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.
Install with Tessl CLI
npx tessl i github:daymade/claude-code-skills --skill meeting-minutes-takerOverall
score
87%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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 and explicitly states when to use it with four numbered trigger conditions. The description uses appropriate third-person voice throughout and includes natural trigger terms users would actually say. The only minor weakness is verbosity - the features list could be more concise while retaining the essential information.
| 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 | Clear niche focused specifically on meeting transcripts and minutes with distinct triggers like 'Speaker 1/2/3', 'transcript-fixer', and meeting-specific terminology. Unlikely to conflict with general document or summarization skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with excellent workflow clarity and validation checkpoints. The multi-pass generation strategy with parallel subagents is clearly explained with concrete implementation details. Main weakness is verbosity - the document repeats key concepts multiple times and includes extensive examples that could be moved to reference files to improve token efficiency.
Suggestions
Move detailed Mermaid diagram examples to a separate reference file (e.g., references/diagram_examples.md) and keep only 1-2 brief examples inline
Consolidate the anti-patterns section - many items are variations of the same concept (e.g., multiple items about single-pass vs multi-pass generation)
Remove redundant explanations of 'why multiple complete passes work' - this concept is explained 3+ times in different sections
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but verbose in places - includes some redundant explanations (e.g., explaining why multiple passes work multiple times, repeating the same concepts in different sections). The anti-patterns section is extensive but could be consolidated. However, it avoids explaining basic concepts Claude knows. | 2 / 3 |
Actionability | Highly actionable with concrete workflows, specific file naming patterns, executable code examples for Mermaid diagrams, detailed checklists, and copy-paste ready templates. The Task tool usage is clearly specified with exact parameters and file paths. | 3 / 3 |
Workflow Clarity | Excellent workflow clarity with explicit numbered steps, progress tracking checklist, clear validation checkpoints (user confirmation for speaker mapping, filename confirmation), and feedback loops (iterate on human feedback, cross-AI comparison). Multi-step processes are well-sequenced with explicit decision points. | 3 / 3 |
Progressive Disclosure | References external files appropriately (meeting_minutes_template.md, completeness_review_checklist.md, context_file_template.md) with a clear reference table. However, the main document is quite long (~500+ lines) with some content that could be moved to reference files (e.g., detailed Mermaid diagram examples, extensive anti-patterns list). | 2 / 3 |
Total | 10 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 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 |
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 12 / 16 Passed | |
- 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.