CtrlK
BlogDocsLog inGet started
Tessl Logo

scribe

Use when using Scribe.

36

Quality

32%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/zoom/skills/scribe/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The body is commendably concise and provides a clean high-level workflow, but it lacks concrete executable guidance and validation feedback loops, and its reference list is misaligned with the actual bundle (most referenced paths are missing). It is a solid skeleton that needs actionable detail and a repaired reference map.

Suggestions

Add at least one minimal executable transcription request/parser snippet (e.g. a Node fetch example) so the guidance is copy-paste ready instead of descriptive.

Insert an explicit validation checkpoint in the workflow (e.g. 'Confirm webhook signature and 2xx delivery before persisting; retry on timeout') to add a feedback loop for the batch pipeline.

Reconcile the References list with the actual bundle: link the existing references/ files (environment-variables.md, samples-validation.md, versioning-and-drift.md) and remove or create the missing concepts/, scenarios/, examples/, and troubleshooting/ paths.

DimensionReasoningScore

Conciseness

The body is a lean ~25 lines with no padding and no explanation of concepts Claude already knows; every line (workflow steps, reference list) earns its place, matching the 'lean and efficient' anchor.

3 / 3

Actionability

The workflow describes rather than instructs — phrases like 'Set up Build-platform credentials and JWT handling' and 'Design ingestion, chunking, retries' give no executable code or commands, fitting the 'some guidance but incomplete' anchor rather than the copy-paste-ready level-3 anchor.

2 / 3

Workflow Clarity

A clear five-step sequence is present, but there are no explicit validation checkpoints or validate→fix→retry feedback loops; for a batch/webhook pipeline the rubric caps such workflows at 2, and step 5 is a debug checklist rather than a recovery loop.

2 / 3

Progressive Disclosure

The body signals one-level-deep references clearly, but 5 of the 7 referenced files (concepts/, scenarios/, examples/, troubleshooting/) do not exist on disk while 3 actual references/ files are never linked, so navigation is partly broken — matching the 'some structure but could be better organized' anchor.

2 / 3

Total

9

/

12

Passed

Description

0%

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 effectively a placeholder — it restates the skill name in a tautological trigger and conveys no capabilities, natural keywords, or distinctiveness. Every dimension scores at the floor because nothing concrete is explicitly stated.

Suggestions

Replace 'Use when using Scribe.' with concrete actions, e.g. 'Transcribe uploaded or stored media via Zoom AI Services Scribe, parse transcripts, and wire up webhook-based batch pipelines.'

Add a real trigger clause: 'Use when the user needs to transcribe a recorded Zoom meeting, media file, or stored audio/video for transcription or downstream AI workflows.'

Disambiguate from live options: mention 'for recorded/asynchronous media, not live meetings' to reduce conflict with RTMS or Meeting SDK skills.

DimensionReasoningScore

Specificity

The phrase "using Scribe" names no concrete actions or capabilities — it merely restates the skill's own name, matching the 'Vague or no actions; abstract language' anchor rather than the level-2 anchor that names a domain and some actions.

1 / 3

Completeness

Neither the 'what' (no capabilities stated beyond the name) nor the 'when' (the trigger is circular) is meaningfully answered, so it falls below the level-2 anchor that at least has a clear 'what'.

1 / 3

Trigger Term Quality

The only keyword is "Scribe" inside a tautological "Use when using Scribe" clause, offering no natural user-facing variations; this is closer to the jargon/generic anchor than the 'some relevant keywords' anchor.

1 / 3

Distinctiveness Conflict Risk

"Scribe" alone is a generic, overloaded term with no distinct triggers, so it would conflict with other skills rather than occupying a clear niche as the level-3 anchor requires.

1 / 3

Total

4

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 5 missing

Warning

Total

15

/

16

Passed

Repository
openai/plugins
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.