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".

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, code-complete skill body that leads with executable TypeScript across a clearly sequenced five-step pipeline and backs it with an error-cause-solution table. Main weaknesses are the absence of explicit validation checkpoints and the lack of any bundle/reference file to offload the large GraphQL field enumerations.

Suggestions

Add an explicit validation checkpoint between fetch and process (e.g., assert sentences is non-empty and summary_status is complete before calling processMeeting), with a retry/backoff note for the 429 case.

Move the full GET_TRANSCRIPT field enumeration into a references/ file (e.g. references/transcript-query.graphql) and keep only the core fields inline, so the SKILL.md body stays a lean overview.

Tighten the GET_TRANSCRIPT query to the fields processMeeting and transcriptToText actually consume, or annotate which fields are optional per plan tier, to reduce token weight without losing actionability.

Dimension	Reasoning	Score
Conciseness	Mostly lean code-first body with minimal prose and no over-explanation of GraphQL/TypeScript concepts, but the full GET_TRANSCRIPT query enumerating every field is substantial content that could be trimmed or referenced separately. Not a 5 because a few sections carry more field detail than the core workflow strictly needs.	4 / 5
Actionability	Every step ships complete, copy-paste-ready TypeScript — the GraphQL client, filtered list query, full-transcript query, processMeeting transform, and transcriptToText exporter are all fully executable and cover the common cases.	5 / 5
Workflow Clarity	Five steps are clearly sequenced (build client → list → fetch → process → export) with built-in error throwing and a causes/solutions table, but there are no explicit validate-then-proceed checkpoints or retry feedback loops. Not capped at 3 because the workflow is retrieval/processing rather than destructive or batch.	4 / 5
Progressive Disclosure	Well-organized into Overview, Prerequisites, five instruction steps, Error Handling, Output, Resources, and Next Steps, with cross-skill references (fireflies-install-auth, fireflies-rate-limits, fireflies-core-workflow-b) and external doc links clearly signaled. Not a 5 because no bundle files exist and the large inline query reference is not split into a separate file.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted description that clearly states capabilities, use-when guidance, and natural trigger phrases in third-person voice. It comprehensively covers what the skill does and when to invoke it with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain (Fireflies.ai meeting transcripts) and lists multiple concrete actions — 'Retrieve and process... with speaker diarization and summaries', 'fetching transcripts, extracting action items', 'building meeting intelligence pipelines' — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Retrieve and process Fireflies.ai meeting transcripts with speaker diarization and summaries') and when ('Use when fetching transcripts... Trigger with phrases like...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides four natural trigger phrases users would actually say — 'fireflies transcript', 'get meeting notes', 'fireflies meeting data', 'fetch fireflies recording' — covering synonyms (transcript, notes, data, recording) with no jargon-only terms.	5 / 5
Distinctiveness Conflict Risk	Targets a specific named SaaS (Fireflies.ai) with fireflies-prefixed triggers, creating a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/saas-packs/fireflies-pack/skills/fireflies-core-workflow-a/SKILL.md
Commit: 8585d6d

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.