CtrlK
BlogDocsLog inGet started
Tessl Logo

brainstorming

Explore user intent, requirements, and design options through collaborative dialogue before implementation. Use before building new features, components, or systems — whenever the user describes something to build and design decisions are involved. Triggers: "brainstorm", "help me design", "think through the requirements", "头脑风暴", "设计方案", "梳理需求". Not for bug fixes, config changes, or tasks with an obvious implementation path.

71

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 well-sequenced, highly actionable design workflow with strong validation feedback loops. Its main weaknesses are moderate over-explanation of concepts Claude already knows and two referenced detail files that are missing from the bundle.

Suggestions

Add the missing visual-companion.md and spec-document-reviewer-prompt.md files to the bundle (or remove the references and inline the essential parts), so the signaled progressive-disclosure paths actually resolve.

Trim explanatory rationale Claude already knows — e.g., the modularity philosophy in '为隔离和清晰而设计' and the justification in the '反模式' section — keeping only the directive guidance.

Link the scripts/ bundle explicitly (e.g., name start-server.sh / server.cjs) when describing the --open launch, so the implementation backing the visual companion is discoverable.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete checklists and prompts, but includes unnecessary rationale Claude already knows (modularity philosophy in "为隔离和清晰而设计", the anti-pattern justification for why simple projects need design). Not a 4 because several paragraphs are trimmable explanation rather than instruction.

3 / 5

Actionability

Highly actionable: a 9-step ordered checklist, a flowchart, verbatim copy-paste prompts (the visual-companion offer, the spec review gate message), concrete file path docs/specs/YYYY-MM-DD-<主题>-design.md, and the --open flag. Specific examples cover the common cases.

5 / 5

Workflow Clarity

Clear sequence with explicit validation checkpoints and feedback loops: "用户认可设计?—[否,修改]→" and "用户审阅规格?...需要修改 → 返回", plus the spec self-review fix-in-place loop. This is a design (non-destructive) skill so the batch/destructive cap does not apply.

5 / 5

Progressive Disclosure

Well-organized into clear sections and it signals one-level-deep references (visual-companion.md, spec-document-reviewer-prompt.md "在本 skill 目录中"), but neither referenced file exists in the bundle — only scripts/ server files are present — so the navigation leads to dead ends. Not a 4 because broken references are more than a minor gap.

3 / 5

Total

16

/

20

Passed

Description

95%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 is exemplary: it states concrete capabilities, provides rich bilingual trigger terms, and clearly scopes both when to use and when not to use the skill. Minimal conflict risk thanks to explicit exclusions.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Explore user intent, requirements, and design options through collaborative dialogue") and target artifacts (features, components, systems), with only minor abstraction gaps. Not a 5 because the actions lean conceptual rather than maximally concrete.

4 / 5

Completeness

Explicitly answers both what (explore intent/requirements/design options via dialogue) and when ("Use before building new features, components, or systems"), plus concrete trigger phrases and a negative scope clause. Clearly matches the top anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including synonyms and bilingual variants: "brainstorm", "help me design", "think through the requirements", "头脑风暴", "设计方案", "梳理需求". These are phrases users would actually say.

5 / 5

Distinctiveness Conflict Risk

Clear niche (pre-implementation design/brainstorming) with distinct triggers and an explicit exclusion ("Not for bug fixes, config changes, or tasks with an obvious implementation path") minimizing conflict with implementation skills.

5 / 5

Total

19

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
feiskyer/claude-code-settings
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.