CtrlK
BlogDocsLog inGet started
Tessl Logo

md-report-summary

生成高质量 Markdown 周报、工作汇报、总结、介绍等文档。无草稿时从 Web 搜索并总结;有草稿时结合草稿整理、润色、补充。当用户提到周报、工作汇报、总结、介绍、述职、复盘时使用。

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

92%

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 lean, actionable instruction set with clear branching workflows, user-confirmation checkpoints, and concrete good/bad writing examples. Its main weakness is progressive disclosure: it points to reference/templates.md, but that bundle file does not exist, leaving the reference broken.

Suggestions

Add the missing reference/templates.md file (or correct the path) so the referenced templates link resolves; a broken one-level reference currently caps progressive_disclosure at 2.

Consolidate the overlapping preservation rules between 四、有草稿流程 step 3 and 五、通用原则 (both restate 'do not modify image paths' and 'preserve tables/data verbatim') to remove redundancy.

Add an explicit output self-check step that re-验证s the result against 六、写作质量标准 before returning, turning the quality standards into a true validation checkpoint in the workflow.

DimensionReasoningScore

Conciseness

The body is lean — task-identification tables, short numbered flows, and concrete do/don't examples — and does not explain concepts Claude already knows (e.g., no 'what is a weekly report' padding), so every section earns its place; it is not the level-2 case that includes unnecessary explanation.

3 / 3

Actionability

Gives executable, specific guidance: named tool usage ('WebSearch'), explicit preservation rules ('图片引用 ![描述](路径) 路径不可修改,原样保留'), and concrete good/bad examples (the 🚫 '完成了模型测试' vs 👍 '完成 Qwen3.5-122B-A10B-AWQ …错题率降至 1/18…' pair); as an instruction-only skill the absence of code is not penalized because guidance is actionable.

3 / 3

Workflow Clarity

Clear sequence: task identification → draft/no-draft branch → numbered flows → output, with explicit user-input checkpoints ('先询问用户选择周报类型', '确认信息') and a quality checklist (六、写作质量标准); the destructive/batch validation cap does not apply to a generation task, so this stays above level 2.

3 / 3

Progressive Disclosure

The body is well-organized into clear sections and signals a one-level-deep reference to [reference/templates.md](reference/templates.md), but that referenced file is not present in the bundle (no reference/ or references/ directory exists), so the navigation to the detail material is broken — better than level 1's monolithic wall of text but not the clean, navigable structure of level 3.

2 / 3

Total

11

/

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.

The description is concise yet complete: it names several concrete capabilities, provides explicit natural trigger terms, and clearly answers both what the skill does and when to invoke it. It uses third-person voice and avoids over-claiming.

DimensionReasoningScore

Specificity

Quotes multiple concrete actions — '生成高质量 Markdown 周报、工作汇报、总结、介绍等文档', '从 Web 搜索并总结', '结合草稿整理、润色、补充' — matching the anchor that lists several specific concrete actions rather than vague language.

3 / 3

Completeness

States both what it does (generate/polish Markdown report documents, with/without draft branches) and when to use it via the explicit clause '当用户提到周报、工作汇报、总结、介绍、述职、复盘时使用', so the 'Use when' trigger is present and not merely implied.

3 / 3

Trigger Term Quality

Explicit natural terms a user would say — '周报、工作汇报、总结、介绍、述职、复盘' plus 'weekly report' — giving good coverage of common phrasings rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

It occupies a clear niche (Chinese-language Markdown report/summary/retrospective authoring) with distinct trigger terms, making it unlikely to fire for unrelated skills; it is cohesive rather than generically broad.

3 / 3

Total

12

/

12

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: 4 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.