Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
66
58%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/sdd/skills/brainstorm/SKILL.mdQuality
Discovery
67%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 does well at establishing both 'what' and 'when' with explicit trigger guidance and even a negative trigger, earning strong completeness marks. However, the capabilities described are somewhat abstract (collaborative questioning, alternative exploration) rather than concrete deliverables, and the trigger terms could better match natural user language. The broad scope of 'before writing code' creates potential overlap with other planning or architecture skills.
Suggestions
Add more natural trigger terms users would say, such as 'brainstorm,' 'design,' 'architecture,' 'plan a feature,' 'think through an approach,' or 'explore options'
Replace abstract process descriptions with concrete outputs, e.g., 'produces design documents, evaluates trade-offs between approaches, identifies edge cases and requirements gaps'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names some actions like 'refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation,' but these are somewhat abstract process descriptions rather than concrete, specific actions like 'generates architecture diagrams' or 'produces requirement documents.' | 2 / 3 |
Completeness | The description explicitly addresses both 'what' (refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation) and 'when' (when creating or developing, before writing code or implementation plans), and even includes a 'don't use' clause for additional clarity. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'creating,' 'developing,' 'writing code,' 'implementation plans,' and 'rough ideas,' but misses many natural user phrases like 'brainstorm,' 'design review,' 'architecture,' 'plan a feature,' 'think through,' or 'help me figure out.' The negative trigger ('mechanical processes') is vague. | 2 / 3 |
Distinctiveness Conflict Risk | The scope of 'creating or developing, before writing code' is quite broad and could overlap with general coding assistance, planning, or architecture skills. The negative trigger helps somewhat, but 'mechanical processes' is too vague to clearly delineate boundaries. The design-thinking niche is somewhat distinct but not sharply defined. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a reasonably well-structured brainstorming/design skill with a clear conversational workflow, but it suffers from some redundancy between the process description and key principles, and lacks concrete artifacts like a design document template or example output. The probability-based approach generation is a distinctive feature but could benefit from an example to clarify expectations.
Suggestions
Add a concrete example of a design document output or provide a template file at `.specs/plans/example.design.md` to make the expected deliverable actionable and unambiguous.
Remove or consolidate the Key Principles section since most points duplicate guidance already given in The Process section, improving conciseness.
Add explicit validation/recovery steps: what happens if the user rejects the overall direction after design sections are presented? Include a feedback loop for major pivots vs. minor adjustments.
Provide a brief example of the '6 approaches with probabilities' output format so Claude knows exactly what the expected structure looks like.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some redundancy (e.g., 'Be flexible - Go back and clarify when something doesn't make sense' repeats earlier guidance, and the Key Principles section largely restates what was already covered in The Process section). The probability sampling instruction is oddly specific but adds unique value. | 2 / 3 |
Actionability | Provides a clear process with specific steps like writing to `.specs/plans/<topic>.design.md` and using `/worktrees create`, but much of the guidance is procedural/conversational rather than executable. The '6 approaches with probabilities' instruction is concrete but unusual. No example output or template for the design document is provided. | 2 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced (understand → explore → present → document → implement), but there are no explicit validation checkpoints beyond 'ask after each section whether it looks right.' There's no guidance on what to do if the user rejects the design entirely, and the transition from design to implementation lacks verification steps. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and reasonable length, but references to external resources like 'write-concisely skill' and commands like `/worktrees create` and `/add-task` are mentioned without any links or further context. No bundle files support the skill, and no design template is referenced despite being a natural candidate for a separate file. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
dedca19
Table of Contents
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.