transcribe

Process audio recordings, meeting transcripts, podcasts, or lectures. Runs an intake interview (date, mode, speakers, language) then processes into structured notes with action items, decisions, and glossary. Triggers: EN: "transcribe", "I have a recording", "process this audio", "meeting notes from recording", "summarize the call", "lecture notes", "podcast summary". IT: "trascrivi", "ho una registrazione", "processa questo audio", "note della riunione", "riassumi la call". FR: "transcrire", "j'ai un enregistrement", "résumer l'appel". ES: "transcribir", "tengo una grabación", "resumir la llamada". DE: "transkribieren", "Aufnahme verarbeiten". PT: "transcrever", "tenho uma gravação".

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-3

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

The body is highly actionable with a clearly sequenced workflow and a verification checklist, but it is a monolithic ~530-line document carrying six full inline templates and some duplicated sections. Splitting templates into reference files and de-duplicating would materially improve conciseness and progressive disclosure.

Suggestions

Externalize the six output-mode templates into separate reference files (e.g. references/templates/meeting.md, lecture.md) and keep SKILL.md as a lean overview with one-line pointers — this trims ~350 lines and lifts progressive_disclosure.

De-duplicate overlapping sections: 'Follow-Up Generator' repeats Mode 1's 'Follow-Up Email Draft' and 'Key Decisions Log' repeats 'Decisions Made' — consolidate each into a single source of truth to reduce token cost.

Tighten template placeholder prose (e.g. '{{2-4 sentences capturing the essence of the meeting. Written for someone who wasn't there.}}') to bare field hints, since Claude already knows how to draft such summaries.

Dimension	Reasoning	Score
Conciseness	The ~530-line body is mostly actionable rather than explanatory of known concepts, but six full inline output templates plus duplicated sections (Follow-Up Generator vs Mode 1's email draft; Key Decisions Log vs Decisions Made) and verbose placeholder prose could be tightened, fitting the score-2 anchor.	2 / 3
Actionability	Concrete, specific guidance throughout — exact output templates, file-naming convention with real examples, precise vault-path resolution rules, and an exact post-it format; absence of code is not penalized for an instruction-only skill whose guidance is this specific.	3 / 3
Workflow Clarity	Clear sequence (vault resolution → intake interview → transcription processing → mode selection → extraction) with an explicit Quality Checklist verification step before saving; the operation is non-destructive so no fix-retry loop is required, matching the score-3 anchor.	3 / 3
Progressive Disclosure	No bundle reference files exist and the six output templates (~350 lines) are inlined in a single monolithic SKILL.md that could be split into per-mode reference files with a lean overview, matching the score-2 anchor of content that should be separate being inline.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 third-person, specific, and supplies explicit trigger guidance in six languages, cleanly answering both what the skill does and when to use it. It is somewhat long due to the multilingual trigger lists, but every list earns its place by broadening distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Process audio recordings, meeting transcripts, podcasts, or lectures", "Runs an intake interview (date, mode, speakers, language)", "processes into structured notes with action items, decisions, and glossary" — matching the score-3 anchor.	3 / 3
Completeness	Explicitly answers both what (process audio into structured notes) and when via an explicit "Triggers:" clause with enumerated terms, satisfying the score-3 anchor and the 'Use when...' requirement.	3 / 3
Trigger Term Quality	Extensive natural trigger terms a user would actually say ("transcribe", "I have a recording", "meeting notes from recording", "summarize the call", "lecture notes", "podcast summary") with strong multilingual coverage, exceeding the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	Clear niche (audio/transcription into Obsidian notes) with distinct, language-specific triggers unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (548 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: gnekt/My-Brain-Is-Full-Crew
Path: skills/transcribe/SKILL.md
Commit: 238ae8c

Reviewed: 23 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.