brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./app/skills/brainstorming/SKILL.md

Quality

Content

62%

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

The skill body presents an exceptionally clear, well-sequenced brainstorming workflow with strong validation gates and feedback loops. Its weaknesses are repetition and over-explanation of known concepts, plus references to bundle files that are not actually present, which undermines both actionability and navigation.

Suggestions

Provide the referenced bundle files (spec-document-reviewer-prompt.md and visual-companion.md) in the references/ directory, or inline the essential parts and remove the dangling references, so the spec-review and visual-companion steps are actually executable.

De-duplicate the workflow: collapse the overlap between the Checklist, "The Process", "After the Design", and "Key Principles" sections into a single authoritative sequence, referencing it from the others rather than restating it.

Trim explanation of concepts Claude already knows (modularity, interface design, how it reasons about code in context) to keep only the skill-specific guidance, reducing token cost.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient process guidance, but it repeats the same workflow across the Checklist, "The Process", "After the Design", and "Key Principles" sections, and over-explains concepts Claude already knows (e.g., modularity, well-defined interfaces, and how Claude "reasons better about code you can hold in context at once"), so it could be tightened.	2 / 3
Actionability	Much of the guidance is concrete and specific (spec path `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md`, 2-3 approaches, max 5 iterations, exact visual-companion offer text), but two sub-steps reference files that are not in the bundle ("see spec-document-reviewer-prompt.md" and "read the detailed guide... skills/brainstorming/visual-companion.md"), leaving those instructions incomplete and non-executable.	2 / 3
Workflow Clarity	The multi-step process is clearly sequenced via a numbered 9-step checklist and a process-flow diagram, with explicit validation checkpoints (approval gates after each design section, a spec review loop with a 5-iteration cap, and a user review gate that waits for response) and feedback loops for error recovery.	3 / 3
Progressive Disclosure	Content is organized into clear, well-labeled sections and references are one-level-deep and clearly signaled, but the referenced files (spec-document-reviewer-prompt.md, visual-companion.md) do not exist in the bundle, breaking navigation, and the Visual Companion detail is largely inline rather than actually split out.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 clearly conveys both what the skill does and when to use it, with explicit triggers and concrete action terms. Its main weaknesses are second-person voice (costing specificity), a somewhat generic umbrella trigger, and overlap with implementation-skill triggers.

Suggestions

Rewrite in third person (e.g., "Explores user intent, requirements, and design before implementation") and drop the "You MUST use this" framing to restore specificity and align with rubric voice expectations.

Replace the generic "before any creative work" with concrete user-facing triggers such as "Use when the user asks to design, plan, or scope a new feature, component, or behavior change before implementation."

Sharpen distinctiveness by emphasizing the design/spec phase (e.g., "Use before implementation planning when a feature or component needs a design spec") to reduce overlap with implementation skills.

Dimension	Reasoning	Score
Specificity	The description names several concrete actions ("creating features, building components, adding functionality, or modifying behavior") and what it does ("Explores user intent, requirements and design"), which would warrant a 3, but the opening "You MUST use this" is second-person voice, which the rubric penalizes by reducing specificity by one.	2 / 3
Completeness	It explicitly answers both what ("Explores user intent, requirements and design before implementation") and when ("before any creative work - creating features, building components, adding functionality, or modifying behavior"), providing explicit trigger guidance equivalent to a "Use when" clause.	3 / 3
Trigger Term Quality	Terms like "creating features", "building components", "adding functionality", and "modifying behavior" are reasonably natural, but the umbrella trigger "before any creative work" is generic/abstract and the imperative "You MUST use this" framing does not cleanly map to a user utterance, leaving common variations uncovered.	2 / 3
Distinctiveness Conflict Risk	The pre-implementation design framing gives it a recognizable niche, but its trigger territory (creating features, building components, adding functionality, modifying behavior) overlaps heavily with the very implementation skills it gates, so it could still trigger for the wrong skill.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ZHangZHengEric/Sage
Path: app/skills/brainstorming/SKILL.md
Commit: ce79d60

Reviewed: about 18 hours 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.