meeting-synthesis
Turn one or more meeting transcripts, notes, or Slack threads into concise takeaways and clear action items with DRIs. Works with a single meeting or a batch from the whole week.
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 ./execution-skills/skills/meeting-synthesis/SKILL.mdQuality
Discovery
82%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 a strong description with excellent specificity and natural trigger terms that clearly define its niche around meeting content processing. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude more confidently select this skill. The description effectively communicates both input types and output formats, making it distinctive among potential skills.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user shares meeting transcripts, meeting notes, or Slack threads and wants a summary, takeaways, or action items.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Turn meeting transcripts, notes, or Slack threads into concise takeaways and clear action items with DRIs.' It specifies input types (transcripts, notes, Slack threads), outputs (takeaways, action items with DRIs), and scope (single meeting or weekly batch). | 3 / 3 |
Completeness | Clearly answers 'what does this do' (turns transcripts/notes/threads into takeaways and action items), but lacks an explicit 'Use when...' clause. The 'when' is only implied by the description of capabilities, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'meeting transcripts', 'notes', 'Slack threads', 'takeaways', 'action items', 'DRIs', 'batch', 'whole week'. These are terms users naturally use when requesting meeting summaries. | 3 / 3 |
Distinctiveness Conflict Risk | Has a clear niche focused specifically on meeting-related content (transcripts, notes, Slack threads) with distinct outputs (takeaways, action items with DRIs). Unlikely to conflict with general summarization or document processing skills due to the meeting-specific framing. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill that provides a complete prompt template with clear output formats for both single and batch meeting processing. Its main strengths are the concrete table formats, good/bad examples for action items, and the single-vs-multi branching logic. Weaknesses include some verbosity in the prompt template itself, lack of validation/verification steps, and the monolithic structure of the prompt block.
Suggestions
Add a brief validation step: e.g., 'After generating output, verify every action item has a specific verb and measurable outcome; flag any that are vague.'
Trim the prompt template by removing explanatory commentary Claude doesn't need (e.g., 'Your job is to extract signal from noise') and consolidating the rules that are already implied by the template structure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some unnecessary framing ('You are an experienced PM who is ruthlessly concise') and explanatory commentary that Claude doesn't need. The rules section restates things that are already implied by the template structure. The tips section adds useful but somewhat verbose guidance. | 2 / 3 |
Actionability | The skill provides a fully concrete, copy-paste-ready prompt template with specific output formats (tables with exact columns), clear examples of good vs bad action items ('Follow up on pricing' vs 'Share revised pricing tiers with the team by Friday'), and explicit formatting for both single and multi-meeting scenarios. | 3 / 3 |
Workflow Clarity | The skill clearly branches between single-meeting and multi-meeting paths with well-defined output sections, but lacks any validation or verification steps. There's no guidance on checking output quality, handling ambiguous transcripts, or what to do if the input is too noisy to extract meaningful action items. | 2 / 3 |
Progressive Disclosure | The content is reasonably well-structured with clear sections (template, tips), but the prompt template itself is quite long and monolithic. For a standalone skill with no bundle files, the organization is acceptable but the inline prompt could benefit from being more concise with detailed format specs split out. | 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- amplitude/builder-skills
- Commit
221ffaa
- 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.