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.
78
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./meeting-minutes-taker/SKILL.mdQuality
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 and when to use it. It provides specific concrete actions, natural trigger terms, explicit 'use when' conditions, and occupies a clear niche. The only minor concern is that it's quite verbose, but the detail serves the purpose of disambiguation well.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: transforms transcripts into structured minutes, speaker identification via feature analysis, intelligent file naming, evidence-based recording with speaker quotes, Mermaid diagrams for architecture discussions, multi-turn parallel generation, and iterative refinement. | 3 / 3 |
Completeness | Clearly answers both 'what' (transforms transcripts into structured meeting minutes with various features) and 'when' with an explicit numbered list of trigger conditions: when a transcript is provided and minutes requested, when merging versions, when reviewing for missing items, and when anonymous speakers need identification. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'meeting transcript', 'meeting minutes', 'notes', 'summaries', 'Speaker 1/2/3', 'speaker identification', 'transcript'. These cover common variations of how users would describe this task. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on meeting transcript-to-minutes transformation with clear triggers. Unlikely to conflict with general summarization or document processing skills due to the specific meeting/transcript/minutes terminology and detailed feature set. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has excellent workflow clarity with well-defined steps, validation checkpoints, and iteration patterns, but is severely undermined by extreme verbosity. The same concepts (parallel subagents, UNION merge, isolated context, file-based offloading) are repeated 4-5 times across different sections. The content would benefit enormously from splitting detailed reference material into separate files and keeping the main SKILL.md as a lean overview with the core checklist and key rules.
Suggestions
Reduce content by 50-60%: eliminate all 'why this works' explanations (Claude doesn't need persuading), remove duplicate descriptions of UNION merge/parallel subagents/isolated context, and consolidate the anti-patterns list which repeats guidance already given in the workflow.
Move detailed reference content to separate files: speaker identification analysis (Phase A/B/C), diagram examples, quote formatting rules, and quality assessment criteria could each be in references/ files, keeping SKILL.md as a concise overview.
Make Task tool usage more concrete: provide actual Task tool call syntax rather than pseudocode comments like `Task(subagent_type="general-purpose", prompt="...")` — show the exact prompt structure a subagent should receive.
Consolidate the workflow: the 'Core Workflow' checklist and the subsequent detailed step descriptions repeat the same information — merge them into a single pass through the workflow with inline details.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Contains extensive explanations of why things work ('Why multiple complete passes work', 'Why isolated context matters', 'Benefits of file-based context offloading'), redundant examples, and repeated anti-patterns. The same concepts (UNION merge, parallel subagents, isolated context) are restated multiple times across sections. Much of this could be condensed to 1/3 the length without losing actionable content. | 1 / 3 |
Actionability | Provides concrete workflow steps, checklists, and specific examples (file naming patterns, speaker analysis tables, quote formatting). However, the Task tool usage is pseudocode rather than executable, the merge process lacks concrete implementation, and many steps are described conceptually rather than with copy-paste ready commands or code. | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced with a trackable checklist, explicit validation checkpoints (speaker confirmation, filename confirmation, quality assessment decision point, self-review checklist), and feedback loops (human review iteration pattern with concrete examples of multiple rounds). The workflow handles error recovery well with cross-AI comparison verification steps. | 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 SKILL.md itself is monolithic with enormous inline content that should be split out — the speaker identification section, diagram examples, quote formatting rules, and anti-patterns list could each be separate reference files. The document tries to be both overview and comprehensive reference. | 2 / 3 |
Total | 8 / 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 (659 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- daymade/claude-code-skills
- Commit
5c9eda4
- 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.