CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

douyin-live

抖音公开直播间互动:已授权的弹幕与点赞。房间读取和事件监听使用 douyin-hunter live。

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./crews/main/skills/expert-bd/tools/douyin-live/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

The body is an exemplar of token-efficient, safety-conscious instruction: concrete commands, hard limits, and explicit stop/no-resend conditions with zero fluff. Its weaknesses are structural — no section organization, and a dangling reference to a 'Live Interaction workflow' that doesn't exist in the bundle, which also weakens the actionability of the main procedure.

Suggestions

Resolve the dangling reference: either add the 'Live Interaction workflow' as a real bundled file with a clearly signaled path, or inline the essential steps so the procedure is self-contained.

Add a short example of obtaining room_id (e.g., the `douyin-hunter live room` invocation and which field of its response to use) so the chat/like commands are fully executable end-to-end.

Add minimal section headers (e.g., 命令 / 限制与确认 / 边界与停止条件) to organize the content and satisfy the well-organized-sections bar for short skills.

DimensionReasoningScore

Conciseness

The ~15-line body is lean and information-dense — executable commands, hard limits ("弹幕 ≤200 字,单次点赞 1–20 次"), and stop conditions with no padding and no explanation of concepts Claude already knows. Every token earns its place.

5 / 5

Actionability

Provides copy-paste-ready commands with flags (`douyin-live chat --room-id ... --text`, `douyin-live like --room-id ... --count 1`) plus concrete constraints. Not 5 because "按本包 Live Interaction workflow 执行" references a workflow that has no corresponding file in the bundle, and obtaining room_id via `douyin-hunter live room` is named but never shown.

4 / 5

Workflow Clarity

A usable sequence is present (reuse douyin-login session → get room_id from `douyin-hunter live room` → preview → add --confirm) with explicit checkpoints ("风控立即停止", "结果未知先核实,不能自动重发"). Not 5 because the steps are unnumbered/implicit and the referenced 'Live Interaction workflow' does not exist as a bundled file, leaving a gap in the main procedure.

4 / 5

Progressive Disclosure

The skill is under 50 lines and single-purpose (eligible for 5), but there are no section headers and the sole internal reference — "本包 Live Interaction workflow" — is neither signaled with a path nor backed by an actual file (references/, scripts/, assets/ are absent). Some structure exists via the code block and boundary paragraph, but organization and reference signaling need improvement.

3 / 5

Total

16

/

20

Passed

Description

66%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.

The description is concise, concrete, and third-person, clearly stating what the skill does and where its boundary sits relative to sibling tools. Its main weakness is the complete absence of 'when to use' trigger guidance, which caps completeness. Adding a 'Use when...' clause with natural trigger phrases would lift it substantially.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user asks to send 弹幕, like, or interact in a Douyin 直播间') to satisfy the completeness requirement.

Include common synonyms/variations of the trigger terms (直播, 直播互动, 发弹幕) to broaden natural keyword coverage.

Optionally state the preview/confirm default and message/like limits in the description to make capability coverage comprehensive.

DimensionReasoningScore

Specificity

Lists several concrete actions — "已授权的弹幕与点赞" (authorized danmaku and likes) plus "房间读取和事件监听" (room reading and event listening) — with minor gaps in coverage. Not 5 because it is extremely terse and omits scope details (e.g., preview/confirm behavior, limits) that would make coverage comprehensive.

4 / 5

Completeness

Has a clear 'what' (authorized danmaku and likes in public Douyin live rooms) but no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3. It is above 2 because the 'what' is concrete and unambiguous rather than vague.

3 / 5

Trigger Term Quality

Contains natural terms a user would say — "抖音", "直播间", "弹幕", "点赞", "互动" — giving good keyword coverage. Not 5 because common variations/synonyms (e.g., "直播", "评论", "发弹幕") are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche (Douyin live-room interaction) that explicitly delineates from the sibling skill ("房间读取和事件监听使用 douyin-hunter live"), keeping triggers distinct. Not 5 because closely related skills (douyin-hunter live, douyin-login) occupy the same Douyin-live trigger space, leaving minor overlap risk.

4 / 5

Total

15

/

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

TeamWiseFlow/xiaobei

Path

crews/main/skills/expert-bd/tools/douyin-live/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.