Name: arn-brainstorming
Rating: 68 (1 reviews)
Author: AppsVortex

arn-brainstorming

This skill should be used when the user says "brainstorming", "arn brainstorming", "brainstorm", "let's brainstorm", "start brainstorming", "brainstorming session", "greenfield wizard", "arn spark wizard", "greenfield pipeline", "walk me through greenfield", "guided greenfield", "full greenfield pipeline", "greenfield flow", "explore to feature backlog", "greenfield start to finish", "run the greenfield pipeline", "guide me through greenfield", "greenfield guided mode", "greenfield setup", "new project wizard", "add a feature", "new feature", "I need another feature", "add feature to greenfield", "one more feature", or wants to be walked through the entire Arness greenfield exploration pipeline in a single continuous session with guided decision gates instead of invoking each skill manually. Also triggers when the user wants to add a new feature to an existing greenfield project after the clickable prototype is complete.

Quality

83%

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

77%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-architected orchestrator with excellent actionability and workflow clarity: explicit skill invocations, a tabulated state machine, and robust resumability and error handling. Its main weaknesses are token waste from repeated ASCII progress diagrams and an inline monolithic core pipeline that underuses progressive disclosure.

Suggestions

Replace the ~12 near-duplicate ASCII pipeline diagrams with a single reusable template showing the current stage as a variable, cutting significant repeated tokens.

Tighten or remove the chatty 'Inform the user: ...' narration lines, which restate what the next Skill invocation already conveys.

Move the detailed per-gate option text and the resumability artifact table into a one-level-deep reference file (e.g. references/gates.md) so SKILL.md stays a lean overview, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The procedural content is dense and mostly necessary, but ~12 near-duplicate ASCII progress diagrams (one word capitalized per copy) and chatty 'Inform the user' lines consume tokens that could be tightened, matching 'mostly efficient but includes some unnecessary explanation'.	2 / 3
Actionability	It gives fully-qualified `Skill: arn-spark:...` invocations, exact artifact paths to check, and exact AskUserQuestion prompts with enumerated options, making the orchestrator guidance concrete and copy-paste executable.	3 / 3
Workflow Clarity	Steps 0-12 are clearly sequenced, the 9 gates are tabulated, resumability uses an explicit first-match-wins artifact table, and error handling provides retry/skip/abort feedback loops plus validation checkpoints (risks section, locked-prototype check).	3 / 3
Progressive Disclosure	The add-feature-flow.md reference is present, real, and clearly signaled one level deep, and Step 0 is split out, but the core 500-line pipeline remains an inline monolith that could benefit from further splitting, matching 'some structure but could be better organized'.	2 / 3
	Total	10 / 12 Passed

Description

90%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, trigger-rich description that clearly states what the skill does and when to invoke it, with distinctive natural-language triggers and correct third-person voice. Its only weakness is that the capability statement is a single abstract action rather than a list of concrete operations.

Dimension	Reasoning	Score
Specificity	It names the domain ('Arness greenfield exploration pipeline') and actions ('walk through... in a single continuous session with guided decision gates', 'add a new feature'), but describes essentially one overarching capability rather than a list of multiple concrete actions as the score-3 anchor requires.	2 / 3
Completeness	It explicitly answers both what (walk through the greenfield pipeline with guided decision gates) and when via the explicit 'This skill should be used when the user says...' trigger clause.	3 / 3
Trigger Term Quality	It enumerates many natural phrases a user would actually say ('brainstorming', 'let's brainstorm', 'greenfield wizard', 'add a feature', 'one more feature'), giving strong coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	The 'arn spark wizard' / 'greenfield pipeline' niche is highly distinctive and unlikely to trigger the wrong skill, and the description uses correct third-person voice ('the user says', 'the user wants').	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (521 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: AppsVortex/arness
Path: plugins/arn-spark/skills/arn-brainstorming/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.