CtrlK
BlogDocsLog inGet started
Tessl Logo

dingtalk-todo

钉钉待办 / TODO。Use when 用户说 创建待办/TODO/任务提醒/指派任务/标记完成/查待办/紧急待办/循环待办/批量建待办/逾期待办。不做日报周报(走 dingtalk-misc)、审批(走 dingtalk-misc)、日程(走 dingtalk-calendar)。命令前缀:dws todo。

68

Quality

83%

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

88%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.

An excellent operational skill body: fully executable commands, explicit routing priority with a golden-routes table, and strong validation/recovery discipline for writes and batch operations. The only notable flaws are a slightly repetitive schema-lookup paragraph and one orphaned reference file (references/recipes/conventions.md) that no document links to.

DimensionReasoningScore

Conciseness

The body is dense and operational with no explanation of concepts Claude already knows — every line is a routing rule, command, or constraint. Minor trimming is possible (the schema-lookup paragraph under Shortcuts reiterates Help-avoidance rules already stated in 执行契约), which fits anchor 4 rather than the fully lean anchor 5.

4 / 5

Actionability

Every route is a copy-paste-ready command with concrete flags and placeholders (e.g. `dws todo +assign --to "张三" --task "<标题>" --format json`, `--priority 10|20|30|40`, `python scripts/todo_batch_create.py <todos.json> --dry-run`), with a full atomic-command skeleton table. This matches anchor 5 fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

Multi-step processes are explicitly sequenced (执行_contract read-first rule, numbered 路由优先级 1–5, Golden Routes intent table) with explicit validation checkpoints: mandatory post-write read-back verification ("写后必须核验"), reconciliation instead of blind replay for non-idempotent writes, and a dry-run planDigest confirmation gate for batch creation. Feedback loops for error recovery (unknown flag → Help once; unknown command → no Help, report drift) are present, matching anchor 5.

5 / 5

Progressive Disclosure

The SKILL.md is a clear overview with well-labeled, one-level-deep references (intent disambiguation, lite recipes, composite lifecycle, full command reference — all verified to exist) plus bundled scripts. However, `references/recipes/conventions.md` is an orphan: it is referenced nowhere in SKILL.md or the other reference files, so that content is not navigable from the skill entry point — a minor organization gap that fits anchor 4 rather than 5.

4 / 5

Total

18

/

20

Passed

Description

78%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 highly distinctive, trigger-rich description with explicit scope exclusions and a clear command prefix. Its main weakness is that the what-side is a bare domain name — the concrete capabilities only surface indirectly through the when-clause, and a few natural trigger terms (update, delete) are absent.

Suggestions

Add a brief capability list to the what-clause (e.g. create/assign/update/complete/query/comment on DingTalk todos) so the description states actions directly rather than only via triggers.

Include natural trigger phrases for the remaining common intents, such as 修改待办/更新待办 and 删除待办, to round out trigger coverage.

DimensionReasoningScore

Specificity

The what-clause is just "钉钉待办 / TODO", but concrete actions are enumerated through the trigger list (创建待办、指派任务、标记完成、查待办、批量建待办、逾期待办). It lists several specific actions with minor gaps (update, delete, comment, and attachment operations are never mentioned), which matches anchor 4 rather than 5.

4 / 5

Completeness

Both what and when are present: the when is explicit with concrete trigger phrases plus explicit exclusions ("不做日报周报(走 dingtalk-misc)…日程(走 dingtalk-calendar)"), but the what is a terse domain name plus command prefix ("钉钉待办 / TODO … 命令前缀:dws todo") without stating capabilities. This matches anchor 4 (both present, what could be more explicit) rather than anchor 5.

4 / 5

Trigger Term Quality

The "Use when 用户说" clause gives natural spoken phrases with synonyms (待办/TODO/任务提醒) across create, assign, complete, query, urgent, recurring, batch, and overdue intents. A few natural terms are missing (e.g. 修改待办/更新待办, 删除待办), so it fits anchor 4 rather than the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

It carves a clear DingTalk-todo niche with distinct triggers and explicitly deflects adjacent domains to sibling skills (dingtalk-misc for reports/approvals, dingtalk-calendar for schedule), plus a command prefix. Conflict risk is minimal, matching anchor 5.

5 / 5

Total

17

/

20

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.

Validation — 13 / 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

relative_links

Relative link issues: 1 suspicious

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.