CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

youtube-live

在 YouTube 直播间发送文字聊天;直播资料、历史和持续观察使用 youtube-hunter live。

Quality

79%

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

Fix and improve this skill with Tessl

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

Quality

Content

86%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 lean, operational skill writing: executable commands, a default-preview/confirm safety gate, explicit error-handling policy, and clear scope exclusions with no wasted tokens. The only weaknesses are minor — the youtube-hunter prerequisite lacks a concrete command, and error recovery is stated as policy rather than explicit retry/fix steps. Structure and token efficiency are fully appropriate for a simple single-purpose skill.

DimensionReasoningScore

Conciseness

The ~6-line body contains zero padding and no explanations of concepts Claude already knows: every sentence delivers prerequisites ("先用 youtube-hunter 登录并读取真实直播视频 ID;账号需要有频道"), auth/preview policy, executable commands, error policy, and scope exclusions. Every token earns its place, matching the 'lean and efficient' anchor.

5 / 5

Actionability

Two concrete, executable command templates (preview and --confirm variants) with placeholders cover the common cases, plus concrete prerequisites. The minor gap keeping it from level 5 is that the prerequisite step — logging in via youtube-hunter and reading the live video ID — is stated directionally without any accompanying command.

4 / 5

Workflow Clarity

The sequence is clear and well-gated: log in and fetch the real video ID → confirm target/text/authorization → default preview → add --confirm only when authorized, with a safety rule against blind resends on timeout ("超时不直接重发"). It falls short of level 5 because error recovery ("慢速模式、会员限制或平台拒绝按实际错误处理") is a general policy rather than explicit feedback-loop steps.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no external references needed (no references/, scripts/, or assets/ bundle files exist), and the content is tightly organized: prerequisites, commands, error handling, and scope limits in distinct short paragraphs. Per the rubric's simple-skill guideline, this earns a 5.

5 / 5

Total

18

/

20

Passed

Description

61%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 states a clear, concrete single action and explicitly boundaries itself against the sibling youtube-hunter skill, which is good for distinctiveness. However, it lacks an explicit 'Use when' trigger clause, capping completeness, and lists only one action with limited synonym coverage. Adding explicit trigger guidance and natural variations would move it toward the top anchors.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to send a chat message or comment in a YouTube live stream" (Use when the user asks to send a message or comment in a YouTube live stream), to raise completeness above the cap of 3.

Enumerate the concrete actions covered — e.g. preview/dry-run send vs. confirmed send, sending to a video ID or link — so specificity reflects the skill's actual capability set rather than a single verb.

Include common natural synonyms users might say, such as "直播聊天" (live chat), "发弹幕/留言" (send a comment), or "live chat", to broaden trigger term coverage toward level 5.

DimensionReasoningScore

Specificity

"在 YouTube 直播间发送文字聊天" names the domain (YouTube live) plus one concrete action (send text chat), matching the '1-2 concrete actions, not comprehensive' anchor. It lists only a single action rather than the several specific actions of the level-4 anchor, though the routing clause ("直播资料、历史和持续观察使用 youtube-hunter live") adds some scope precision.

3 / 5

Completeness

The 'what' is clear (send text chat in a YouTube live room), but there is no explicit 'Use when...' trigger clause; the 'when' is only weakly implied by contrast with the youtube-hunter routing sentence. Per the judging guideline, a missing 'Use when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms users would say are present — "YouTube 直播间", "文字聊天", "直播", "历史" — giving good keyword coverage, but common variations/synonyms like "弹幕", "留言", or "live chat" are missing, so it does not reach the comprehensive synonym coverage of level 5.

4 / 5

Distinctiveness Conflict Risk

The routing sentence ("直播资料、历史和持续观察使用 youtube-hunter live") carves out a clear niche and explicitly disambiguates from the closely related youtube-hunter skill, leaving only minor overlap risk for generic YouTube-live requests. It falls short of level 5 because the description lacks distinct explicit trigger phrases that would minimize conflict risk further.

4 / 5

Total

14

/

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/youtube-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.