CtrlK
BlogDocsLog inGet started
Tessl Logo

dev-workflow

开发流程五步法。支持需求理解、方案设计、代码实现、代码审查、Bug 修复。当用户提到「需求分析」「方案设计」「代码实现」「代码审查」「理解需求」「技术设计」「开始写代码」「Review」「检查代码」「bug」「报错」「崩溃」「异常」「出错了」时使用。

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 well-structured and highly actionable for orchestration and document landing, but two issues hold it back: the automatic disk-writing workflow lacks validation checkpoints, and the five referenced reference files are missing from the bundle.

Suggestions

Add a validation checkpoint after auto-落盘 (e.g., confirm the file was created/appended and the time-header separator was written correctly), with a fix-and-retry loop for write failures.

Ship the referenced per-stage files (reference/requirement.md, design.md, implementation.md, review.md, bug-fix.md) or inline the per-stage procedures so the skill is self-contained.

Remove or condense the '使用时机' keyword list since the same triggers already appear in the frontmatter description.

DimensionReasoningScore

Conciseness

Mostly lean with concrete paths and formats that earn their place, but the '使用时机' keyword list duplicates the frontmatter triggers and could be trimmed.

4 / 5

Actionability

Concrete, copy-paste-ready guidance throughout — exact file paths (docs/需求理解.md), title format (## YYYY-MM-DD HH:mm), separator (---), and append-not-overwrite rules with clear fallback logic.

5 / 5

Workflow Clarity

The five-stage sequence and handoffs are clearly laid out, but the core auto-落盘 write behavior has no validation or error-recovery checkpoint, which caps workflow clarity at 3 per the destructive/batch rule.

3 / 5

Progressive Disclosure

Structure and one-level-deep references are clearly signaled, but the five referenced reference/*.md files do not exist in the bundle, breaking navigation and leaving the per-stage procedures missing.

3 / 5

Total

15

/

20

Passed

Description

91%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 strong: it clearly states what the skill does, enumerates the five workflow stages, and provides an extensive set of natural-language triggers including synonyms. Its only weakness is breadth-induced overlap risk with single-purpose review or bug-fix skills.

DimensionReasoningScore

Specificity

Names the domain ('开发流程五步法') and lists five concrete stages (需求理解、方案设计、代码实现、代码审查、Bug 修复), giving several specific capabilities with only minor gaps in per-stage detail.

4 / 5

Completeness

Explicitly answers both what (开发流程五步法 + the five stages) and when ('当用户提到…时使用' with concrete trigger phrases).

5 / 5

Trigger Term Quality

Comprehensive coverage of natural terms including synonyms and colloquial variations ('需求分析', '理解需求', '开始写代码', '报错', '出错了', 'Review'), matching what users would naturally say.

5 / 5

Distinctiveness Conflict Risk

Triggers are specific to dev-process phases, but the broad five-stage scope invites overlap with dedicated review and bug-fix skills, so it is mostly distinct with minor overlap risk.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 5 missing

Warning

Total

15

/

16

Passed

Repository
xstongxue/best-skills
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.