Name: arn-spark-feature-extract
Rating: 74.4 (1 reviews)
Author: AppsVortex

arn-spark-feature-extract

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.

Quality

92%

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

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is a thorough, actionable, well-sequenced conversational workflow with strong progressive disclosure via two reference templates. Its main weakness is verbosity from repeated dispatch boilerplate and a redundant agent-invocation guide that re-covers material already in the steps.

Suggestions

Define the agent-dispatch convention once (e.g. in a short 'Agent dispatch' subsection or a referenced file) and reference it from Steps 2 and 2b instead of repeating the full 'passing the model from .arness/agent-models/spark.md ... see ensure-config.md' boilerplate each time.

Trim or fold the 'Agent Invocation Guide' table into the workflow steps, since most rows restate actions already specified in Steps 2-4; keep only the rows that add new guidance (e.g. the 'Defer technology/implementation questions' rows).

Consolidate the long bullet list of artifact paths in Prerequisites/Step 1 into a single table or a referenced 'artifacts.md' reference file to reduce inline token load.

Dimension	Reasoning	Score
Conciseness	The body is largely project-specific procedural guidance Claude does not already know, but it is padded with repetition — the agent-dispatch boilerplate ('Invoke ... via the Task tool, passing the model from .arness/agent-models/spark.md ... see ensure-config.md "Dispatch convention" for fallback') is repeated verbatim several times, and the 'Agent Invocation Guide' table restates content already in the workflow steps.	2 / 3
Actionability	Highly executable: exact file paths, concrete commands ('gh issue create --title "F-NNN: ..." --label "arness-feature-issue,..."'), copy-paste user-facing prompts in quotes, and specific templates to read make the guidance directly actionable.	3 / 3
Workflow Clarity	A clear 8-step sequence with explicit checkpoints and feedback loops — gap detection/resolution (Step 2b), sizing validation before writing (Step 5), and batch issue-creation gating ('Wait for each batch to complete before starting the next') with retry-on-failure handling.	3 / 3
Progressive Disclosure	Detailed material is split into real one-level-deep bundle files (references/feature-entry-template.md and references/feature-backlog-template.md) that are clearly signaled and referenced by path, keeping the SKILL.md body as an overview that points to the templates for field definitions.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 is well-crafted: it pairs a dense 'what' statement with an explicit, comprehensive set of natural trigger phrases, and uses third-person/passive voice throughout. It clearly communicates both capability and invocation context with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'extract a structured, prioritized feature list', 'producing a feature backlog document', 'bridges into arn-code-feature-spec', 'optionally uploads features to the issue tracker' — rather than vague language.	3 / 3
Completeness	Explicitly answers both 'what' (extract/produce a feature backlog document with Feature Tracker) and 'when' (the 'should be used when the user says...' clause with explicit triggers).	3 / 3
Trigger Term Quality	Extensive natural trigger phrases a user would actually say ('feature extract', 'create backlog', 'list features', 'what should we build', 'prioritize features', 'feature tracker') with good coverage of variations.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Arness feature-extraction/backlog pipeline) with 'arn'-prefixed and feature-specific triggers unlikely to conflict with unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: AppsVortex/arness
Path: plugins/arn-spark/skills/arn-spark-feature-extract/SKILL.md
Commit: 7f87870

Reviewed: 14 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.