CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dingtalk-aicard

Create, edit, and validate DingTalk AI Card (A2UI) JSON files offline. Use for cards built from requirements or images, structural protocol errors, and named component or function contract lookup through native DWS commands. Send a card to the current user only when a preview is requested.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 exemplary SKILL.md body: dense, unambiguous, and honest about validation scope and delivery boundaries. Structure is a routing layer over a well-organized one-level-deep reference bundle, with executable commands and a complete construction example. No notable weaknesses found.

DimensionReasoningScore

Conciseness

The body is lean, imperative, and assumes Claude's competence throughout — no padding, no explanation of what JSON, DingTalk, or card protocols are. The version strings ("v1.0", "1.0", V0.8) are functional protocol constants the agent must write into files, not time-sensitive drift, so they cost nothing.

5 / 5

Actionability

Concrete copy-paste commands cover the common cases: `dws aicard explain Tabs --format json`, `dws aicard lint --file card.a2ui.json --format json`, full `update-a2ui-card --biz-id <bizId> --content <message-strings> --flow-status <state>` invocations, and a complete executable three-message JSON array for card construction. The send command's flags and JSON-encoding requirement are fully specified.

5 / 5

Workflow Clarity

The route-by-intent table sequences entry points, the scenario table maps each case (new card, host-created surface, existing-card update) to its required messages and preflight mode, and validation checkpoints are explicit ("Check exit status and `data.valid` plus `data.preflight.valid`"). Error-recovery feedback loops are present: "An uncertain result must be checked before another create; do not resend automatically" and "inspect `updateWarning` and the receipt; do not recreate automatically", plus readback verification after sending.

5 / 5

Progressive Disclosure

The body is a pure routing overview with two navigation tables pointing to a well-split bundle; every referenced path was verified to exist (design.md with #root-surface and #headers-and-card-insets anchors, patterns/progress.md#examples-and-replay, all six pattern files, three index files, protocol/examples/README.md). References are one level deep, and the single indirection (the example index) is explicitly framed as a chooser with "Read a named example directly" guidance.

5 / 5

Total

20

/

20

Passed

Description

87%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 strong description: third-person, concise, with an explicit Use-for clause carrying three concrete triggers and a well-scoped capability list including a boundary on sending. Its only shortcoming is minor coverage/keyword gaps (no mention of updating delivered cards; no file-extension or synonym triggers).

DimensionReasoningScore

Specificity

"Create, edit, and validate DingTalk AI Card (A2UI) JSON files offline", "named component or function contract lookup through native DWS commands", and "Send a card to the current user only when a preview is requested" list several specific concrete actions. Not 5 because the delivered-card update flow (update-a2ui-card, a major body capability) is not mentioned; not 3 because coverage far exceeds 1–2 actions.

4 / 5

Completeness

The what is explicit (create, edit, validate, contract lookup, conditional send) and the when is an explicit "Use for..." clause with three concrete trigger phrases: "cards built from requirements or images, structural protocol errors, and named component or function contract lookup". Both are answered clearly and concretely.

5 / 5

Trigger Term Quality

Good natural keyword coverage: "DingTalk AI Card (A2UI)", "structural protocol errors", "component or function", "preview", "DWS commands". Not 5 because synonyms and file extensions are missing (no ".a2ui.json", no "lint"/"validate a card message" phrasing a user might naturally say); not 3 because the terms go well beyond a couple of generic keywords and include the domain name, format, and error-trigger phrase.

4 / 5

Distinctiveness Conflict Risk

"DingTalk AI Card (A2UI)" names a clear niche with distinct triggers (DingTalk, A2UI, DWS, card protocol errors) that no generic skill would claim; conflict risk with other skills is minimal.

5 / 5

Total

18

/

20

Passed

Validation

75%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 11 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 11 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository

DingTalk-Real-AI/dingtalk-workspace-cli

Path

skills/multi/dingtalk-aicard/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.