CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fireflies-transcript

Fetch raw Fireflies.ai meeting transcripts. Use only when the user explicitly invokes /fireflies-transcript; for YouTube, use youtube-transcript.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary single-file skill: fully executable commands for every step, dense with hard-won API gotchas (exact-match title filter, epoch-millisecond dates, sentences:null handling) that Claude could not know otherwise, and an explicit success criterion plus failure-mode recovery paths. Nothing material is missing for its stated purpose.

DimensionReasoningScore

Conciseness

The body is lean and every token earns its place: it adds only Fireflies-specific knowledge Claude cannot know ("`date` is epoch **milliseconds**", "The `transcripts(title:)` filter is EXACT-match", "Transcripts run to hundreds of sentences — save to a file, never dump to stdout/chat") with zero explanation of known concepts. Nothing could be trimmed without losing information, so it matches the 'lean and efficient; assumes Claude's competence' anchor.

5 / 5

Actionability

Both steps are copy-paste executable curl+jq pipelines, including a jq-wrapped query builder ("-d "$(jq -nc --arg query "$QUERY" '{query: $query}')"), and the skill covers the common output cases ("speaker-labeled raw text (usual deliverable)" and "bare text only"). This matches the 'fully executable; copy-paste ready code or commands; specific examples cover the common cases' anchor.

5 / 5

Workflow Clarity

Clear sequence (auth state-check with a stop condition → find meeting id → pull transcript) with explicit validation ("A pull is successful only if the sentence count is > 0 and the speakers/topic match") and a feedback loop per failure mode ("errors[] ... fix the query", "401/invalid key ... ask the user for a new one"). The skill is read-only, so no destructive/batch validation cap applies; this matches the 5 anchor's explicit validation steps and error-recovery loops.

5 / 5

Progressive Disclosure

This is a simple, single-purpose skill with no external references needed (no references/, scripts/, or assets/ exist and none are mentioned in the body), and the body is cleanly sectioned (Auth, Step 1, Step 2, Failure modes, Verify). Under the simple-skill exception, well-organized sections with no need for external files score 5; there is no inlined content that belongs in a separate file.

5 / 5

Total

20

/

20

Passed

Description

82%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 strong, tight description: it states a concrete capability, gives an unambiguous invocation trigger, and actively disambiguates against the closest sibling skill. Its only weakness is thin capability coverage — one action instead of several — which slightly limits trigger-term breadth.

Suggestions

Add one or two more concrete capabilities to the 'what' clause, e.g. "Fetch raw Fireflies.ai meeting transcripts with speaker labels, keywords, and participant lists" to raise specificity from one action to several.

Include natural synonyms such as "meeting notes" or "meeting recording" alongside "meeting transcripts" so users searching with those phrasings still land on this skill.

Consider stating the read-only nature in the description ("read-only GraphQL fetch") so users know no data is modified before invoking it.

DimensionReasoningScore

Specificity

The description names the domain and one concrete action ("Fetch raw Fireflies.ai meeting transcripts"), matching the 'names domain and 1-2 concrete actions' anchor. It does not list several specific actions (e.g., speaker-labeled output, summaries, participants), so it is not a 4; the action given is fully concrete, so it is above a 2.

3 / 5

Completeness

"Fetch raw Fireflies.ai meeting transcripts" clearly answers 'what', and "Use only when the user explicitly invokes /fireflies-transcript" answers 'when' with a concrete trigger phrase. The 'when' clause is as explicit and specific as possible for a disable-model-invocation skill, so it exceeds the 4 anchor where 'when' could be more explicit.

5 / 5

Trigger Term Quality

Includes good natural keywords — "Fireflies.ai meeting transcripts", "YouTube", and the exact slash-command name "/fireflies-transcript" — that a user invoking this skill would naturally say. It stops short of the 5 anchor's comprehensive synonym coverage (missing variants like "meeting notes", "meeting recording", "call transcript").

4 / 5

Distinctiveness Conflict Risk

Fireflies.ai is a clear niche with distinct triggers, and the description even preempts the nearest conflict ("for YouTube, use youtube-transcript"), giving minimal conflict risk. Matches the 'clear niche with distinct triggers' anchor exactly.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

davidondrej/skills

Path

skills/research-and-web/fireflies-transcript/SKILL.md

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.