convex-create-component

Builds reusable Convex components with isolated tables and app-facing APIs. Use for new components, reusable backend modules, integrations, or component boundary work.

Quality

90%

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

Quality

Content

92%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.

Excellent skill body: complete executable code for the default local-component path, a validated workflow with feedback loops, and clean one-level-deep progressive disclosure into real reference files. The only weakness is mild structural redundancy — the wrapper example, some Critical Rules, and the checklist repeat content — which costs a little token efficiency.

Suggestions

Drop the duplicated app-wrapper example (the Patterns "Client-facing API" good example repeats the Component Skeleton's sendNotification verbatim) and reference one from the other.

Let the Patterns section carry the code illustrations for auth/env and boundary IDs, and trim the corresponding Critical Rules to one-line pointers to avoid stating each rule twice.

Dimension	Reasoning	Score
Conciseness	The body is dense and fluff-free with no explanations of concepts Claude already knows, but the app-side wrapper code appears verbatim twice, the Patterns section re-illustrates Critical Rules prose, and the checklist restates the workflow — minor redundancy that could be trimmed.	4 / 5
Actionability	Fully executable skeletons cover component config, schema, functions, app wiring, and app-side wrappers, plus exact validation commands ("npx convex codegen --component-dir convex/components/<name>") — copy-paste ready and covering the common local-component case.	5 / 5
Workflow Clarity	A clearly sequenced 10-step workflow is followed by an ordered validation fallback chain (codegen --component-dir, codegen, dev), explicit error-recovery guidance ("stop and ask the user for that exact step instead of guessing"), and a closing checklist.	5 / 5
Progressive Disclosure	Four real reference files (all verified to exist) are one level deep and well-signaled: a goal-to-reference decision table, "Read exactly one reference file" instruction, a Reference Files section, and a clearly scoped advanced-patterns pointer.	5 / 5
	Total	19 / 20 Passed

Description

82%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 description: third-person voice, concrete what-and-when structure, and explicit trigger guidance. The only gaps are a couple of missing natural synonyms (publishing/npm package) and only two concrete capability specifics, which keep specificity and trigger coverage just below top marks.

Suggestions

Add one or two more concrete capabilities (e.g., schema definition, app.use wiring) to lift specificity from naming the domain to listing several specific actions.

Include natural synonyms users would say such as "npm package", "publish a component", or "shared Convex library" to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Builds reusable Convex components with isolated tables and app-facing APIs" names the domain plus two concrete capability aspects, matching the 1-2-concrete-actions anchor rather than the 'several specific actions' level above.	3 / 5
Completeness	The description explicitly answers both what ("Builds reusable Convex components with isolated tables and app-facing APIs") and when ("Use for new components, reusable backend modules, integrations, or component boundary work") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Triggers like "new components", "reusable backend modules", "integrations", and "component boundary work" are natural user phrasing, but common synonyms such as "npm package", "publishing", or "shared library" are missing.	4 / 5
Distinctiveness Conflict Risk	"Convex components" is a clear niche with domain-anchored triggers; the when-clause conditions (component boundary work, reusable backend modules) are specific enough that conflict with unrelated skills is minimal.	5 / 5
	Total	17 / 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-create-component/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.