fireflies-core-workflow-a
Retrieve and process Fireflies.ai meeting transcripts with speaker diarization and summaries. Use when fetching transcripts, extracting action items, or building meeting intelligence pipelines. Trigger with phrases like "fireflies transcript", "get meeting notes", "fireflies meeting data", "fetch fireflies recording".
67
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 a strong skill description that clearly identifies the specific platform (Fireflies.ai), lists concrete capabilities, and provides explicit trigger guidance with natural user phrases. It covers all key dimensions well, with particularly strong distinctiveness due to the product-specific naming and domain terminology.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'retrieve and process meeting transcripts', 'speaker diarization', 'summaries', 'extracting action items', and 'building meeting intelligence pipelines'. These are concrete, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (retrieve/process transcripts with diarization, summaries, action items) and 'when' (explicit 'Use when...' clause plus 'Trigger with phrases like...' providing concrete trigger guidance). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'fireflies transcript', 'get meeting notes', 'fireflies meeting data', 'fetch fireflies recording'. These are phrases users would naturally say, and the inclusion of the product name 'Fireflies' and common variations like 'meeting notes' and 'recording' is strong. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific product name 'Fireflies.ai' and domain-specific terms like 'speaker diarization' and 'meeting intelligence pipelines'. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 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 with complete executable TypeScript code covering the full Fireflies transcript retrieval pipeline. Its main weaknesses are the lack of validation checkpoints between steps (e.g., checking transcript processing status before fetching full data) and the verbosity of inline GraphQL queries that could benefit from being referenced externally. The error handling table is a nice touch but would be stronger if integrated as validation steps in the workflow.
Suggestions
Add a validation step between Step 2 and Step 3 to check that the transcript's processing status is complete before fetching full sentences, and add a retry/backoff pattern for rate limits.
Consider moving the full GraphQL query strings to a referenced file and keeping only a concise example in the main skill body to reduce token usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with executable code examples, but includes some unnecessary verbosity—the full GraphQL queries with every field listed are quite long, and the MeetingIntelligence processing function could be more concise. The hardcoded date '2026-03-15T00:00:00Z' is also unnecessary detail. | 2 / 3 |
Actionability | Fully executable TypeScript code throughout—complete GraphQL client, queries, processing functions, and export utilities are all copy-paste ready. The error handling table provides specific error codes with concrete solutions. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced (build client → list → fetch → process → export), but there are no validation checkpoints. For an API workflow, there's no verification that the API key works, no check that the transcript is fully processed before fetching sentences, and no error recovery loop despite mentioning rate limits. | 2 / 3 |
Progressive Disclosure | References to `fireflies-install-auth`, `fireflies-rate-limits`, and `fireflies-core-workflow-b` provide some navigation, and external docs are linked. However, the inline content is quite long (~150 lines of code) and the full GraphQL queries with all fields could be split into reference files. No bundle files support the references. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
a04d1a2
- 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.