youdaonote

有道云笔记官方 skill，支持笔记 CRUD（创建/读取/更新/删除）、待办管理、网页剪藏、笔记搜索、文件夹管理等基础操作。如需构建知识库或 Wiki，请使用 youdaonote-llm-wiki skill 而非本 skill。

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./SKILLs/youdaonote/SKILL.md

Quality

Content

76%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.

A highly actionable, well-structured CLI reference with strong pre-flight validation and error-recovery guidance for setup. Its weaknesses are the missing validation step before destructive delete operations (capping workflow clarity) and some repetition of the create-vs-save warning.

Suggestions

Add a validation step before destructive commands, e.g., 'delete 前先运行 read <fileId> 确认目标并征得用户确认', to lift the workflow-clarity cap.

Consolidate the thrice-repeated 'create is plain-text only, use save' warning into one authoritative location (注意事项) to tighten conciseness.

Consider moving the full command cheat-sheet table and install guide details into a references/ file, keeping SKILL.md as a leaner overview.

Dimension	Reasoning	Score
Conciseness	The body is efficient: a terse command cheat-sheet table, bullet-form remediation, and no explanations of concepts Claude already knows. It is not a 5 because the 'create only supports plain text, use save' warning is repeated three times (command table, 笔记管理 intro, and 注意事项) and could be consolidated.	4 / 5
Actionability	Every command is copy-paste ready with concrete flags and JSON payloads (e.g., the contentFile save pattern and the exact curl install command), and error handling is matched to specific observed error strings ('command not found', "error: unknown option '-s'"). Coverage of common cases is complete, matching the fully-executable anchor.	5 / 5
Workflow Clarity	The setup/repair workflow has strong checkpoints (pre-flight `list` probe, version check, upgrade paths, `check --json` diagnostics), but the destructive operations (`delete`, `todo delete`, `todo group-delete`) are documented with no validation or verification step such as read-before-delete or user confirmation. Per the rubric's destructive-operation cap, workflow clarity cannot exceed 3 despite the otherwise strong sequencing.	3 / 5
Progressive Disclosure	No bundle files exist, and the ~155-line body is well organized into clearly labeled sections (前置条件, 命令速查, 笔记管理, 网页剪藏, CLI 未安装处理, 故障排查, 注意事项) with the full capability discoverable via `help --json`. It is not a 5 because the body exceeds 50 lines and content such as the 25-row command table and full install/upgrade guide could arguably be split into a reference file.	4 / 5
	Total	16 / 20 Passed

Description

75%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.

A specific, well-scoped description that enumerates concrete capabilities and cleanly delineates itself from a sibling skill. Its main weakness is the absence of an explicit 'use when' trigger clause, which both caps completeness and slightly weakens trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g., '当用户提到有道云笔记、云笔记、保存笔记、待办或剪藏网页时使用本 skill', to raise completeness and trigger-term quality.

Include a few more natural synonyms users might say ('云笔记', '待办清单', '收藏笔记') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — '笔记 CRUD（创建/读取/更新/删除）、待办管理、网页剪藏、笔记搜索、文件夹管理' — with the CRUD term expanded into its component operations, comprehensively covering the CLI's surface. It is not a 4 because coverage has no significant gaps and every capability named is concrete rather than generic.	5 / 5
Completeness	The 'what' is clearly stated (note CRUD, todo management, web clipping, search, folder management), but there is no 'when to use this skill' clause — only a negative boundary ('如需构建知识库或 Wiki，请使用 youdaonote-llm-wiki skill 而非本 skill'). Per the rubric, a missing explicit trigger clause caps completeness at 3; it is not a 2 because the 'what' is specific and complete.	3 / 5
Trigger Term Quality	It contains natural terms users would say ('笔记', '待办', '网页剪藏', '搜索', '文件夹', '有道云笔记'), giving good keyword coverage. It misses a few natural phrasings/synonyms (e.g., '云笔记', '收藏', '待办清单') and has no explicit trigger-oriented wording, so it falls between the 'good coverage' and 'comprehensive coverage' anchors.	4 / 5
Distinctiveness Conflict Risk	It names a specific product ('有道云笔记官方 skill') and explicitly disambiguates against the closely related 'youdaonote-llm-wiki' skill, establishing a clear niche with distinct triggers and minimal conflict risk. The explicit cross-skill boundary is stronger than the anchor-4 'minor overlap risk' example.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: netease-youdao/LobsterAI
Path: SKILLs/youdaonote/SKILL.md
Commit: 791a352

Reviewed: 2 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.