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.

72

Quality

88%

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%

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

A clearly sequenced, actionable instruction skill with strong workflow checkpoints, but it carries some redundancy across the checklist/flowchart/详解 sections and references companion markdown files that do not exist in the bundle.

Suggestions

Add the referenced files visual-companion.md and spec-document-reviewer-prompt.md to the skill bundle, or remove the references and inline the essential parts.

Consolidate the 检查清单, 流程图, and 流程详解 sections to remove overlap and reduce token usage without losing the sequenced workflow.

Convert the companion file references to proper markdown links (e.g., [visual-companion.md](visual-companion.md)) so navigation is unambiguous.

DimensionReasoningScore

Conciseness

Mostly lean without concept-padding, but the checklist, flowchart, and 流程详解 sections restate the same sequence, and the 可视化伴侣 section is lengthy enough that the body could be tightened.

2 / 3

Actionability

Provides concrete, executable guidance for an instruction-only skill: numbered ordered checklist, specific output path docs/specs/YYYY-MM-DD-<主题>-design.md, one-question-per-message rule, a 4-point spec self-review, and quoted user-facing prompts.

3 / 3

Workflow Clarity

Clear sequenced process with a flowchart and explicit validation checkpoints (规格自审 -> fix in place -> user review gate -> revise loop), matching the clear-sequence-with-feedback-loops anchor.

3 / 3

Progressive Disclosure

References to spec-document-reviewer-prompt.md and visual-companion.md are signalled ("在本 skill 目录中") but those referenced markdown files are absent from the skill directory, so the disclosure structure is partly broken.

2 / 3

Total

10

/

12

Passed

Description

100%

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 well-crafted description that clearly states capability, when to use it, and when not to, with natural trigger terms in both English and Chinese. It is concise, third-person, and distinct from other skills.

DimensionReasoningScore

Specificity

Lists concrete actions ("Explore user intent, requirements, and design options", "collaborative dialogue before implementation") rather than vague language, matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers what (explore intent/requirements/design options via collaborative dialogue) and when ("Use before building new features..." with an explicit Triggers list and a "Not for..." clause).

3 / 3

Trigger Term Quality

Natural user phrases like "brainstorm", "help me design", "think through the requirements" plus Chinese variants give good coverage of terms users would actually say.

3 / 3

Distinctiveness Conflict Risk

Clear pre-implementation design niche with distinct triggers and explicit negative guidance ("Not for bug fixes, config changes, or tasks with an obvious implementation path") that prevents mis-triggering.

3 / 3

Total

12

/

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.

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.