CtrlK
BlogDocsLog inGet started
Tessl Logo

dingtalk-markdown

钉钉原生 Markdown 文件。Use when 用户说 读取或下载.md原文/创建.md文件/全量覆盖远程Markdown/按文本或RE2正则局部替换Markdown。Distinct from dingtalk-doc(在线富文本文档与块编辑)、dingtalk-drive(任意类型文件的一般存储与传输)。命令前缀:dws markdown。

73

Quality

92%

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

85%Weight 40%Scale 1-3

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

A well-structured, actionable skill body: concrete commands, an explicit dry-run/confirm validation loop for destructive edits, and a clean one-level reference split. The only weakness is verbosity in the meta-notices (experimental disclaimer and command-availability caveat).

Suggestions

Trim the command-availability warning to one line — drop the service-discovery/static-endpoint/backend-tool-registration implementation details and keep only the actionable rule: verify with `dws <cmd> --help` or `--dry-run` before calling.

Shorten the experimental-preview notice; the mono-vs-multi and dispatch-verifier details can be cut to a single line or moved to a reference, since they are not needed to execute the markdown operations.

Keep the lean intent-table + hard-constraints + cross-product-routing structure as-is — it is the strongest part of the body.

DimensionReasoningScore

Conciseness

The operational core (intent table, hard constraints, cross-product routing) is lean, but the experimental-preview notice and the command-availability warning ("服务发现已下线...静态端点目录和后端工具注册...") carry implementation details that could be tightened — matching the score-2 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the score-3 'every token earns its place'.

2 / 3

Actionability

The intent table gives copy-paste-ready commands with real flags (e.g. `dws markdown patch --node <fileId> --pattern '<RE2>' --content "<新文本>" --regex --dry-run`), matching the 'fully executable code/commands; specific examples; copy-paste ready' anchor rather than the score-2 'incomplete; pseudocode'.

3 / 3

Workflow Clarity

Destructive overwrite/patch operations have an explicit dry-run → user-confirm → --yes checkpoint ("先用命令级 --dry-run 查看差异,获得用户明确确认后再加 --yes"), plus safety behavior (0-hit no-write, empty-result abort), matching the 'clear sequence with explicit validation steps; feedback loops' anchor; validation is present so the destructive-op cap at 2 does not apply.

3 / 3

Progressive Disclosure

The body is an overview (intent table + hard constraints + routing) that signals one clearly-marked one-level-deep reference, "命令参考:[markdown.md](references/markdown.md)" (verified to exist), with detailed flag tables split into that file — matching the 'clear overview with well-signaled one-level-deep references; content appropriately split' anchor.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 strong, concise description that names concrete operations, gives explicit 'Use when' triggers in natural user phrasing, and explicitly disambiguates from two sibling skills. No first/second-person voice or vague fluff.

DimensionReasoningScore

Specificity

Lists four concrete operations — "读取或下载.md原文", "创建.md文件", "全量覆盖远程Markdown", "按文本或RE2正则局部替换Markdown" — which matches the 'lists multiple specific concrete actions' anchor rather than the score-2 'some actions but not comprehensive'.

3 / 3

Completeness

Explicitly answers both what ("钉钉原生 Markdown 文件" plus the four actions) and when (the "Use when 用户说..." clause), satisfying the 'clearly answers both what AND when with explicit triggers' anchor; the explicit 'Use when' clause avoids the score-2 cap.

3 / 3

Trigger Term Quality

Triggers are framed as natural user phrasings ("用户说 读取或下载.md原文/创建.md文件...") covering the main verbs a user would say; this is good coverage rather than the score-2 'some relevant keywords but missing common variations'. The embedded "RE2正则" is slightly technical but does not undermine overall natural coverage.

3 / 3

Distinctiveness Conflict Risk

The "Distinct from dingtalk-doc(在线富文本文档与块编辑)、dingtalk-drive(任意类型文件的一般存储与传输)" clause carves out a clear niche with contrasted sibling skills, matching the 'clear niche with distinct triggers; unlikely to conflict' anchor rather than the score-2 'could still overlap'.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
DingTalk-Real-AI/dingtalk-workspace-cli
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.