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.

1.17x

Quality

67%

Does it follow best practices?

Impact

74%

1.17x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is brainstorming in obra/superpowers

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 content is highly actionable and workflow-clear with strong validation gates, but it carries some repeated gating language and points to a referenced guide file that does not exist in the bundle. Fixing the broken reference and deduplicating the prohibition would lift the score.

Suggestions

Add the missing 'visual-companion.md' to the bundle (e.g., references/) or remove the instruction to read it, since the referenced path currently resolves to no file.

Surface the existing scripts/ (frame-template.html, helper.js, server.cjs, start-server.sh, stop-server.sh) as a clearly signaled reference so the visual companion tooling is discoverable.

Consolidate the repeated 'do NOT invoke implementation skills / only writing-plans' prohibition into one authoritative statement to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete checklists and quoted messages, but the 'do not invoke implementation skills' prohibition is repeated across the HARD-GATE, anti-pattern, process flow, terminal-state, and implementation sections, so it could be tightened.	2 / 3
Actionability	It gives an ordered 9-step checklist, an exact spec path 'docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md', a verbatim companion-offer message, and concrete self-review criteria, providing copy-paste-ready guidance.	3 / 3
Workflow Clarity	The multi-step process is clearly sequenced with a dot graph and explicit validation checkpoints — user approves design, spec self-review, user reviews spec — plus 'only proceed once the user approves' feedback loops.	3 / 3
Progressive Disclosure	Sections are well organized, but the body references a guide at 'skills/brainstorming/visual-companion.md' that is not present in the bundle, and the existing scripts/ files are not surfaced as navigable references.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 answers both what and when, but its second-person voice triggers a specificity penalty and its broad 'any creative work' framing risks overlap with other skills. Tightening the trigger to natural user phrasings and using third person would raise the score.

Suggestions

Rewrite in third person (e.g., 'Processes ideas into designs...') to avoid the specificity penalty for second-person voice.

Add concrete natural trigger terms users would actually say, such as 'Use when brainstorming, planning a feature, or designing a component before implementation'.

Narrow the scope to reduce overlap, e.g. 'Use before designing or planning any new feature or component' instead of the catch-all 'any creative work'.

Dimension	Reasoning	Score
Specificity	The phrase 'creating features, building components, adding functionality, or modifying behavior' names several actions, but the description uses second person ('You MUST use this'), which the rubric penalizes by reducing specificity by one point, dropping it from 2 to 1.	1 / 3
Completeness	It explicitly states both what it does ('Explores user intent, requirements and design before implementation') and when to use it ('before any creative work - creating features, building components, adding functionality, or modifying behavior').	3 / 3
Trigger Term Quality	Terms like 'creating features', 'building components', and 'adding functionality' are relevant, but common user phrasings such as 'design', 'brainstorm', or 'plan a feature' are missing, leaving incomplete natural-keyword coverage.	2 / 3
Distinctiveness Conflict Risk	The 'any creative work' framing is broad and would overlap with frontend-design, writing-plans, and general implementation skills, so it is only somewhat specific and could conflict.	2 / 3
	Total	8 / 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: openai/plugins
Path: plugins/superpowers/skills/brainstorming/SKILL.md
Commit: 11c74d6

Reviewed: about 10 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.