meeting-minutes-taker
Transforms raw meeting transcripts into high-fidelity, structured meeting minutes with iterative review for completeness. This skill should be used when (1) a meeting transcript is provided and meeting minutes, notes, or summaries are requested, (2) multiple versions of meeting minutes need to be merged without losing content, (3) existing minutes need to be reviewed against the original transcript for missing items, (4) transcript has anonymous speakers like "Speaker 1/2/3" that need identification. Features include: speaker identification via feature analysis (word count, speaking style, topic focus) with context.md team directory mapping, intelligent file naming from content, integration with transcript-fixer for pre-processing, evidence-based recording with speaker quotes, Mermaid diagrams for architecture discussions, multi-turn parallel generation to avoid content loss, and iterative human-in-the-loop refinement.
93
92%
Does it follow best practices?
Impact
96%
1.60xAverage score across 3 eval scenarios
Critical
Do not install without reviewing
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that thoroughly covers what the skill does with specific concrete actions, provides explicit 'when to use' triggers in a numbered list format, and includes natural keywords users would employ. The description is comprehensive without being vague, clearly distinguishing itself from general summarization or document processing skills through its meeting-specific focus and detailed feature list.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Transforms raw meeting transcripts into structured meeting minutes', 'speaker identification via feature analysis', 'intelligent file naming', 'evidence-based recording with speaker quotes', 'Mermaid diagrams for architecture discussions', and 'multi-turn parallel generation'. | 3 / 3 |
Completeness | Clearly answers both what (transforms transcripts into structured minutes with various features) AND when with explicit numbered triggers: '(1) a meeting transcript is provided and meeting minutes requested, (2) multiple versions need merging, (3) existing minutes need review, (4) anonymous speakers need identification'. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'meeting transcript', 'meeting minutes', 'notes', 'summaries', 'Speaker 1/2/3', 'transcript'. These are terms users would naturally use when requesting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused specifically on meeting transcripts and minutes with distinct triggers like 'Speaker 1/2/3 identification' and 'transcript-fixer integration'. Unlikely to conflict with general document or summarization skills due to specific meeting context. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive, well-structured skill with excellent actionability and workflow clarity. The multi-pass generation strategy with parallel subagents is thoroughly documented with concrete implementation details. The main weakness is verbosity - some concepts are explained multiple times and certain sections could be more concise while maintaining clarity.
Suggestions
Consolidate redundant explanations of why multiple passes work and why isolated context matters - these concepts appear in multiple places
Consider moving the extensive anti-patterns list to a separate reference file to reduce main skill length while preserving the valuable guidance
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but verbose in places. It includes some redundant explanations (e.g., explaining why multiple passes work multiple times) and could be tightened. The anti-patterns section is extensive but valuable. Some sections like 'Why isolated context matters' explain concepts Claude should understand. | 2 / 3 |
Actionability | Highly actionable with concrete checklists, specific file path conventions, executable Mermaid diagram examples, exact quote formatting requirements, and copy-paste ready patterns. The multi-turn generation strategy includes specific Task tool usage and file naming conventions. | 3 / 3 |
Workflow Clarity | Excellent workflow clarity with explicit numbered steps, progress tracking checklist, validation checkpoints (speaker confirmation, filename confirmation, quality assessment), and clear feedback loops for human review iterations. The multi-pass generation workflow is thoroughly documented with explicit merge strategies. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections, a Quick Start overview, and appropriate references to external files (meeting_minutes_template.md, completeness_review_checklist.md, context_file_template.md). Content is logically organized with tables for quick reference and expandable detail sections. | 3 / 3 |
Total | 11 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (646 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- fernandezbaptiste/claude-code-skills
- Commit
4f0eae8
- 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.