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

85%

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

71%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.

The skill body is highly actionable with concrete templates and a clear processing workflow, but it is token-heavy: six full templates are inlined rather than split into reference files, which hurts both conciseness and progressive disclosure. No bundle files are provided to offload the detail.

Suggestions

Move the six mode output templates (Meeting, Lecture, Podcast, Interview, Voice Journal, General) into separate files under references/ (e.g. references/templates/meeting.md) and keep SKILL.md as an overview that links to them, improving both conciseness and progressive_disclosure.

Trim redundant prose such as 'Inform the user that the agent cannot directly transcribe audio' and consolidate the repeated frontmatter/section guidance shared across modes.

Add an explicit validation feedback loop before saving (e.g. 'run the Quality Checklist; if any box fails, fix and re-check before writing to 00-Inbox/') to raise workflow_clarity from 4 to 5.

Dimension	Reasoning	Score
Conciseness	The body is ~515 lines with six full output templates (Meeting, Lecture, Podcast, Interview, Voice Journal, General) inlined; most content is actionable rather than concept-explanation, but the aggregate template bulk could be tightened and is noticeably over a lean budget.	3 / 5
Actionability	Copy-paste-ready output templates with complete YAML frontmatter, tables, and section structure, plus a concrete intake-interview question list and filename convention with worked examples — fully executable instruction-only guidance.	5 / 5
Workflow Clarity	Clear sequence (intake → transcription processing → mode selection → action/decision extraction → follow-up → naming → writing rules) with a pre-save Quality Checklist as a checkpoint, but error-recovery feedback loops are only implicit rather than spelled out.	4 / 5
Progressive Disclosure	Good section structure, but all six large templates are inlined in SKILL.md with no bundle files (references/, scripts/, assets/ absent); the bulk that could live in one-level-deep reference files is kept inline, and the only references point to an external vault agent system rather than this skill's own materials.	3 / 5
	Total	15 / 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.

The description is excellent: it concisely states concrete capabilities, provides comprehensive multilingual natural-language triggers, and cleanly answers both what the skill does and when to use it. Third-person voice is maintained throughout.

Dimension	Reasoning	Score
Specificity	Names the domain ('audio recordings, meeting transcripts, podcasts, or lectures') and multiple concrete actions ('Runs an intake interview', 'processes into structured notes with action items, decisions, and glossary') — comprehensive coverage matching the 5-anchor example.	5 / 5
Completeness	Explicitly answers both 'what' (process audio into structured notes with action items, decisions, glossary via an intake interview) and 'when' (a dedicated 'Triggers:' block with concrete phrases), matching the 5-anchor example.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases across seven languages ('transcribe', 'I have a recording', 'meeting notes from recording', 'summarize the call', 'lecture notes', 'podcast summary'), covering synonyms and user-natural phrasing.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (transcription/meeting intelligence) with specific, audio-centric triggers that minimal overlap with other skills; written in third person ('Process', 'Runs') with no first/second-person voice penalty.	5 / 5
	Total	20 / 20 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 (529 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

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

Reviewed: 5 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.