Name: arn-spark-use-cases-teams
Rating: 72 (1 reviews)
Author: AppsVortex

arn-spark-use-cases-teams

This skill should be used when the user says "use cases teams", "arn use cases teams", "team use cases", "debate use cases", "collaborative use cases", "use cases with debate", "team-based use case review", "use case debate", "review use cases as a team", or wants to create structured use case documents through expert debate where product strategist and UX specialist review and discuss each other's findings before revising, producing a use-cases/ directory with individual Cockburn fully-dressed use case files and a README index.

Quality

88%

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.

A well-structured, highly actionable orchestration skill with clear sequencing, validation checkpoints, feedback loops, and clean progressive disclosure of detail into reference files. The main weakness is conciseness, primarily from the Agent Invocation Guide table duplicating the workflow prose.

Suggestions

Remove or sharply condense the Agent Invocation Guide table, which duplicates Steps 4–6 in detail; keep it only for genuinely novel cross-references not already covered in the workflow.

Tighten the Step 5a prose (agent_teams vs sequential vs single-reviewer) into a more compact decision format to reduce length without losing the concrete file-path guidance.

Consider condensing the Error Handling bullet list by merging closely related fallback cases (e.g., the directory-creation and writer-failure print-in-conversation fallbacks) to trim the tail of the skill.

Dimension	Reasoning	Score
Conciseness	The body is operationally specific with no concept-padding Claude already knows, but the Agent Invocation Guide table restates Steps 4–6 in full and several prose blocks could be tightened, so it is mostly efficient with some redundancy rather than lean.	2 / 3
Actionability	Guidance is copy-paste ready: exact agent names, exact file paths (e.g. [use-cases-dir]/reviews/round-N-business-review.md), an executable env-var check (echo $CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS), explicit reference paths to read, and ready-to-use AskUserQuestion prompts with options — fully actionable for an instruction-only skill.	3 / 3
Workflow Clarity	The 8-step workflow (with sub-steps 5a–5e) is clearly sequenced with explicit validation checkpoints (env-var check, agent-availability probe, resume detection), user-confirmation gates, and a convergence feedback loop (debate → revise → convergence check → stop or next round), and destructive overwrites are gated by the Step 1 user decision.	3 / 3
Progressive Disclosure	SKILL.md is an overview that points to real, verified one-level-deep references (references/debate-protocol.md and references/review-report-template.md) via clearly signaled 'Read <path>' instructions, with no nested reference chains and detail appropriately externalized.	3 / 3
	Total	11 / 12 Passed

Description

92%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.

A strong, explicit description that clearly states both capabilities and trigger conditions with good keyword coverage. Its main weakness is overlap with the sibling arn-spark-use-cases skill, which the description does not itself disambiguate.

Suggestions

Add a brief disambiguating clause contrasting this skill with /arn-spark-use-cases (e.g., 'use this debate-driven variant instead of /arn-spark-use-cases when…') to reduce trigger conflict with the sibling skill.

Trim near-duplicate trigger phrases (e.g., 'use case debate' vs 'debate use cases' vs 'use cases with debate') to keep the trigger list concise without losing coverage.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete actions ('create structured use case documents through expert debate', 'review and discuss each other's findings before revising', 'producing a use-cases/ directory with individual Cockburn fully-dressed use case files and a README index'), matching the anchor for listing several specific concrete actions rather than merely naming a domain.	3 / 3
Completeness	It explicitly answers both 'what' (debate-driven Cockburn use case production) and 'when' via an explicit trigger clause ('This skill should be used when the user says…'), so the 'when' is stated rather than merely implied.	3 / 3
Trigger Term Quality	It supplies broad coverage of natural phrasings a user might say ('team use cases', 'debate use cases', 'collaborative use cases', 'use cases with debate', 'team-based use case review', 'review use cases as a team'), meeting the good-coverage anchor rather than a single keyword.	3 / 3
Distinctiveness Conflict Risk	The debate/team niche and triggers are fairly specific, but the skill overlaps with the sibling arn-spark-use-cases skill (both produce 'use cases' / a use-cases/ directory) and the description field itself does not disambiguate the two, so 'unlikely to conflict' is not fully met.	2 / 3
	Total	11 / 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-use-cases-teams/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.