convex-agent

Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.

Quality

70%

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 ./.agents/skills/convex-agent/SKILL.md

Quality

Content

72%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 concise and well-structured with a clear sequenced workflow, but it lacks executable code examples and validation checkpoints for the destructive/batch-style operations it describes.

Suggestions

Add one complete, copy-paste code example for the common case (e.g. defining an agent with convexGateway and creating a streaming thread) so the guidance is executable, not just described.

Insert validation checkpoints in the workflow, e.g. after embedding docs confirm the vector index is populated and after defining the agent verify a streamed message returns.

Provide a minimal convex.config.ts snippet showing how to add the agent component, since step 1 references it but gives no example.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient — a short summary, five terse steps, and four rules — with no padding and no explanation of concepts Claude already knows.	5 / 5
Actionability	Provides concrete specifics (package names, convexGateway config fragment, 'env' micro power, 'use node') but includes no complete copy-paste executable code examples, only an inline fragment and prose steps.	3 / 5
Workflow Clarity	Five well-sequenced steps with a clear conditional fallback, but operations like embedding docs into a vector index and persisting threads have no validation/verification checkpoints, which caps this at 3.	3 / 5
Progressive Disclosure	A single-file, under-50-line skill with no external bundle files, cleanly organized into summary, Workflow, and Rules sections — meeting the simple-skill exception for a 5.	5 / 5
	Total	16 / 20 Passed

Description

53%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 clear and reasonably specific about adding an AI agent/RAG backend to a Convex app, with a named package. Its main weakness is the absence of any explicit trigger guidance ('Use when...') and limited natural-language trigger terms.

Suggestions

Add a 'Use when...' clause with concrete natural-language triggers, e.g. 'Use when adding an AI agent, chatbot, or RAG backend to a Convex app.'

Expand the action list beyond the single verb 'Add' to specific concrete actions (define agents, create durable threads, persist message history, embed docs for vector search).

Include common synonyms users say ('chatbot', 'assistant', 'embed documents', 'vector search') to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (AI agent/RAG backend) and the concrete package (@convex-dev/agent) but lists only the single high-level action 'Add' rather than enumerating several specific concrete actions.	3 / 5
Completeness	Clearly states what the skill does but provides no explicit 'Use when...' trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant domain terms ('AI agent', 'RAG backend', 'Convex app', '@convex-dev/agent') but leans technical and misses common natural phrasings and synonyms a user would say.	3 / 5
Distinctiveness Conflict Risk	Tied to a specific package and framework giving it a clear niche with minor overlap risk against general agent/RAG skills, but lacks explicit distinct trigger phrasing needed for a 5.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openclaw/clawhub
Path: .agents/skills/convex-agent/SKILL.md
Commit: 0180b56

Reviewed: 3 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.