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.
84
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
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 and when to use it. It provides specific concrete actions, natural trigger terms, explicit 'use when' conditions, and occupies a clear niche. The description is perhaps slightly verbose with the feature list, 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 like speaker identification and transcript processing. Unlikely to conflict with general summarization or document processing skills due to the specific meeting context and detailed feature set. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is exceptionally thorough and actionable with a well-structured multi-step workflow, concrete examples, and clear validation checkpoints. However, it is severely over-verbose — many concepts are explained multiple times (anti-patterns repeat earlier rules, rationale sections explain things Claude already knows), and large sections like speaker identification, diagram examples, and multi-pass strategy could be offloaded to reference files. The content would benefit greatly from aggressive trimming to roughly half its current length.
Suggestions
Cut explanatory rationale sections ('Why multiple complete passes work', 'Why isolated context matters', 'Benefits of file-based context offloading') — Claude understands these concepts; keep only the actionable instructions.
Move the Speaker Identification section (Phases A-C) and Mermaid diagram examples into separate reference files, leaving only brief summaries with links in the main SKILL.md.
Deduplicate the anti-patterns section — many entries restate rules already given in the workflow (e.g., parallel subagents, transcript-specific directories, quote formatting are each mentioned 3+ times).
Remove the WRONG/CORRECT comparison blocks for concepts that only need a single correct example (e.g., multi-pass strategy, directory structure) to reduce redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Extensively explains concepts Claude already understands (why isolated context matters, why multiple passes work, benefits of file-based offloading). Many sections repeat the same points (anti-patterns rehash rules already stated). The WRONG/CORRECT examples for multi-pass strategy, quote formatting, and directory structure are repeated multiple times throughout. | 1 / 3 |
Actionability | Highly actionable with concrete file naming patterns, specific Task tool invocations, executable bash commands, complete Mermaid diagram examples, exact quote formatting templates, and detailed checklists. The guidance is specific and copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with a trackable checklist, clear sequencing (Steps 0-7), explicit validation checkpoints (speaker confirmation, filename confirmation, quality assessment decision point, self-review checklist), and feedback loops (iterate on human feedback, cross-AI comparison verification against transcript). | 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 SKILL.md itself is monolithic with enormous inline content that could be split into reference files — the speaker identification section, diagram examples, and multi-pass strategy details would be better as separate references. | 2 / 3 |
Total | 9 / 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
6bb8d7f
- 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.