meeting-insights-analyzer
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership skills.
64
47%
Does it follow best practices?
Impact
96%
1.12xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.trae/skills/meeting-insights-analyzer/SKILL.mdQuality
Discovery
67%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 strong in specificity and distinctiveness, clearly articulating concrete analytical capabilities around meeting behavior. However, it lacks an explicit 'Use when...' trigger clause, which caps completeness, and uses second person ('when you avoid conflict') which should be penalized per the rubric guidelines. The trigger terms could be expanded to cover more natural user phrasings.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for feedback on a meeting, wants to analyze a meeting transcript or recording, or seeks communication improvement insights.'
Replace second person voice ('when you avoid conflict') with third person ('when speakers avoid conflict') to align with style requirements.
Include additional natural trigger terms users might say, such as 'meeting notes', 'call recording', 'how did I do in the meeting', or 'meeting feedback'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: analyzing meeting transcripts/recordings, uncovering behavioral patterns, identifying conflict avoidance, filler words, conversation domination, and missed listening opportunities. | 3 / 3 |
Completeness | Clearly answers 'what' (analyzes transcripts, identifies behavioral patterns) but lacks an explicit 'Use when...' clause. The 'Perfect for professionals...' sentence implies a target audience but doesn't provide explicit trigger guidance for when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes some natural keywords like 'meeting transcripts', 'recordings', 'filler words', 'communication', and 'leadership skills', but misses common variations users might say like 'meeting notes', 'call recording', 'feedback on my meeting', or 'how did I do in the meeting'. | 2 / 3 |
Distinctiveness Conflict Risk | Has a clear niche focused specifically on meeting transcript behavioral analysis and communication feedback, which is distinct enough to avoid conflicts with general transcript summarization or generic communication skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is well-intentioned and covers the domain thoroughly, but suffers from extreme verbosity—it explains concepts Claude already knows (what filler words are, what active listening means) and includes large sections that could be separate files or omitted entirely. The workflow is reasonable but lacks validation steps for file parsing and speaker identification. The actionability is moderate: good output templates but no concrete code for transcript parsing or metric calculation.
Suggestions
Cut the content by at least 60%: remove 'When to Use', 'What This Skill Does', 'Common Analysis Requests', 'Related Use Cases', and 'Setup Tips' sections—these are either obvious to Claude or not part of the skill's core instructions.
Move the detailed output templates and pattern definitions into separate referenced files (e.g., PATTERNS.md, OUTPUT_TEMPLATES.md) to improve progressive disclosure.
Add concrete code snippets or commands for parsing common transcript formats (VTT, SRT) and calculating speaking ratios, rather than describing these abstractly.
Add validation checkpoints: verify transcript files were parsed correctly, confirm speaker identification is accurate before proceeding with analysis, and validate that all files in the folder were processed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Includes extensive 'When to Use' and 'What This Skill Does' sections that describe capabilities Claude can infer. The 'Common Analysis Requests' list, 'Related Use Cases', and 'Setup Tips' for third-party tools add significant bloat. Much of the content explains concepts Claude already understands (what conflict avoidance looks like, what filler words are, how active listening works). | 1 / 3 |
Actionability | The skill provides structured output templates and specific patterns to look for (hedging language examples, speaking ratio calculations), which is somewhat concrete. However, there's no executable code for parsing transcript formats (VTT, SRT), calculating speaking ratios, or counting filler words—these are described abstractly rather than implemented. The 'instructions' are more of a conceptual framework than executable guidance. | 2 / 3 |
Workflow Clarity | The 6-step workflow (Discover → Clarify → Analyze → Examples → Synthesize → Follow-up) provides a clear sequence. However, there are no validation checkpoints—no step to verify transcript parsing succeeded, no check that speaker identification is correct, no verification that the analysis covers all files. For a multi-step process involving file parsing and analysis, this is a notable gap. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. The output templates, setup tips, example analyses, common requests, and detailed pattern definitions are all inline. The content would benefit enormously from splitting the output templates, setup guides, and detailed pattern catalogs into separate referenced files. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Lingjie-chen/MT5
- Commit
3069d33
- 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.