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 ./plugins/all-skills/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 uses second person voice ('when you avoid conflict') which violates the style guideline, and it lacks an explicit 'Use when...' trigger clause, which caps completeness. Adding explicit trigger guidance and switching to third person would significantly improve it.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user shares a meeting transcript, call recording, or asks for feedback on their meeting behavior or communication style.'
Switch from second person ('when you avoid conflict') to third person ('Identifies when speakers avoid conflict, use filler words...') to match the required voice.
| 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 does this do' with specific capabilities, 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 document analysis 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 significantly over-engineered and verbose for what is essentially a text analysis task. It explains many concepts Claude already understands (what hedging language is, how to count filler words, what active listening looks like) and includes extensive output templates inline that inflate the token cost. The workflow is reasonably structured but lacks validation steps for input data quality, and the entire content would benefit greatly from being split across multiple files.
Suggestions
Cut the content by at least 60%: remove 'When to Use This Skill', 'What This Skill Does', 'Common Analysis Requests', and 'Related Use Cases' sections entirely—these describe capabilities Claude can infer from the instructions.
Move the detailed output templates, setup tips for specific tools, and extended examples into separate referenced files (e.g., OUTPUT_TEMPLATES.md, SETUP.md, EXAMPLES.md) to improve progressive disclosure.
Add validation checkpoints: verify transcript format is parseable, confirm speaker identification is correct before proceeding, and handle edge cases (missing timestamps, unlabeled speakers).
Remove explanations of what patterns look like (e.g., listing hedging words, defining active listening) and instead focus on the specific analytical approach and output format Claude should use.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~250+ lines. Explains obvious concepts Claude already knows (what conflict avoidance looks like, what filler words are, how to count speaking ratios). The 'When to Use This Skill' and 'What This Skill Does' sections are largely redundant with the instructions. The 'Common Analysis Requests' list and 'Related Use Cases' add little value. Setup tips for specific tools (Zoom, Google Meet, etc.) pad the content significantly. | 1 / 3 |
Actionability | Provides structured output templates and detailed examples of what analysis output should look like, which is useful. However, there is no executable code or concrete commands—everything is descriptive guidance about what to look for and how to format output. The analysis steps are conceptual checklists rather than executable procedures (e.g., 'Calculate percentage of meeting spent speaking' without any concrete method). | 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 was correct, no verification that speaker identification is accurate, no feedback loop for when transcripts lack timestamps or speaker labels. For an analysis task involving potentially messy input data, these gaps matter. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. Everything is inline—detailed output templates, setup instructions for multiple tools, example analyses, common requests lists. The output templates and tool-specific setup tips could easily be split into separate reference files. No bundle files exist to support this either. | 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
- davepoon/buildwithclaude
- Commit
d065ead
- 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.