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

78%

Does it follow best practices?

Impact

60%

1.05x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./eval/local/skills/benchmarks/dependency/superpowers/brainstorming/SKILL.md

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

Quality

Content

73%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.

A well-structured, actionable process skill with excellent workflow clarity and validation checkpoints. Its main weakness is repetition of the approval gate across several sections, which inflates token cost without adding guidance.

Suggestions

Consolidate the approval-before-implementation rule into the HARD-GATE and remove its restatements in the anti-pattern section, terminal-state note, and Key Principles to reduce repetition.

Trim Key Principles to items not already detailed in The Process section, or remove it in favor of the inline process steps.

Add explicit navigation to the scripts bundle (e.g., 'start: scripts/start-server.sh --open; stop: scripts/stop-server.sh') so the server tooling is discoverable from the body.

Dimension	Reasoning	Score
Conciseness	Mostly efficient prose with useful checklists, but the approval-before-implementation gate is restated multiple times (HARD-GATE, anti-pattern section, terminal-state warning, Key Principles) and Key Principles repeats items already covered in The Process.	3 / 5
Actionability	Provides a concrete ordered checklist, a process flow diagram, an explicit spec path, a four-step spec self-review, and a ready-to-paste companion offer message, with minor gaps such as an example design-doc structure.	4 / 5
Workflow Clarity	Clear sequenced checklist with a DOT flow diagram containing decision diamonds and explicit feedback loops ('no, revise', 'changes requested'), plus validation checkpoints (spec self-review and user review gate).	5 / 5
Progressive Disclosure	Well-sectioned body with a clearly signaled one-level-deep reference to visual-companion.md and an indirectly referenced scripts bundle (server --open), though the scripts are not enumerated with explicit navigation links.	4 / 5
	Total	16 / 20 Passed

Description

83%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.

A strong description that clearly states both purpose and trigger conditions with concrete, natural language. Minor gaps in action coverage and synonym breadth keep specificity and trigger quality just below maximum.

Dimension	Reasoning	Score
Specificity	Names several concrete trigger actions ('creating features, building components, adding functionality, or modifying behavior') and the core action ('Explores user intent, requirements and design'), with minor gaps such as producing a written spec.	4 / 5
Completeness	Explicitly answers both what ('Explores user intent, requirements and design before implementation') and when ('before any creative work - creating features...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users say ('creating features', 'building components', 'adding functionality') with good coverage, but misses common synonyms like 'brainstorming', 'designing', or 'planning a feature'.	4 / 5
Distinctiveness Conflict Risk	The 'before implementation / design' framing carves a distinct pre-implementation niche, though 'any creative work' is broad and carries minor overlap risk with related design skills.	4 / 5
	Total	17 / 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: rpamis/comet
Path: eval/local/skills/benchmarks/dependency/superpowers/brainstorming/SKILL.md
Commit: 99fd749

Reviewed: 3 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.