clawhub-convex

Apply ClawHub-specific Convex conventions and route to the right managed Convex skill. Use for any change under convex/, Convex commands or deployment targeting, query performance, migrations, retention, runtime validation, or skill stat reads and writes in the ClawHub repository.

Quality

85%

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

83%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.

An efficient, highly actionable routing skill with concrete commands and named functions throughout. Its main weakness is workflow clarity for destructive/batch operations, where validation is delegated to companion skills rather than expressed as inline checkpoints.

Suggestions

Add an explicit inline validation checkpoint for destructive/batch workflows (e.g. after a migration backfill, run `bunx convex logs --failure` / `bunx convex insights --details` and confirm before proceeding) rather than only delegating validation to companion skills.

For the production deploy sequence, state the pre/post verification steps inline (push -> verify -> deploy -> re-verify) so the workflow_clarity cap lifts.

Consider moving the hot-path conventions list and skill-stat compatibility table into a referenced companion file to keep SKILL.md a pure overview and raise progressive_disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense with repo-specific actionable guidance; it never explains what Convex is or how libraries work, assuming Claude's competence. Every section earns its tokens. Not below 5 — no padding detected.	5 / 5
Actionability	Provides fully executable commands (e.g. `bunx convex dev --once`, `bunx convex deploy -y`, `bunx convex codegen`, `bunx convex insights --details`), exact import paths, and named functions (`readCanonicalStat()`, `applySkillStatDeltas()`, `digestToOwnerInfo(digest)`) covering the common cases.	5 / 5
Workflow Clarity	A clear "Start Here" routing sequence exists and testing lists real-path verification options, but destructive/batch operations (migrations, backfills, deploys) delegate validation to companion skills rather than providing inline validate-fix-retry checkpoints, which caps this dimension. Not a 4 because the validation checkpoints for risky ops are implicit/delegated rather than explicit.	3 / 5
Progressive Disclosure	Well-organized single-file overview with clear section headers and explicit one-level routing to companion skills (e.g. `convex-performance-audit`, `convex-migration-helper`). No bundle files exist and no nested references appear. Not a 5 because some inlined detail (hot-path conventions, the skill-stat table) could arguably live in a companion reference.	4 / 5
	Total	17 / 20 Passed

Description

87%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 that clearly states what the skill does, when to use it, and scopes itself to a specific repository niche. It is concise, third-person, and rich in concrete trigger terms with low conflict risk.

Dimension	Reasoning	Score
Specificity	"Apply ClawHub-specific Convex conventions and route to the right managed Convex skill" names the domain plus several concrete trigger domains (convex/ changes, commands/deployment, query performance, migrations, retention, runtime validation, skill stat reads/writes), with only minor coverage gaps. Not a 5 because the actual action verbs are limited to two (apply conventions, route).	4 / 5
Completeness	Explicitly answers both what ("Apply ClawHub-specific Convex conventions and route to the right managed Convex skill") and when ("Use for any change under convex/, Convex commands or deployment targeting...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms a ClawHub user would say are well covered — "Convex", "convex/", "migrations", "retention", "query performance", "deployment", "runtime validation", "skill stat reads and writes" — with a few natural synonyms missing. Not a 5 because it lacks common phrasings like "backfill" or file extensions a user might mention.	4 / 5
Distinctiveness Conflict Risk	Clear niche scoped to the ClawHub Convex repository with distinct triggers and explicit routing to companion skills, giving minimal conflict risk with other skills.	5 / 5
	Total	18 / 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/clawhub-convex/SKILL.md
Commit: 694ff71

Reviewed: 1 day 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.