CtrlK
BlogDocsLog inGet started
Tessl Logo

meeting-summarizer

Use this skill when the user has a meeting recording, transcript, or notes and wants a structured summary with action items, decisions, and follow-ups.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A code-forward, highly actionable skill body that covers the full pipeline with executable examples and clean sectioning. Its main weakness is the absence of explicit validation/error-handling checkpoints in the workflow.

Suggestions

Add a validation/error-handling step in the pipeline (e.g., warn or branch when the transcript exceeds the 6000-character cap, and handle Whisper transcription failures).

Optionally move the longer code blocks into a scripts/ bundle and reference them from SKILL.md to deepen progressive disclosure now that the body exceeds 50 lines.

Tighten the Quick Reference table or merge it into the Full Pipeline section to remove minor redundancy with the preceding code.

DimensionReasoningScore

Conciseness

The body is lean and mostly code with a one-sentence overview and minimal commentary, assuming Claude's competence; only minor trimming opportunities exist (e.g., the Quick Reference table partially restates the pipeline).

4 / 5

Actionability

Provides fully executable, copy-paste-ready Python for transcription, summarization via the Anthropic tool-use API, Markdown formatting, and a complete end-to-end pipeline with a concrete usage example covering the common cases.

5 / 5

Workflow Clarity

The transcribe → summarize → format sequence is clearly shown in the Full Pipeline section, but there are no explicit validation or error-handling checkpoints (e.g., silent transcript[:6000] truncation, transcription failure), representing minor validation gaps.

4 / 5

Progressive Disclosure

Content is well-organized into clearly labeled sections (Overview, Transcribe, Summarize, Format, Full Pipeline, Quick Reference) in a single self-contained file with no nested references; no bundle files are present or needed, though the ~150-line body could optionally split scripts out.

4 / 5

Total

17

/

20

Passed

Description

83%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.

A well-crafted description that clearly states both capability and trigger conditions using natural, user-facing language. It is specific and distinctive with only minor gaps in action coverage and synonym breadth.

DimensionReasoningScore

Specificity

Names the meeting-summary domain plus several concrete outputs ("action items, decisions, and follow-ups") alongside "structured summary", but does not enumerate the processing actions themselves, leaving minor gaps relative to a fully comprehensive listing.

4 / 5

Completeness

Explicitly answers both what ("structured summary with action items, decisions, and follow-ups") and when ("Use this skill when the user has a meeting recording, transcript, or notes and wants...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user-facing terms ("meeting recording, transcript, or notes", "action items", "decisions", "follow-ups") with good coverage, though a few common synonyms such as "meeting minutes" are absent.

4 / 5

Distinctiveness Conflict Risk

The meeting-summarization niche is clearly delineated by distinct triggers ("meeting recording, transcript, or notes"), with only minor overlap risk against generic summarization or note-taking skills.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ProwlrBot/prowlr-marketplace
Reviewed

Table of Contents

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.