cross-stack-bugfix

Diagnoses and fixes bugs that span multiple layers (runtime, CLI, UI, platform, tests) requiring coordinated changes across surfaces. Use when a bug does not map cleanly to a narrower skill, the fix touches more than one surface, or changes need cross-cutting validation.

Quality

86%

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

Quality

Content

86%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 concise, well-structured instruction-only skill with concrete commands and a verification checkpoint. Its main gap is that the diagnosis and implementation steps are directive rather than prescriptive, and the workflow lacks an explicit error-recovery loop.

Suggestions

Add a concrete 'how to diagnose' pointer or checklist for identifying impacted surfaces, so steps 1-3 are actionable rather than directive.

Articulate an explicit validate-fix-retry loop in the Workflow (e.g., 'If agent-report surfaces mismatches, fix and re-run until clean') to support the multi-surface verification.

Confirm the Must Read reference path resolves from the skill location, since no bundle directory exists to host it.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept re-explanation or padding; every section (Trigger, Workflow, Gotchas, Commands, Acceptance) earns its tokens and assumes Claude's competence.	5 / 5
Actionability	Provides copy-paste-ready commands (make agent-report, make agent-feature-gate) and a real doc reference, but the diagnose/implement steps remain high-level rather than prescribing how to diagnose; minor gaps keep it below 5.	4 / 5
Workflow Clarity	A clear five-step sequence with an explicit verification checkpoint (make agent-report) and an Acceptance checklist; falls short of 5 because the workflow does not articulate an explicit validate-fix-retry feedback loop despite handling multi-surface changes.	4 / 5
Progressive Disclosure	Well-organized sections with a single one-level-deep, clearly signaled reference under 'Must Read'; for a sub-50-line skill this matches the top anchor (no bundle files present to verify against).	5 / 5
	Total	18 / 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.

A strong description that concretely scopes a multi-surface bugfix niche, provides explicit 'Use when' triggers, and actively reduces overlap risk by deferring to narrower skills. The only weakness is a limited action vocabulary (diagnose/fix) and somewhat abstract trigger phrasing.

Dimension	Reasoning	Score
Specificity	Names the multi-layer domain and enumerates concrete surfaces (runtime, CLI, UI, platform, tests) with two distinct actions (diagnose, fix), matching the 'several specific actions with minor gaps' anchor; not 5 because the action set is limited to diagnose/fix rather than many distinct operations.	4 / 5
Completeness	Clearly answers both 'what' (diagnoses and fixes multi-layer bugs requiring coordinated changes) and 'when' (a three-part 'Use when...' clause with concrete triggers), matching the top anchor.	5 / 5
Trigger Term Quality	Explicit trigger clauses ('bug does not map cleanly to a narrower skill', 'fix touches more than one surface', 'cross-cutting validation') give good keyword coverage a user would naturally say; not 5 because it lacks comprehensive synonyms or file-extension-style natural variations.	4 / 5
Distinctiveness Conflict Risk	Positions itself as an explicit fallback that defers to narrower skills, giving a clear niche (cross-surface coordination) with minimal conflict risk.	5 / 5
	Total	18 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: vllm-project/semantic-router
Path: tools/agent/skills/cross-stack-bugfix/SKILL.md
Commit: e73c772

Reviewed: 9 days 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.