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 lacks an explicit 'Use when...' trigger clause, relying instead on an implied audience statement ('Perfect for professionals...'). It also uses second person ('when you avoid conflict') which slightly weakens the professional tone, though the rubric specifically penalizes first/second person on specificity—the second person here is describing the user's behavior being analyzed rather than addressing the user directly.
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 communication.'
Include additional natural trigger terms users might say, such as 'meeting notes', 'call recording', 'Zoom transcript', '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 does this do' with specific capabilities, but lacks an explicit 'Use when...' clause. The phrase 'Perfect for professionals seeking...' hints at when but is not an explicit trigger guidance, which caps this at 2 per the rubric guidelines. | 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 | The combination of meeting transcript analysis with behavioral pattern detection (conflict avoidance, filler words, conversation dominance) creates a clear, distinct niche that is unlikely to conflict with general transcription 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 it does. It spends most of its token budget explaining concepts Claude already understands (what hedging language is, how to count filler words) and providing extensive output templates rather than actionable parsing logic or executable code. The workflow is reasonable but lacks validation steps for transcript parsing, and the entire content is monolithic with no progressive disclosure.
Suggestions
Cut the 'When to Use This Skill', 'What This Skill Does', 'Common Analysis Requests', and 'Related Use Cases' sections entirely—they add no actionable value and waste tokens on things Claude can infer.
Add concrete code snippets for parsing common transcript formats (VTT, SRT, TXT with speaker labels) and computing metrics like speaking ratios and filler word counts.
Move the output format templates, setup tips, and detailed examples into separate referenced files (e.g., OUTPUT_FORMATS.md, SETUP.md, EXAMPLES.md) to reduce the main skill to a concise overview.
Add a validation step after transcript parsing to confirm speaker identification is correct and file formats were properly handled before proceeding with analysis.
| 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. Setup tips for various meeting tools, common analysis requests list, and related use cases add significant bloat without adding actionable value. | 1 / 3 |
Actionability | Provides detailed output templates and analysis categories, but lacks executable code or concrete commands. The analysis steps are descriptive rather than executable—there are no scripts, no parsing logic, no actual code for processing VTT/SRT files. The guidance is essentially 'look for these patterns' which Claude could infer. The output format templates are the most actionable element. | 2 / 3 |
Workflow Clarity | The 6-step workflow (Discover → Clarify → Analyze → Examples → Synthesize → Follow-up) provides a clear sequence, but lacks validation checkpoints. There's no verification step to confirm transcript parsing was correct, no handling of malformed transcripts, and no feedback loop for when speaker identification is ambiguous or files can't be parsed. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. Everything is inline—output templates, setup instructions, examples, common requests—resulting in a very long document. Content like setup tips for various tools, the common analysis requests list, and detailed output templates could easily be split into separate reference 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
- davepoon/buildwithclaude
- Commit
364c6b2
- 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.