build-zoom-bot

Use when building bots.

Quality

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/zoom/skills/build-zoom-bot/SKILL.md

Quality

Content

68%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 body is an admirably lean router/index skill: it orients the reader, names the core sub-skills, and surfaces genuinely non-obvious pitfalls (batch vs live transcription, join authority, retry behavior). Its weaknesses are the absence of any executable detail or validation checkpoints in the workflow, and reference links that point to files not present in this bundle with no per-reference guidance on when to consult each.

Suggestions

Add one concrete executable anchor — e.g. a minimal Meeting SDK join snippet or the exact credential/setup prerequisite — so the first step of the workflow is actionable without hopping to another skill.

Annotate each Primary Reference with its purpose and trigger (e.g. 'rtms — live audio/video/transcript streams; use when the bot must react in-meeting') so navigation does not depend on opening every linked file.

Add a verification checkpoint to the workflow (e.g. confirm the bot's join authority and auth model before designing media capture) to close the validation gap in the sequence.

Dimension	Reasoning	Score
Conciseness	The ~35-line body is lean and efficient with no padding: it never explains what a bot or SDK is, and every section (Covers, Workflow, References, Common Mistakes) carries non-obvious information — matching 'every token earns its place'.	5 / 5
Actionability	It names concrete technologies (Meeting SDK, RTMS, REST API, Webhooks) and a decision framework (join/observe/transcribe/summarize/act), but provides no executable steps, commands, endpoints, or specifics on join strategy or auth — 'some concrete guidance but incomplete; missing key details', above anchor 2 because more than high-level hints is given.	3 / 5
Workflow Clarity	The four-step sequence is present and logically ordered (clarify → route → add APIs → surface constraints) but contains no validation checkpoints or feedback loops, matching 'steps listed but validation gaps; checkpoints missing or implicit'. The destructive/batch cap does not apply since this is a design skill.	3 / 5
Progressive Disclosure	Good structure with a clearly signaled, one-level-deep reference list, but the five linked files (../meeting-sdk/SKILL.md etc.) do not exist in this bundle and are listed as bare names without descriptions of what each provides — 'good structure; references mostly clear; minor organization gaps' rather than the fully navigable anchor 5.	4 / 5
	Total	15 / 20 Passed

Description

25%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 is a bare 'when' clause with no 'what': 'Use when building bots.' It fails to convey any capability, omits Zoom-specific trigger terms, and risks firing for any bot-building request. The body of the SKILL.md already contains far better material ('automation that joins meetings, captures media, or reacts to live session data') that should be lifted into the description.

Suggestions

State concrete capabilities in the description, e.g. 'Build Zoom meeting bots that join meetings, capture real-time audio/video and transcripts, and orchestrate storage and post-processing.'

Add natural trigger terms users would actually say: 'meeting bot', 'Zoom bot', 'join meetings programmatically', 'live transcription', 'capture meeting media'.

Tighten distinctiveness by naming the Zoom/Meeting SDK domain explicitly so the skill does not compete with generic Discord/Slack/chatbot builders.

Dimension	Reasoning	Score
Specificity	The description names the domain ('building bots') but contains zero concrete actions or capabilities — no verbs describing what the skill does, matching 'names the domain but actions are minimal or generic' rather than the purely abstract anchor 1.	2 / 5
Completeness	Only 'when' is present ('Use when building bots') with no 'what' at all — an exact match to the anchor-2 example 'Use when working with documents'; score 3 would require a clear statement of what the skill does.	2 / 5
Trigger Term Quality	The single keyword 'bots' is generic and misses every natural phrase a user would say ('Zoom bot', 'meeting bot', 'join meetings', 'transcribe meetings', 'capture audio'), matching 'one or two generic keywords; missing the natural phrases users say'.	2 / 5
Distinctiveness Conflict Risk	'Building bots' would equally trigger Discord, Slack, chatbot, or trading-bot requests — very broad with high overlap risk across many similar skills (anchor 2), though not conflicting with virtually any skill (anchor 1).	2 / 5
	Total	8 / 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
relative_links	Relative link issues: 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/zoom/skills/build-zoom-bot/SKILL.md
Commit: 5fd93af

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.