CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

1.17x
Quality

58%

Does it follow best practices?

Impact

74%

1.17x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/brainstorming/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

32%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description suffers from extreme over-breadth, claiming it MUST be used before essentially any development task. The 'what' is vague ('explores user intent, requirements and design') without listing concrete actions like 'generates requirement documents, creates design specs, asks clarifying questions'. The aggressive scope ('You MUST use this before any creative work') would cause constant false triggers and conflicts with other skills.

Suggestions

Narrow the scope significantly - instead of 'any creative work', specify the exact types of tasks this skill handles, e.g., 'Conducts requirements gathering sessions, generates design documents, and creates implementation plans for ambiguous or complex feature requests.'

Add distinct trigger terms that differentiate this from general development skills, e.g., 'Use when the user has an unclear or underspecified request, mentions needing a design review, requirements analysis, or says they want to plan before coding.'

Replace the imperative 'You MUST use this' with third-person descriptive language like 'Facilitates pre-implementation planning by...' to match expected description conventions.

DimensionReasoningScore

Specificity

The description uses vague language like 'creative work', 'creating features', 'building components', 'adding functionality', and 'modifying behavior' without listing concrete actions the skill performs. 'Explores user intent, requirements and design' is abstract and doesn't describe specific capabilities.

1 / 3

Completeness

The 'when' is addressed ('before any creative work - creating features, building components, adding functionality, or modifying behavior'), and the 'what' is weakly stated ('Explores user intent, requirements and design before implementation'). However, the 'what' is vague and the 'when' is overly broad, making the guidance imprecise. It does have explicit trigger guidance so it's not capped at 2 for missing 'Use when', but the quality is borderline.

2 / 3

Trigger Term Quality

Terms like 'creating features', 'building components', 'adding functionality', and 'modifying behavior' are somewhat relevant keywords a user might use, but they are extremely broad and would match nearly any development task. Missing more specific natural language triggers.

2 / 3

Distinctiveness Conflict Risk

This description is extremely generic and would conflict with virtually any development-related skill. 'Creating features, building components, adding functionality, or modifying behavior' covers nearly all software development tasks, making it impossible to distinguish from other skills.

1 / 3

Total

6

/

12

Passed

Implementation

85%

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

This is a strong process skill with excellent workflow clarity, explicit validation gates, and well-structured progressive disclosure. The actionability is high for a non-code skill, with specific file paths, exact prompt text, and clear decision criteria. The main weakness is moderate verbosity — some sections explain reasoning Claude likely already understands (e.g., benefits of modular design) and could be trimmed to save tokens.

Suggestions

Trim the 'Design for isolation and clarity' section — Claude already understands modular design principles. Reduce to 2-3 bullet points of project-specific guidance rather than general software engineering advice.

The 'Anti-Pattern' section could be condensed to a single sentence within the hard gate, e.g., 'This applies to ALL projects regardless of perceived simplicity — the design can be brief but must exist and be approved.'

DimensionReasoningScore

Conciseness

The skill is reasonably well-written but includes some verbose sections that could be tightened. The 'Anti-Pattern' section, the extended 'Design for isolation and clarity' section, and the detailed Visual Companion explanation add bulk. Some guidance (e.g., explaining why to break systems into smaller units) is knowledge Claude already has. However, most content is project-specific and earns its place.

2 / 3

Actionability

The skill provides highly concrete, specific guidance: exact file paths for specs, exact phrasing for user prompts, a numbered checklist, specific decision criteria for visual vs terminal, and clear gate conditions. While there's no code to execute (this is a process skill), the instructions are precise and copy-paste ready where applicable.

3 / 3

Workflow Clarity

The workflow is exceptionally clear with a numbered checklist, a graphviz process flow diagram, explicit validation gates (user approval after design sections, spec self-review with specific checks, user review gate before proceeding), and feedback loops (revise design if not approved, re-run spec review if changes requested). The hard gate preventing premature implementation is well-placed.

3 / 3

Progressive Disclosure

Content is well-structured with clear sections that progress logically. The visual companion details are appropriately referenced to an external file (skills/brainstorming/visual-companion.md). The skill references other skills (writing-plans, elements-of-style) without deeply nesting. Sections are clearly labeled and navigable.

3 / 3

Total

11

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
obra/superpowers
Reviewed

Table of Contents

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.