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.

1.05x

Quality

—

Does it follow best practices?

Impact

60%

1.05x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

77%

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

The body is a well-structured, highly actionable brainstorming workflow with strong validation gates and feedback loops. Its main weaknesses are repetition that inflates the token budget and a broken/unsurfaced reference to the visual-companion guide and its scripts.

Suggestions

De-duplicate the 'Do NOT invoke any other skill / only writing-plans' rule to a single stated location and remove the general 'Design for isolation and clarity' principles Claude already knows to tighten conciseness.

Provide the referenced visual-companion.md file (or correct the path) and explicitly link the bundled scripts (e.g. 'start the server with scripts/start-server.sh --open') so progressive disclosure is navigable.

Consolidate the repeated 'one question at a time' guidance so it appears once rather than in the checklist, process, and key-principles sections.

Dimension	Reasoning	Score
Conciseness	Mostly efficient process guidance, but it repeats itself ('Do NOT invoke any other skill' appears at lines 13, 61, 131; 'one question at a time' in checklist, process, and key principles) and restates general design wisdom Claude already knows ('can someone understand a unit without reading its internals'), so it could be tightened.	2 / 3
Actionability	Highly actionable for an instruction skill: an ordered 9-item checklist, exact spec path 'docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md', a verbatim user-review-gate prompt, a verbatim visual-companion offer, and concrete decision criteria ('would the user understand this better by seeing it than reading it?').	3 / 3
Workflow Clarity	Clear sequence with explicit validation checkpoints: a numbered checklist, a process-flow diagram with revise loops, the HARD-GATE before implementation, the spec self-review loop, and a user-review gate with a fix-and-retry feedback loop.	3 / 3
Progressive Disclosure	Sections are well organized and the visual-companion detail is appropriately deferred to a separate guide, but the referenced 'skills/brainstorming/visual-companion.md' does not exist in the bundle and the bundled scripts/ files (server.cjs, start-server.sh, etc.) are never referenced by path, leaving navigation broken.	2 / 3
	Total	10 / 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 is explicit on both purpose and trigger, but the broad 'any creative work' trigger surface creates overlap risk and it uses second-person voice which costs specificity. Tightening the trigger terms and dropping 'You' would lift the score.

Suggestions

Rewrite in third person to avoid the specificity penalty — e.g. 'Explores user intent, requirements, and design before implementation. Use before any creative work such as creating features, building components, adding functionality, or modifying behavior.'

Add natural trigger variations users actually say (brainstorm, design, plan an approach, scope a feature) so trigger_term_quality reaches 3.

Narrow the trigger to reduce conflict with implementation skills — emphasize 'before implementation' framing rather than the broad 'any creative work' net.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('creating features, building components, adding functionality, or modifying behavior', 'Explores user intent, requirements and design') which would anchor at 3, but the description opens with second-person voice ('You MUST use this before any creative work'), so per the voice guideline specificity is reduced by 1.	2 / 3
Completeness	Clearly answers both what ('Explores user intent, requirements and design before implementation') and when with an explicit trigger ('before any creative work - creating features, building components, adding functionality, or modifying behavior'), so it is not capped at 2 for a missing trigger clause.	3 / 3
Trigger Term Quality	Phrases like 'creating features' and 'modifying behavior' are natural, but the umbrella 'creative work' is generic-as-trigger and common variations users actually say (brainstorm, design, plan, architecture) are absent, matching 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The 'before any creative work' gate gives a niche, but the trigger surface ('creating features, building components, adding functionality, or modifying behavior') is broad and would fire for almost any coding task, overlapping with implementation skills.	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: obra/superpowers
Commit: d884ae0

Reviewed: 4 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.