross-file
Use when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules, contradictions.
Passed 13 of 17 test cases with the skill, and 5 of 17 without it.
and 9 more in the full report
12 fixed5 passed either way3 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
File A contains 'ALWAYS generate commit messages in conventional style' and File B contains 'NEVER generate commit messages in conventional style'. What category of finding is this?
| Checked | Without skill | With skill |
|---|---|---|
| Classifies ALWAYS vs NEVER rule conflicts under Instruction Consistency | Missed | Passed |
The instructions your model reads when the skill loads.
Analyze cross-file semantic consistency across agents, skills, and workflows.
const args = '$ARGUMENTS'.split(' ').filter(Boolean);
const targetPath = args.find(a => !a.startsWith('--')) || '.';
Detects issues that span multiple files - things single-file analysis misses:
Run Analyzer - Execute the JavaScript analyzer to get findings:
node -e "const a = require('./lib/enhance/cross-file-analyzer.js'); console.log(JSON.stringify(a.analyze('.'), null, 2));"
For a specific path: a.analyze('./plugins/enhance')
Parse Results - The analyzer returns JSON with summary and findings
Report - Return findings grouped by category
The JavaScript analyzer (lib/enhance/cross-file-analyzer.js) implements all cross-file detection. The patterns below are reference documentation.
tool_not_in_allowed_list: Tool used in prompt body but not in frontmatter tools: list
test cases passed, vs 5 / 17 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.