meeting-transcript

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

Quality

61%

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

63%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-structured and actionable with clear sequencing and verification steps, but it is monolithic and contains notable redundancy across filtering/verification sections. Splitting large reusable blocks into reference files and de-duplicating would improve both conciseness and progressive disclosure.

Suggestions

Consolidate the overlapping 'Content Filtering Guidelines', 'Content Filtering Protocol', 'Quality Assurance', and 'Uncertainty Handling' sections to remove repeated filtering/verification content.

Move the detailed agent prompts and metadata/content-structure templates into separate reference files (e.g., references/agent-prompts.md, references/templates.md) and link to them from SKILL.md.

Fix the inconsistency where the Integration section calls 'Phase 2, Agent 3' the 'meeting-reviewer' while Phase 2 defines it as the 'context-enricher'.

Dimension	Reasoning	Score
Conciseness	The body is mostly free of concepts Claude already knows, but significant redundancy across 'Content Filtering Guidelines', 'Content Filtering Protocol', 'Quality Assurance', and 'Uncertainty Handling' repeats the same filtering/verification ideas and could be tightened.	3 / 5
Actionability	Concrete, actionable guidance throughout: numbered agent prompts with explicit return values, a metadata YAML template, and a detailed content-structure schema with specific fields per section.	4 / 5
Workflow Clarity	A clear three-phase sequence (Setup, Parallel Processing, Assembly) with verification checkpoints (Accuracy Verification, Quality Assurance, Uncertainty Handling); however, the Integration section mislabels 'Phase 2, Agent 3' as 'meeting-reviewer' contradicting the earlier 'context-enricher', a minor consistency gap.	4 / 5
Progressive Disclosure	Well-organized section headers, but the ~230-line file is monolithic with detailed agent prompts, templates, and domain-specific processing all inlined that could be split into separate reference files; no external references are signaled.	3 / 5
	Total	14 / 20 Passed

Description

58%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 clearly conveys what the skill does with specific, concrete outputs, but omits any explicit trigger guidance telling Claude when to invoke it. Adding a 'Use when...' clause with natural trigger phrases would lift completeness and trigger-term quality.

Suggestions

Append a 'Use when...' clause with natural trigger phrases (e.g., 'Use when the user shares a meeting transcript, recording, or meeting notes, or asks to extract action items or decisions from a meeting').

Include synonym trigger terms like 'transcript', 'meeting minutes', and 'action items' to improve keyword coverage.

Keep the concrete output list but ensure the third-person voice is maintained throughout (currently good).

Dimension	Reasoning	Score
Specificity	Names the domain ('meeting recordings and notes') and several concrete outputs ('structured decisions, action items, and team dynamics') plus 'intelligent noise filtering', listing multiple specific actions with only minor coverage gaps.	4 / 5
Completeness	Provides a clear 'what' (process meetings into structured outputs with noise filtering) but entirely lacks a 'when'/'Use when...' clause, capping completeness at 3 per the missing-trigger-guidance rule.	3 / 5
Trigger Term Quality	Contains relevant natural keywords ('meeting recordings', 'notes') but misses common variations users would say such as 'transcript', 'meeting minutes', or 'action items' as triggers.	3 / 5
Distinctiveness Conflict Risk	The meeting-transcript niche is fairly distinct with low conflict risk, though minor overlap could occur with general note-taking or summarization skills.	4 / 5
	Total	14 / 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
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: cb4644d

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.