Name: convex
Rating: 59.2 (1 reviews)
Author: administrakt0r

convex

Convex reactive backend expert: schema design, TypeScript functions, real-time subscriptions, auth, file storage, scheduling, and deployment.

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/convex/SKILL.md

The canonical home for this skill is convex in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

65%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 highly actionable with comprehensive executable examples, but it is a monolithic inlined reference that lacks validation feedback loops for risky database operations and does not progressively disclose content into separate files. Splitting framework integrations into reference files and adding explicit validation steps would lift the lowest dimensions.

Suggestions

Move the per-framework client integrations (Angular, Clerk, Better Auth, Convex Auth) and the validator-types table into separate reference files under references/, keeping only the core query/mutation/action pattern inline.

Add explicit validation checkpoints to destructive or database-affecting workflows — e.g. after `npx convex dev` confirm the deployment synced, and after schema changes run `npx convex dev` to validate against existing data before proceeding.

Trim the opening 'You are an expert in Convex…' paragraph and consolidate the Best Practices / Anti-Patterns / Common Pitfalls sections to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	Most content is genuinely Convex-specific reference material, but the opening 'You are an expert in Convex…' paragraph and the lengthy inlined body (emoji Best Practices, full integration code for every framework) are padding that could be trimmed; it is mostly efficient but could be tightened.	3 / 5
Actionability	The body provides fully executable, copy-paste-ready TypeScript examples and CLI commands covering the common cases — queries, mutations, actions, HTTP webhooks, auth variants, file storage, scheduling, and cron — matching the 'fully executable, copy-paste ready' anchor.	5 / 5
Workflow Clarity	A setup sequence exists (create-next-app → install → convex dev, with numbered sub-steps), but there are no explicit validation checkpoints or validate→fix→retry feedback loops for the database/destructive operations this skill covers; per the guideline, missing feedback loops for db operations caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Sections are well-organized with clear headers, but no bundle files exist and large reference blocks (Angular/Clerk/Better-Auth integrations, the validator-types table) are inlined in SKILL.md rather than split into one-level-deep reference files, so content that should be separate is inline.	3 / 5
	Total	14 / 20 Passed

Description

75%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 specific and clearly distinct, but it states only what the skill does without any explicit 'when to use' trigger guidance, which caps its completeness. Adding a 'Use when…' clause would lift the weakest dimension.

Suggestions

Append an explicit 'when' clause, e.g. 'Use when building or debugging an app on the Convex backend, or when the user mentions Convex, reactive backends, Convex queries/mutations, or Convex Auth.'

Add user-natural synonyms to broaden trigger coverage: queries, mutations, actions, cron jobs, real-time data, and Convex CLI/deploy workflows.

Keep the third-person, capability-list style but pair each capability cluster with a trigger phrase to satisfy both 'what' and 'when' simultaneously.

Dimension	Reasoning	Score
Specificity	The description lists multiple specific concrete actions — 'schema design, TypeScript functions, real-time subscriptions, auth, file storage, scheduling, and deployment' — giving comprehensive coverage of the platform's capabilities.	5 / 5
Completeness	It clearly answers 'what' via the enumerated capabilities, but there is no 'Use when…' clause or equivalent explicit trigger guidance answering 'when'; per the judging guidelines a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Good keyword coverage a Convex user would naturally say (Convex, reactive backend, schema design, real-time subscriptions, auth, scheduling, deployment), but it misses common synonyms and variations users mention such as queries, mutations, cron, and real-time data.	4 / 5
Distinctiveness Conflict Risk	It names a specific platform ('Convex reactive backend') with a distinct niche and Convex-specific capability list, giving minimal conflict risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (798 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/convex/SKILL.md
Commit: 57c135b

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.