CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dingtalk-cli

Use when the user wants to log in to DingTalk or check authentication and permissions; read, query, search, send, reply to, forward, or recall messages and chat history; manage group chats or send DING alerts; find coworkers or query contacts, departments, and reporting relationships; read, search, create, or edit docs, drive files, spreadsheets, AI tables, wiki, mail, calendars, meeting rooms, AI meeting minutes, todos, reports, whiteboards, or AI cards; query attendance or live sessions, handle OA approvals, manage goals, contracts, digital employees, or applications; subscribe to real-time events; or look up developer documentation and use DingTalk OpenAPI.

Quality

97%

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

93%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 lean, highly actionable router skill: an intent-to-skill table, concrete auth commands with a sequenced device-flow login procedure, and command-discovery guidance, all composed of non-obvious runtime-specific rules. The only gap is the absence of an explicit error-recovery loop for failed or expired logins, which keeps workflow clarity just below top marks.

DimensionReasoningScore

Conciseness

Every sentence carries non-obvious domain knowledge ("--no-browser alone only suppresses browser launch; it does not replace --device", "A zero process exit code alone does not prove the requested business operation completed") with no concept explanations or padding. Matches the lean/every-token-earns-its-place anchor rather than the 4 anchor, which requires some trimmable over-explanation.

5 / 5

Actionability

Provides copy-paste-ready commands for the skill's core jobs — routing (read_skills calls plus a full intent-to-skill table), auth ("dws auth login --device --no-browser"), and discovery ("dws schema --cli-path ... --compact --format json"). Matches the fully-executable anchor; not 4 because the common cases are all covered with concrete commands.

5 / 5

Workflow Clarity

The login flow is clearly sequenced with an explicit validation step ("Verify the result with: dws auth status --format json") and background-task continuation via shell_exec/shell_await, and the missing-skill case has a recovery path. Not 5 because error recovery for a denied or expired login is delegated to "the selected skill's confirmation and retry rules" rather than given as an explicit feedback loop here; not 3 because checkpoints are present and explicit.

4 / 5

Progressive Disclosure

The body is itself a well-signaled one-level-deep index: a routing table mapping each user intent to a single skill, with per-product detail correctly split out into the sibling skills and referenced via read_skills. Easy navigation with nothing inlined that belongs elsewhere, matching the 5 anchor.

5 / 5

Total

19

/

20

Passed

Description

100%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.

An exemplary trigger-focused description: a single explicit "Use when..." enumeration that comprehensively and concretely covers authentication, messaging, contacts, docs, drive, calendar, mail, todos, approvals, events, and OpenAPI usage. It answers what and when simultaneously with natural user vocabulary and near-zero conflict risk.

DimensionReasoningScore

Specificity

Enumerates many concrete actions ("read, query, search, send, reply to, forward, or recall messages", "send DING alerts", "query attendance or live sessions", "subscribe to real-time events") with comprehensive coverage across the entire product surface. It exceeds the 4 anchor because there are no meaningful gaps in capability coverage, only exhaustive enumeration.

5 / 5

Completeness

Opens with an explicit "Use when the user wants to log in to DingTalk..." clause whose enumerated verbs simultaneously state what the skill does, answering both what and when with concrete trigger phrases. Not 4, because the when-clause is maximally explicit rather than something that "could be more specific".

5 / 5

Trigger Term Quality

Covers the natural vocabulary a user would say for nearly every DingTalk product: "messages and chat history", "group chats", "coworkers", "contacts", "spreadsheets", "mail", "todos", "approvals", "DingTalk OpenAPI". This matches the comprehensive-with-synonyms anchor rather than the 4 anchor's "a few natural terms missing".

5 / 5

Distinctiveness Conflict Risk

Names a clear niche (DingTalk) with product-specific triggers like "DING alerts", "AI tables", and "DingTalk OpenAPI" that no other skill domain would claim. Minimal conflict risk, matching the clear-niche anchor rather than the 4 anchor's "minor overlap risk".

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

dtyq/magic

Path

backend/super-magic/agents/skills/dingtalk-cli/SKILL.md

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.