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.

1.44x

Quality

68%

Does it follow best practices?

Impact

75%

1.44x

Average score across 10 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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

Quality

Content

67%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 clear, actionable, well-sequenced process guide that avoids explaining concepts Claude already knows. Its main improvement opportunity is tightening redundancy between The Process and Key Principles, and adding one or two concrete examples (a sample multiple-choice question, a short design-section excerpt) to lift actionability.

Suggestions

Remove or condense the 'Key Principles' section since each point already appears in 'The Process', or repurpose it as a quick-reference checklist that does not repeat prose.

Add one concrete example multiple-choice question and a short 200-300 word sample design section so the interaction pattern is unambiguous.

Specify a validation step before writing the design doc (e.g. 'confirm the user has accepted all sections before committing') to make the workflow's checkpoint fully explicit.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the 'Key Principles' section restates points already made in 'The Process' (one question at a time, multiple choice, explore alternatives, incremental validation), which is removable redundancy.	3 / 5
Actionability	Guidance is concrete and specific for an instruction-only skill: 'ask questions one at a time', 'propose 2-3 approaches with trade-offs', 'present in 200-300 word sections', and a concrete output path 'docs/plans/YYYY-MM-DD-<topic>-design.md'; minor gaps are the absence of example questions or a sample design section.	4 / 5
Workflow Clarity	The process is clearly sequenced (understand -> explore approaches -> present design -> document/implement) with explicit checkpoints ('checking after each section whether it looks right') and a feedback loop ('be ready to go back and clarify'), though error-recovery guidance is soft rather than a concrete checklist.	4 / 5
Progressive Disclosure	Content is well organized into clear sections and appropriately delegates to other skills (writing-plans, using-git-worktrees) at one level deep, but the file is slightly over the ~50-line simple-skill threshold and all detail lives inline in SKILL.md rather than being split into referenced files.	4 / 5
	Total	15 / 20 Passed

Description

70%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 conveys both purpose and trigger conditions with concrete, natural-language phrases. Its main weaknesses are the second-person opening (which violates the third-person voice requirement and caps specificity) and somewhat broad triggers that risk overlap with related planning/implementation skills.

Suggestions

Rewrite in third person to avoid the specificity penalty, 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.'

Sharpen the 'what' beyond a single verb by naming concrete outputs (e.g. 'refines requirements, evaluates 2-3 approaches with trade-offs, and produces a validated design document').

Narrow the trigger language to the design/brainstorming phase to reduce overlap with implementation skills like writing-plans.

Dimension	Reasoning	Score
Specificity	The 'what' is a single action ('Explores user intent, requirements and design before implementation') with the creative-work list serving as triggers rather than distinct capabilities, fitting anchor 3; reduced to 2 because the description opens with second-person voice ('You MUST use this...'), which the rubric penalizes by one point on specificity.	2 / 5
Completeness	It explicitly answers both what ('Explores user intent, requirements and design before implementation') and when ('You MUST use this before any creative work - creating features...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Phrases like 'creating features, building components, adding functionality, or modifying behavior' are natural terms a user would say when needing this skill, giving good keyword coverage though a few common synonyms (e.g. 'designing', 'planning') are missing.	4 / 5
Distinctiveness Conflict Risk	The 'brainstorming/design before implementation' niche is somewhat distinct, but the broad 'any creative work... adding functionality, or modifying behavior' triggers overlap with the implementation and planning skills the body itself references.	3 / 5
	Total	14 / 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: roman01la/skills-agents
Path: skills/brainstorming/SKILL.md
Commit: aa6f9d3

Reviewed: 10 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.