analyze-skill

Analyze usage data for a specific skill and suggest improvements to its triggers and prompt. Identify usage patterns, missed triggers, and areas for SKILL.md improvement.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "analyze-skill" with this command: npx skills add shinyaigeek/cc-skills-usage/shinyaigeek-cc-skills-usage-analyze-skill

analyze-skill

Analyze the usage of a specified skill and output improvement suggestions for its SKILL.md triggers and prompt.

Arguments

  • skill-name (required): The name of the skill to analyze (e.g., example-skill, review-pr)

If no argument is provided, ask the user for the skill name.

Execution Steps

Step 1: Retrieve Usage Data

Execute the following command using the Bash tool and capture the output:

bunx cc-skills-usage@0.1.1 --conversations --skill <skill-name>

The output includes the following data:

  • Skill Stats: Number of invocations
  • Daily Stats: Daily usage counts
  • Project Stats: Per-project usage counts
  • Token Stats: Token consumption
  • Recent Calls: Recent invocations (with triggerMessage)
  • Conversation Stats: Skill usage rate across all sessions
  • Recent Conversations: User messages from sessions where the skill was not used

Step 2: Read Skill Definition

Use the Read tool to read ~/.claude/skills/<skill-name>/SKILL.md. If the file is not found, use Glob to search under ~/.claude/skills/ to locate the skill directory.

Step 3: Analysis

Perform analysis from the following perspectives:

3a. Analysis of When the Skill Was Used

  • Categorize user messages that triggered the skill from the triggerMessage field in Recent Calls
  • Extract frequently used keywords and phrases

3b. Analysis of When the Skill Was NOT Used

  • Review sessions where the skill was not used (hasSkillCalls: false or the target skill is not in skillsUsed)
  • Examine userMessages from those sessions to find cases where the skill could have been applicable
  • Identify missed trigger patterns

3c. Usage Frequency and Trend Analysis

  • Review usage frequency trends from dailyStats
  • Identify which projects use the skill most from projectStats

3d. Adoption Rate Analysis

  • From conversationStats:
    • Percentage of sessions that used the skill out of total sessions
    • Per-project adoption rate

Step 4: Output Improvement Suggestions

Output the analysis results in the following format:

## Skill Analysis Report: <skill-name>

### Current Usage
- Total invocations: X
- Session usage rate: X% (Y/Z sessions)
- Primary projects: ...
- Usage trend: (increasing/stable/decreasing)

### When the Skill Was Used
- Pattern 1: Messages like "..." (X times)
- Pattern 2: Messages like "..." (Y times)
- ...

### Missed Opportunities
- User message "..." did not trigger the skill (session: ...)
- ...

### Improvement Suggestions

#### Add Trigger Keywords
Based on message patterns not currently captured by the SKILL.md, the following trigger keywords are suggested:
- `keyword1` — Reason: ...
- `keyword2` — Reason: ...

#### Improve Description
Current: "..."
Suggested: "..."
Reason: ...

#### Improve Prompt (SKILL.md Body)
- Improvement 1: ...
- Improvement 2: ...

Notes

  • If data is limited (e.g., fewer than 5 invocations), state this explicitly and analyze as much as possible.
  • If the skill has never been used, provide improvement suggestions based solely on the SKILL.md content.
  • Suggestions must be specific and actionable. Avoid abstract advice.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

cc-skills-usage

No summary provided by upstream source.

Repository SourceNeeds Review
General

ai-image-generator

AI 图片与视频异步生成技能,调用 AI Artist API 根据文本提示词生成图片或视频,自动轮询直到任务完成。 ⚠️ 使用前必须设置环境变量 AI_ARTIST_TOKEN 为你自己的 API Key! 获取 API Key:访问 https://staging.kocgo.vip/index 注册登录后创建。 支持图片模型:SEEDREAM5_0(默认高质量图片)、NANO_BANANA_2(轻量快速)。 支持视频模型:SEEDANCE_1_5_PRO(文生视频,支持音频)、SORA2(文生视频或首尾帧图生视频,支持 firstImageUrl/lastImageUrl)。 触发场景: - 用户要求生成图片,如"生成一匹狼"、"画一只猫"、"风景画"、"帮我画"等。 - 用户要求生成视频,如"生成视频"、"用 SORA2 生成"、"文生视频"、"图生视频"、"生成一段...的视频"等。 - 用户指定模型:SEEDREAM5_0、NANO_BANANA_2、SEEDANCE_1_5_PRO、SORA2。

Archived SourceRecently Updated
General

淘宝投放数据分析

# 投放数据分析技能

Archived SourceRecently Updated
General

productclank-campaigns

Community-powered growth for builders. Boost amplifies your social posts with authentic community engagement (replies, likes, reposts). Discover finds relevant conversations and generates AI-powered replies at scale. Use Boost when the user has a post URL. Use Discover when the user wants to find and engage in conversations about their product.

Archived SourceRecently Updated