arn-infra-triage
This skill should be used when the user says "triage infra request", "infra triage", "arn infra triage", "process infra issue", "handle infra request", "infrastructure request", "triage infrastructure", "analyze infra issue", "infra request analysis", "process infrastructure request", or wants to process an incoming infrastructure request issue created by Arness Core or manually, analyze its infrastructure implications, and produce a structured implications brief.
86
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
89%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 excels at trigger term coverage and completeness, providing extensive explicit trigger phrases and clearly stating both what the skill does and when to use it. Its main weakness is that the capability description could be more specific about the concrete actions and outputs involved in the triage process. The heavy front-loading of trigger phrases makes it functional but somewhat list-heavy rather than naturally descriptive.
Suggestions
Add more specific concrete actions beyond 'analyze implications' and 'produce a structured implications brief' — e.g., describe what the brief contains, what systems are checked, or what categorization is performed.
Consider restructuring to lead with a concise capability statement followed by a 'Use when...' clause, rather than front-loading all trigger phrases which makes the description harder to scan.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions 'process an incoming infrastructure request issue', 'analyze its infrastructure implications', and 'produce a structured implications brief', which names the domain and some actions but lacks detail on what specific concrete steps or outputs are involved beyond a generic 'implications brief'. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (process infrastructure request issues, analyze implications, produce a structured implications brief) and 'when' (with a comprehensive list of trigger phrases and contextual conditions like 'when the user says...' or 'wants to process an incoming infrastructure request'). | 3 / 3 |
Trigger Term Quality | The description includes an extensive list of natural trigger phrases users would say, covering many variations like 'triage infra request', 'infra triage', 'process infra issue', 'infrastructure request', 'analyze infra issue', etc. These are realistic phrases a user would type. | 3 / 3 |
Distinctiveness Conflict Risk | The skill is highly specific to infrastructure request triage with distinct terminology like 'Arness Core', 'implications brief', and 'infra triage', making it very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with a clear multi-step workflow, comprehensive error handling, and good decision trees. Its main weakness is moderate verbosity — some explanatory context could be trimmed — and the main file carries substantial inline detail that could benefit from being split into reference files. The references to external templates and derivation mappings demonstrate good progressive disclosure intent, though the bundle files aren't available to verify.
Suggestions
Trim introductory/explanatory text (e.g., 'This skill bridges application feature development...' and the paragraph explaining what infrastructure request issues are) — Claude can infer this from context.
Consider extracting the agent invocation prompt template and topology-aware behavior details into a reference file to reduce the main SKILL.md length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient for its complexity but includes some unnecessary explanation (e.g., 'This skill bridges application feature development and infrastructure provisioning' and explaining what infrastructure request issues are). Some sections like the free-form parsing guidance and topology-aware behavior explanations could be tightened. | 2 / 3 |
Actionability | The skill provides concrete, executable commands (gh issue view, gh issue edit), specific tool invocations (Task tool with structured prompt template, AskUserQuestion), exact file paths to read, and clear decision trees. The agent invocation prompt template is copy-paste ready with clear placeholder conventions. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with explicit validation checkpoints: prerequisite checks (Arness config, Deferred mode), label verification before proceeding, error handling for each step, fallback behaviors for unreachable paths, and a decision tree for next steps. The error handling section covers failure modes comprehensively with recovery actions. | 3 / 3 |
Progressive Disclosure | The skill references external files (infra-request-template.md, implications-brief-template.md, experience-derivation.md) which is good progressive disclosure, but no bundle files were provided to verify these exist. The main SKILL.md itself is quite long (~150+ lines of substantive content) and some sections like the full agent prompt template and detailed topology-aware behavior could potentially be extracted to reference files. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- AppsVortex/arness
- Commit
1fe948f
- 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.