This skill should be used when the user says "feature extract", "arn feature extract", "extract features", "feature backlog", "create backlog", "list features", "what features do we need", "prioritize features", "feature list", "build the backlog", "what should we build", "upload features", "feature tracker", or wants to extract a structured, prioritized feature list with journey steps, validated components, use case context, and UI behavior details from all project artifacts, producing a feature backlog document with a Feature Tracker that bridges into arn-code-feature-spec and optionally uploads features to the issue tracker.
78
73%
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-feature-extract/SKILL.mdQuality
Discovery
100%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 excels at providing explicit trigger terms and clearly defining both what the skill does and when to use it. The extensive list of trigger phrases ensures reliable skill selection, and the specific outputs (feature backlog, Feature Tracker, journey steps) make the capability concrete. However, the description is structured as a single long sentence which slightly hurts readability, and it leads with trigger terms rather than a concise capability summary.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: extract structured/prioritized feature list, produce feature backlog document with Feature Tracker, bridge into arn-code-feature-spec, upload features to issue tracker. Also mentions specific outputs like journey steps, validated components, use case context, and UI behavior details. | 3 / 3 |
Completeness | Clearly answers both 'what' (extract structured prioritized feature list with journey steps, validated components, use case context, UI behavior details, producing a feature backlog document with Feature Tracker) and 'when' (explicit trigger phrases listed at the start with 'This skill should be used when...'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including many variations users would actually say: 'feature extract', 'extract features', 'feature backlog', 'create backlog', 'list features', 'what features do we need', 'prioritize features', 'what should we build', 'upload features', 'feature tracker'. These are natural, conversational phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: feature extraction and backlog creation from project artifacts, with specific toolchain references (arn-code-feature-spec, Feature Tracker, issue tracker). The domain-specific terminology and explicit trigger phrases make it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill demonstrates excellent workflow design with clear sequencing, validation checkpoints, and comprehensive error handling, but it is severely over-verbose. The content repeats artifact descriptions across multiple sections, explains concepts Claude would already understand, and inlines massive amounts of detail that should be in reference files. The actionability is moderate — while steps are clear, the skill depends on external templates not provided in the bundle and uses descriptive rather than executable guidance for agent invocations.
Suggestions
Reduce the skill body by 50-60% by moving artifact descriptions, error handling tables, and the agent invocation guide into separate reference files, keeping only a concise summary in the main SKILL.md
Eliminate redundant artifact descriptions — the same artifacts (debate reports, showcase outputs, use cases) are described in Prerequisites, Step 1, and Step 2 with overlapping detail
Remove explanations of what artifacts contain (e.g., 'use cases with actor goals, main success scenarios, alternate flows, business rules, and postconditions') — Claude can read the files and understand their structure
Include the referenced template files (feature-entry-template.md, feature-backlog-template.md) in the bundle so the skill is self-contained and actionability can be fully assessed
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~500+ lines. It exhaustively explains every artifact type, every field, every edge case, and every possible user interaction. Much of this detail (e.g., explaining what use cases contain, what debate reports are, how to derive URLs from git remotes) is knowledge Claude already has or could infer. The artifact loading section alone repeats information multiple times across prerequisites, Step 1, and Step 2. | 1 / 3 |
Actionability | The skill provides concrete workflow steps, specific file paths, CLI commands (gh issue create), and detailed table formats. However, it relies heavily on external templates (feature-entry-template.md, feature-backlog-template.md, platform-labels.md) that are not provided in the bundle, and much of the guidance is procedural description rather than executable examples. The agent invocation instructions are descriptive rather than showing exact invocation syntax. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced across 8 steps with explicit validation checkpoints (gap resolution in Step 2b, sizing validation in Step 5, user confirmation before writing in Step 6, opt-in for issue upload in Step 7). Feedback loops are present (Step 4 refinement loop, gap resolution cycle between experts, retry on issue creation failure). The error handling section is comprehensive with specific recovery paths. | 3 / 3 |
Progressive Disclosure | The skill references external templates (feature-entry-template.md, feature-backlog-template.md, platform-labels.md) which is good progressive disclosure, but the main SKILL.md itself is a monolithic wall of text that inlines enormous amounts of detail that could be split into reference files. The agent invocation guide and error handling sections alone are substantial and could be separate files. No bundle files were provided to verify the referenced templates exist. | 2 / 3 |
Total | 8 / 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 | |
1fe948f
Table of Contents
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.