meeting-transcript

Process meeting recordings and notes into structured decisions, action items, and team dynamics with intelligent noise filtering

Quality

72%

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 ./.claude/skills/meeting-transcript/SKILL.md

Quality

Content

77%

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 clear phased workflow, but it is verbose and monolithic — filtering guidance is duplicated and content that could live in reference files is inlined. Splitting large templates into reference files and de-duplicating filtering guidance would improve both conciseness and progressive disclosure.

Suggestions

Merge the overlapping Content Filtering Guidelines (EXCLUDE/INCLUDE) and Content Filtering Protocol into a single section to remove redundancy.

Move the Metadata Template and the three agent prompt blocks into reference files (e.g. references/agent-prompts.md, references/metadata-template.yaml) and link them one level deep.

Trim illustrative banter examples ('Hey, did you see the game last night?') since Claude can recognize side conversations without them.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded: the Content Filtering Guidelines and Content Filtering Protocol overlap, and example banter ('Hey, did you see the game last night?') explains concepts Claude already grasps.	2 / 3
Actionability	Copy-paste-ready agent prompts in code blocks plus concrete field-list templates (Content Structure, Metadata Template) give fully actionable, specific guidance.	3 / 3
Workflow Clarity	Phases 1–3 are clearly sequenced, with an Accuracy Verification step in the filtering protocol and explicit QA/Uncertainty-handling standards serving as checkpoints.	3 / 3
Progressive Disclosure	The skill is a monolithic ~230-line file with no bundle references; agent prompts and templates that could be separate files are inline, though sections are well organized.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and occupies a clear niche, but omits an explicit 'Use when' trigger clause and offers only a narrow set of natural trigger terms. Adding explicit invocation guidance would lift completeness and trigger-term quality.

Suggestions

Add a 'Use when the user shares a meeting transcript, recording notes, or asks to extract action items from a meeting' clause to satisfy the 'when' half of completeness.

Broaden natural trigger terms to include 'meeting transcript', 'meeting summary', and 'meeting notes' variations users actually say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'structured decisions, action items, and team dynamics with intelligent noise filtering' — mirroring the multi-action anchor.	3 / 3
Completeness	Clearly states what the skill does, but lacks a 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 2 per the guideline.	2 / 3
Trigger Term Quality	'meeting recordings and notes' are natural user terms, but coverage is narrow (no 'transcript', 'meeting summary') and there is no explicit trigger phrasing.	2 / 3
Distinctiveness Conflict Risk	The meeting-transcript niche is distinct with clear domain triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: huytieu/COG-second-brain
Path: .claude/skills/meeting-transcript/SKILL.md
Commit: dfbf9e9

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.