convex-database

Convex reactive database patterns, schema design, real-time queries, mutations, actions, authentication, migrations, performance optimization, and component creation. Use when designing Convex schemas, writing queries/mutations, managing the Convex backend, setting up auth, migrating data, optimizing performance, or building Convex components.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 high-quality, token-efficient body focused on Convex-specific gotchas and hard limits rather than generic concepts. It is highly actionable and well-structured, with only minor gaps in workflow validation detail and reference depth.

Suggestions

Replace the vague 'verify' step in the Deploy Loop with a concrete checkpoint (e.g., what to check before running `npx convex deploy`).

Add a one-line validation/checkpoint for the cursor-based batch and migration paths, since they are batch/destructive operations.

Briefly expand 'use the migrations component' with the component name or a pointer so the guidance is self-contained.

Dimension	Reasoning	Score
Conciseness	Lean and dense: hard-limit tables and terse rule bullets with no padding, no explaining what a database is, and every line earning its place — assumes Claude's competence throughout.	5 / 5
Actionability	Mostly executable with concrete API references ('api.file.fn', 'ctx.scheduler.runAfter(0, internal.x.batch, { cursor: result.continueCursor })', 'npx convex env set'), but a few items ('use the migrations component', 'compare before ctx.db.patch()') leave minor gaps.	4 / 5
Workflow Clarity	The Deploy Loop gives a clear sequence with an explicit checkpoint table and a rollback feedback loop, but the intermediate 'verify' step is unspecified and the batch/migration paths lack their own validation checkpoints.	4 / 5
Progressive Disclosure	Well-organized into clear sections with a well-signaled one-level-deep reference ([database-config.md]) and an official-docs link at the top; the bulk of rules live appropriately in SKILL.md with only minor room to split advanced detail.	4 / 5
	Total	17 / 20 Passed

Description

100%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 strong, well-targeted description: third-person, comprehensive in named capabilities, and explicit on both what the skill does and when to invoke it. Trigger phrasing is natural and Convex-specific.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'schema design, real-time queries, mutations, actions, authentication, migrations, performance optimization, and component creation' — with comprehensive coverage and no vague filler.	5 / 5
Completeness	Explicitly answers both 'what' (Convex reactive database patterns and the enumerated capabilities) and 'when' via a concrete 'Use when ...' clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would actually say ('writing queries/mutations', 'setting up auth', 'migrating data', 'optimizing performance', 'building Convex components') plus the synonym pair auth/authentication.	5 / 5
Distinctiveness Conflict Risk	Scoped tightly to Convex-specific triggers ('Convex schemas', 'Convex backend', 'Convex components'), giving it a clear niche with minimal overlap risk against generic database skills.	5 / 5
	Total	20 / 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: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: monkilabs/opencastle
Path: src/orchestrator/plugins/convex/SKILL.md
Commit: fa0c341

Reviewed: 5 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.