meeting-recorder-assistant

Intelligent meeting recording and transcription assistant with automated minutes generation, action item extraction, and sentiment analysis. Supports audio transcription, speaker diarization, meeting summarization, and task extraction. Use when users need to record meetings, transcribe audio, generate meeting minutes, extract action items, or analyze meeting content.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/meeting-recorder-assistant/SKILL.md

Quality

Content

68%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 content is well-organized, concise, and actionable with executable examples backed by real bundle scripts. Its main weakness is the absence of an end-to-end sequenced workflow and validation checkpoints for the recording/transcription pipeline.

Suggestions

Add a sequenced end-to-end workflow (record -> transcribe -> generate minutes -> extract actions) so the multi-step process is explicit.

Include validation/checkpoint steps (e.g., verify the audio file exists and is non-empty before transcription; confirm transcript parsed before minutes generation).

Trim redundant inline code comments like '# Initialize recorder' to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is reasonably lean with short feature bullets and minimal explanatory padding, though comments like '# Initialize recorder' and '# Start recording' are mildly redundant.	4 / 5
Actionability	Provides concrete, executable Python examples for each main feature with real imports matching the bundled scripts, with only minor gaps (e.g., no transcription-path wiring shown end-to-end).	4 / 5
Workflow Clarity	Steps are presented as separate usage snippets rather than a sequenced workflow, and there are no validation or verification checkpoints despite batch/destructive operations like recording and overwriting audio files.	3 / 5
Progressive Disclosure	The body is a concise overview organized into clear sections, and referenced scripts (meeting_recorder.py, meeting_minutes.py, action_extractor.py) are real bundled files referenced one level deep.	4 / 5
	Total	15 / 20 Passed

Description

75%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 strong, covering concrete capabilities and providing an explicit 'Use when' trigger clause in third person. It is slightly verbose and could tighten its trigger-term coverage with synonyms and file extensions.

Suggestions

Add common synonyms and file extensions to the trigger clause (e.g., 'take notes', '.wav', '.mp3') to improve natural-term coverage.

Trim the opening feature list slightly to reduce verbosity while preserving the concrete actions.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions (transcription, speaker diarization, summarization, action item extraction, sentiment analysis) with only minor gaps in coverage.	4 / 5
Completeness	Clearly answers 'what' via the feature list and 'when' via an explicit 'Use when users need to...' clause, though the trigger list could be more concise and specific.	4 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('record meetings, transcribe audio, generate meeting minutes, extract action items') but misses common synonyms like 'take notes' and file extensions.	4 / 5
Distinctiveness Conflict Risk	The meeting-recording niche is fairly distinct with specific triggers, with only minor overlap risk against general transcription or note-taking skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: OpenBMB/PilotDeck
Path: skills/meeting-recorder-assistant/SKILL.md
Commit: 9a33f4d

Reviewed: 2 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.