CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

56

Quality

66%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/arn-spark/skills/arn-brainstorming/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

54%

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 at the expense of explaining what the skill actually does. While it excels at listing when to invoke it, it fails to describe the concrete actions, outputs, or workflow steps involved in the greenfield pipeline. The overly broad trigger terms like 'brainstorm' and 'new feature' also risk conflicting with other skills.

Suggestions

Add a clear 'what it does' section describing concrete actions (e.g., 'Guides users through project exploration, generates feature backlogs, creates clickable prototypes, and manages decision gates for new greenfield projects').

Narrow overly generic trigger terms like 'brainstorm' and 'new feature' by qualifying them (e.g., 'brainstorm in the context of Arness greenfield projects') to reduce conflict risk with other skills.

Restructure to follow the pattern: '[What it does]. Use when [trigger conditions].' instead of leading with a massive trigger phrase list.

DimensionReasoningScore

Specificity

The description is almost entirely trigger phrases with no concrete actions listed. It vaguely references 'the entire Arness greenfield exploration pipeline' and 'guided decision gates' but never explains what the skill actually does (e.g., generates project plans, creates prototypes, builds feature backlogs).

1 / 3

Completeness

The 'when' is extensively covered with explicit trigger phrases, but the 'what' is extremely weak — it only vaguely mentions being 'walked through the entire Arness greenfield exploration pipeline' without explaining what that pipeline does or what concrete outputs it produces. The 'what' is implied rather than clearly stated.

2 / 3

Trigger Term Quality

The description includes an extensive list of natural trigger phrases users would say, such as 'brainstorming', 'let's brainstorm', 'new project wizard', 'add a feature', 'new feature', and many variations. Coverage of natural terms is thorough.

3 / 3

Distinctiveness Conflict Risk

The extensive trigger list and 'Arness greenfield' branding create some distinctiveness, but generic terms like 'brainstorm', 'add a feature', and 'new feature' are very broad and could easily conflict with other brainstorming or feature-planning skills.

2 / 3

Total

8

/

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 orchestration skill that excels at actionability and workflow clarity — every step has concrete file paths, skill invocation names, and explicit decision logic. The artifact detection table for resumability is particularly thorough. The main weakness is that the skill is quite long for a sequencer that explicitly states it 'MUST NOT duplicate sub-skill logic' — some sections (stress test descriptions, error handling enumeration) could be more concise or split into reference files.

Suggestions

Move the detailed error handling section to a reference file (e.g., `references/error-handling.md`) since it covers 12+ edge cases that add significant length to the main skill body.

Trim the G-Stress stress test descriptions — since each sub-skill handles its own execution, the wizard only needs brief labels (e.g., 'Synthetic User Interview — persona-driven usability validation') rather than full explanations.

DimensionReasoningScore

Conciseness

The skill is quite long (~400+ lines) but most content is structural (decision gates, artifact detection tables, workflow steps). Some sections are unnecessarily verbose — the stress test explanations at G-Stress could be shorter since the sub-skills handle the actual work, and the error handling section enumerates many edge cases that could be more compact. However, it avoids explaining concepts Claude already knows and stays focused on sequencing logic.

2 / 3

Actionability

Highly actionable throughout: specific skill invocation names (`Skill: arn-spark:arn-spark-discover`), exact file paths to check for artifact detection, precise AskUserQuestion prompts with numbered options, concrete progress display formats, and explicit conditional logic for every decision gate. The artifact detection table maps specific files to specific resume points with no ambiguity.

3 / 3

Workflow Clarity

Exceptionally clear multi-step workflow with 12 numbered steps, 9 explicitly defined decision gates in a summary table and then detailed per-step, a comprehensive artifact detection table for resumability, and thorough error handling with retry/skip/abort options. Validation checkpoints are present (prototype verdict checking, feature upload verification at G6, locked prototype detection at G5). Feedback loops exist for prototype iteration and error recovery.

3 / 3

Progressive Disclosure

The skill references two external files (`step-0-fast-path.md` and `add-feature-flow.md`) which is good progressive disclosure for those concerns. However, the main SKILL.md itself is very long and monolithic — the detailed artifact detection table, all 9 gate definitions, and the extensive error handling section could potentially be split into reference files. The bundle shows no files were provided for evaluation, so we can't verify the referenced paths exist, but the references are clearly signaled and one-level deep.

2 / 3

Total

10

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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

9

/

11

Passed

Repository
AppsVortex/arness
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.