dingtalk-doc

钉钉文档（adoc）：创建、读取、编辑、块、评论、附件、导出、版本及Markdown/JSONML写入。原生 .md→dingtalk-misc；文件→dingtalk-drive；知识库→dingtalk-wiki；axls→dingtalk-misc，able→dingtalk-aitable。

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/multi/dingtalk-doc/SKILL.md

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 highly actionable, well-structured skill body with excellent workflow sequencing and validation, clear progressive-disclosure navigation to real reference files, and only minor redundancy across its multiple routing tables.

Suggestions

Consolidate the overlapping routing surfaces: the Shortcuts table, intent table, SOPs, and 多步文档短路径 repeat the same block-edit and export-type-judgment flows — fold the short-paths section into the SOPs or reference it to remove duplication.

Consider moving the 16-row Shortcuts catalog (VISIBLE_SHORTCUTS block) into a reference file and keeping only the highest-signal rows inline, reducing SKILL.md length while preserving catalog access via `dws shortcut list`.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's competence (no concept explanations), but it carries notable redundancy across four overlapping routing mechanisms — the Shortcuts table, the intent table, the SOPs, and the 多步文档短路径 section all restate the same block list→action→verify and export type-judgment flows — so it is not the lean every-token-earns-its-place level of a 3.	2 / 3
Actionability	Commands are concrete and copy-paste ready (e.g., `dws doc create --name "<标题>" --content-file <tmp.md> --format json`) and the bundled `doc_create_and_write.py` is a complete, executable script with argparse, usage examples, retry, and partial-write handling, matching the fully-executable anchor.	3 / 3
Workflow Clarity	SOP-1 through SOP-6 give explicitly numbered sequences with mandatory "验证（必须）" read-back checkpoints, a dry-run→confirm→--yes feedback loop in SOP-3, a list→action→list loop in SOP-5, and confirmation+--yes for the irreversible block delete, satisfying the explicit-validation-and-feedback-loops anchor.	3 / 3
Progressive Disclosure	SKILL.md acts as a clear overview hub with well-signaled one-level references that all resolve to real files — "命令参考：[doc.md](references/doc.md)；剧本：[04-document.md](references/04-document.md)", plus intent-guide.md, lite-recipes.md, and doc/doc-import.md — with detailed per-command content appropriately split under references/doc/.	3 / 3
	Total	11 / 12 Passed

Description

67%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 specific, well-de-conflicted description that clearly states capabilities but lacks an explicit "Use when..." trigger clause and leans on routing jargon over natural user keywords.

Suggestions

Add an explicit 'Use when...' clause stating when to invoke this skill (e.g., user wants to create/read/edit/export an online 钉钉文字文档/adoc), capping completeness and trigger quality.

Move or compress the internal cross-skill routing (dingtalk-markdown/drive/wiki/misc/aitable) into the body and keep the description focused on natural trigger terms users would actually say.

Add common natural variations (e.g., '在线文档', '云文档', '文档导出 PDF/Markdown') alongside the technical type codes (adoc, axls, able) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists many concrete capabilities — "创建、读取、编辑、块、评论、附件、导出、版本及Markdown/JSONML写入" — matching the multiple-specific-actions anchor rather than the single-domain score-2 example.	3 / 3
Completeness	The "what" is explicit and comprehensive, but there is no "Use when..." or equivalent explicit trigger guidance for this skill; the only "when" signal is the implied de-confliction routing, which per the guideline caps completeness at 2.	2 / 3
Trigger Term Quality	Leads with the natural term "钉钉文档（adoc）" and common action verbs (创建/读取/编辑/导出), but a large portion is internal routing jargon (dingtalk-markdown/drive/wiki/misc/aitable, axls, able, JSONML) rather than natural user phrasings, so it is not the full coverage of a 3.	2 / 3
Distinctiveness Conflict Risk	It carves out a clear niche (adoc online documents) and explicitly routes overlapping cases away ("原生 .md→dingtalk-markdown；文件→dingtalk-drive；知识库→dingtalk-wiki；axls→dingtalk-misc，able→dingtalk-aitable"), making it unlikely to trigger the wrong sibling skill.	3 / 3
	Total	10 / 12 Passed

Validation

75%

Warnings & errors only

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

Validation — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 1 deeper-than-1-level, 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 2 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: DingTalk-Real-AI/dingtalk-workspace-cli
Path: skills/multi/dingtalk-doc/SKILL.md
Commit: 1877870

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.