arn-spark-help
This skill should be used when the user says "spark help", "arn spark help", "greenfield status", "greenfield help", "where am I in spark", "what's next for spark", "spark pipeline", "spark status", "arn-spark-help", "show spark pipeline", "what step am I on for spark", "spark workflow", "exploration status", "show exploration pipeline", "how does spark work", "explain spark pipeline", or wants to see their current position in the Arness Spark exploration pipeline and get guidance on the next step.
75
70%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/arn-spark/skills/arn-spark-help/SKILL.mdQuality
Discovery
62%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is heavily weighted toward trigger phrases but severely lacks specificity about what the skill actually does. While it excels at listing when to use it and is clearly distinctive, it reads more like a keyword list than a capability description. The 'what' portion needs substantial improvement to describe concrete actions and outputs.
Suggestions
Add specific capability descriptions before the trigger list, e.g., 'Displays the user's current stage in the Arness Spark exploration pipeline, shows completed and remaining steps, and provides actionable guidance for the next step.'
Restructure to lead with concrete actions (what it does) followed by a 'Use when...' clause, rather than opening with the trigger phrase list.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists trigger phrases but never describes concrete actions the skill performs. It vaguely mentions 'see their current position' and 'get guidance on the next step' but doesn't explain what the skill actually does (e.g., display pipeline stages, show completion percentage, recommend actions). | 1 / 3 |
Completeness | The 'when' is thoroughly covered with explicit trigger phrases, but the 'what' is extremely weak — it only vaguely says 'see their current position in the Arness Spark exploration pipeline and get guidance on the next step' without describing what the skill actually does or produces. | 2 / 3 |
Trigger Term Quality | The description includes an extensive list of natural trigger phrases users would say, covering many variations like 'spark help', 'spark status', 'what's next for spark', 'where am I in spark', 'greenfield status', etc. These are realistic user utterances with good coverage. | 3 / 3 |
Distinctiveness Conflict Risk | The skill is highly distinctive due to the specific product name 'Arness Spark' and 'greenfield' terminology. It's unlikely to conflict with other skills given these unique domain-specific triggers. | 3 / 3 |
Total | 9 / 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 read-only status skill with clear workflow sequencing and comprehensive error handling. Its main weakness is moderate verbosity — the FAQ section and cross-plugin rendering examples could be tightened or moved to reference files. The detection logic is precise and unambiguous, making it easy for Claude to execute reliably.
Suggestions
Move the FAQ content from Step 4 into a separate reference file (e.g., references/faq.md) to reduce the SKILL.md body length and improve progressive disclosure.
Tighten the cross-plugin hint examples in Step 3 — the three conditional cases could be condensed into a compact table rather than verbose code blocks.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary verbosity, particularly the extensive FAQ section in Step 4 which could be more tightly structured. The cross-plugin awareness rendering examples and multi-case output formatting add bulk, though most content is functional rather than explanatory. | 2 / 3 |
Actionability | The skill provides highly specific, concrete detection rules with exact file paths to check, a clear priority ordering (most advanced to least), specific tool constraints, and precise output formatting guidance. Every step has unambiguous instructions Claude can execute directly. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced across 5 steps (0-4) with explicit ordering logic ('first match wins'), clear conditional branching for edge cases, comprehensive error handling, and well-defined state transitions. The detection cascade from most to least advanced is an effective validation pattern for a read-only status check. | 3 / 3 |
Progressive Disclosure | The skill references an external pipeline-map.md file for detection rules and rendering templates, which is good progressive disclosure. However, no bundle files were provided to verify this reference exists, and the FAQ content in Step 4 could potentially be split into a separate reference file. The inline content is somewhat long for a single SKILL.md but reasonably organized with clear section headers. | 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.