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.

1.81x

Quality

72%

Does it follow best practices?

Impact

100%

1.81x

Average score across 1 eval scenario

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

70%Weight 40%Scale 1-5

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-sequenced, highly actionable process skill with strong workflow clarity and explicit validation gates. It is weakened by repetition of the gating message, some general design-principle padding, and a bundle whose scripts are not navigated from the body.

Suggestions

Consolidate the repeated approval-gate messaging (HARD-GATE, Anti-Pattern, Red Flags, Terminal states) into a single authoritative section and reference it, to cut token cost.

Trim 'Design for isolation and clarity' and 'Working in existing codebases' to only the non-obvious guidance specific to brainstorming, since Claude already knows general decomposition principles.

Surface the scripts/ bundle from the body (e.g., link start-server.sh / server.cjs in the Visual Companion section) and ensure visual-companion.md is actually present in the bundle so the one-level reference resolves.

Dimension	Reasoning	Score
Conciseness	Mostly efficient process guidance, but the approval gate is restated across HARD-GATE, Three Paths, Anti-Pattern, Red Flags, Checklist, Process Flow, and Terminal states, and 'Design for isolation and clarity'/'Working in existing codebases' restate general development wisdom Claude already knows.	3 / 5
Actionability	Provides concrete guidance: numbered per-path checklists, a specific spec path 'docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md', message templates, and quantified rules ('one question per message', '2-3 sentences'), with only minor gaps.	4 / 5
Workflow Clarity	Each path has a sequenced checklist, the HARD-GATE defines explicit approval checkpoints, the dot diagram includes feedback loops ('no, revise', 'changes requested'), and the spec self-review is a validate-fix-retry loop.	5 / 5
Progressive Disclosure	Section structure is good and visual-companion.md is a clearly signaled one-level reference, but the actual scripts/ bundle files are never surfaced from the body and the referenced visual-companion.md is not present in the bundle.	3 / 5
	Total	15 / 20 Passed

Description

75%Weight 40%Scale 1-5

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 states both what the skill does and when to use it, with concrete trigger phrases. Its main weaknesses are second-person voice and a broad trigger scope that creates overlap risk with sibling skills.

Suggestions

Rewrite in third person to avoid the 'You MUST use this' phrasing (e.g., 'Explores user intent, requirements, and design before implementation. Use before creative work such as creating features, building components, adding functionality, or modifying behavior.').

Narrow the trigger scope or add discriminating language so it is less likely to fire for implementation skills like frontend-design, writing-plans, or mcp-builder.

Add a couple of natural synonyms users say (e.g., 'brainstorm', 'design a feature', 'spec out') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Explores user intent, requirements and design before implementation') plus a trigger list, but opens with second person 'You MUST use this', which per the rubric reduces the specificity score by one from a base of 4.	3 / 5
Completeness	Clearly 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') with concrete trigger phrases.	5 / 5
Trigger Term Quality	'creating features, building components, adding functionality, or modifying behavior' are natural phrases a user might say, with good coverage but missing common synonyms, fitting the 4 anchor rather than the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	'before any creative work' is broad and overlaps with related implementation/planning skills (frontend-design, writing-plans, mcp-builder), so it could still trigger for the wrong skill.	3 / 5
	Total	15 / 20 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
Path: skills/brainstorming/SKILL.md
Commit: 5bf4e78

Reviewed: 1 day 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.