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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

87%

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

A strong, action-oriented workflow skill: executable code throughout, lean prose, and well-signaled references. The main gap is workflow clarity, where the sequence is clear but lacks explicit inline verification checkpoints before processing, leaving validation implicit in the error table rather than gated in the step flow.

Suggestions

Add an explicit verification checkpoint in the step flow, e.g. after fetching a transcript (Step 3) check summary_status / non-empty sentences before running processMeeting, mirroring the guidance already in the error-handling table.

Optionally split the large GET_TRANSCRIPT field manifest into a reference file (e.g. references/queries.md) to lighten the SKILL.md body while keeping the quick-start query inline.

State the expected output shape of processMeeting inline (or point to the MeetingIntelligence interface) so downstream routing in the final step is unambiguous without re-reading Step 4.

Dimension	Reasoning	Score
Conciseness	The body is lean — an overview sentence, concise prerequisites, and executable TypeScript with minimal prose; it never explains concepts Claude already knows (e.g., what GraphQL or a transcript is), and every code block earns its place. It is not quite the single-snippet ideal, so it sits at the top of the range rather than exceeding it.	3 / 3
Actionability	Provides complete, copy-paste-ready TypeScript: a working GraphQL client, full query strings with real fields, and concrete processing/export functions — fully executable rather than pseudocode.	3 / 3
Workflow Clarity	Steps 1–5 are clearly sequenced and an error-handling table gives recovery guidance, but there are no explicit inline validation/verification checkpoints (e.g., check summary_status before processing sentences) embedded in the step flow, leaving checkpoints implicit rather than gated. It is above the level-1 anchor because the sequence is unambiguous and recovery is documented.	2 / 3
Progressive Disclosure	Clear overview with well-signaled one-level-deep references — the Resources section links to Fireflies docs and Next Steps defers search/analytics/AskFred to the sibling skill fireflies-core-workflow-b — with no nested reference chains and easy section-based navigation. No bundle files exist to verify, but the existing references are clearly signaled and content is appropriately scoped (heavy search/analytics deferred to the sibling skill).	3 / 3
	Total	11 / 12 Passed

Description

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.

The description is concise, specific, and complete — it states concrete capabilities, gives natural trigger phrases, and explicitly covers both what the skill does and when to use it, all in third person. It is a strong, well-calibrated description with no over-claims or padding.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — "Retrieve and process Fireflies.ai meeting transcripts with speaker diarization and summaries", "extracting action items", "building meeting intelligence pipelines" — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both "what" (retrieve/process transcripts, diarization, summaries, action items, pipelines) and "when" via an explicit "Use when fetching transcripts..." clause, satisfying the top anchor.	3 / 3
Trigger Term Quality	Provides natural trigger phrases users would actually say — "fireflies transcript", "get meeting notes", "fireflies meeting data", "fetch fireflies recording" — giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	The Fireflies.ai niche is clearly scoped with distinct triggers, making it unlikely to fire for unrelated skills; uses third-person voice with no first/second-person phrasing.	3 / 3
	Total	12 / 12 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
Commit: 3022dd3

Reviewed: 1 day 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.