meeting-transcript

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

50%

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

The body is well-structured with a clear phased workflow and useful templates, but it is verbose with redundant filtering sections, lacks integrated validation checkpoints, and is monolithic with no progressive disclosure via reference files. Tightening redundancy and splitting stable reference material into bundled files would improve it.

Suggestions

Consolidate the three overlapping filtering sections (Guidelines, Protocol, Quality Assurance) into one with a single EXCLUDE/INCLUDE list and a brief verification step.

Add an explicit validation/feedback checkpoint in the workflow, e.g. after Phase 2 assembly, verify each action item has an owner+deadline and loop back if not.

Move the stable metadata template and content-structure template into a references/ file (e.g. TEMPLATES.md) and link to it from the body for progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The ~230-line body is mostly task-focused but redundant — content filtering is described three times ("Content Filtering Guidelines", "Content Filtering Protocol", and "Quality Assurance") and the EXCLUDE/INCLUDE example quotes pad length with concepts Claude already grasps.	2 / 3
Actionability	Concrete elements exist (numbered agent prompts, return-format specs, YAML metadata template, content-structure template), but several directives stay abstract ("Assess communication patterns", "Evaluate decision-making process effectiveness") without executable specifics.	2 / 3
Workflow Clarity	The Phase 1→2→3 sequence and parallel-agent spawn instructions are clear, but there are no integrated validation checkpoints or feedback loops (validate→fix→retry) in the processing workflow; QA standards sit separately rather than as in-flow checkpoints.	2 / 3
Progressive Disclosure	No bundle files exist and the skill is a monolithic single file; although sections are well-organized, content that could be split out (metadata template, filtering guidelines, content-structure template) is all inline with no one-level-deep references.	2 / 3
	Total	8 / 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 it omits an explicit "Use when..." trigger clause and only partially covers natural trigger term variations. Adding trigger guidance and more keyword variations would raise the completeness and trigger scores.

Suggestions

Append an explicit trigger clause, 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."

Broaden trigger terms to include natural variations users say: "meeting transcript", "meeting minutes", "process meeting", "meeting notes".

Consider third-person phrasing consistency (already good) but ensure the description leads with the core action before listing outputs.

Dimension	Reasoning	Score
Specificity	The description names the domain ("meeting recordings and notes") and lists multiple concrete outputs — "structured decisions, action items, and team dynamics with intelligent noise filtering" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	It clearly states what the skill does but lacks any "Use when..." clause or explicit trigger guidance; per the judging guidelines a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	"meeting recordings and notes" are natural terms, but common variations users would say ("meeting transcript", "meeting minutes", "process meeting") are absent, fitting the missing-common-variations anchor.	2 / 3
Distinctiveness Conflict Risk	The meeting-transcript niche with structured-decisions/action-items output is a clear, distinct domain unlikely to trigger for unrelated skills, matching the clear-niche anchor.	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
Commit: 5e9851c

Reviewed: 14 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.