convex-quickstart

Get a barebones Convex + web template running from a one-sentence idea.

Quality

64%

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-quickstart/SKILL.md

Quality

Content

75%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 a dense, highly actionable set of Convex-specific rules with a clear workflow and an explicit self-verify feedback loop, well-suited to a single-file skill. The main weakness is presentation: several rules are long run-on sentences crammed into bullets that would be clearer as sub-lists or short examples.

Suggestions

Break the long run-on rules (Data access + imports, HTTP routes) into short sub-bullets or a compact example block so each constraint is scannable.

Inline the SELF-VERIFY step into the Workflow (e.g., add a step 4 'Verify: npx tsc --noEmit …') so the validation checkpoint sits in the sequence rather than only in Rules.

Add one minimal copy-paste convex/*.ts snippet (e.g., a paginated query with .withIndex) to lift actionability from mostly-executable to fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is lean and rule-packed with no padding of concepts Claude already knows; every rule is actionable. Not a 5 because several rules (e.g., the 'Data access + imports' and 'HTTP routes' bullets) are very long run-on sentences that could be tightened into sub-lists; not a 3 because there is no unnecessary explanation.	4 / 5
Actionability	Provides concrete commands ('npx tsc --noEmit', 'CONVEX_AGENT_MODE=anonymous npx convex dev --once') and specific patterns ('api.foo.bar', 'v.literal("exact value")', './_generated/server'). Not a 5 because it gives constraints and snippets rather than a complete copy-paste example covering a common case; not a 3 because the guidance is genuinely executable, not pseudocode.	4 / 5
Workflow Clarity	The 3-step Workflow is clearly sequenced with a CONFIRM checkpoint, and the SELF-VERIFY RULE is an explicit validate→fix→retry feedback loop. Not a 5 because the validation lives in a separate Rules section rather than inline in the workflow, and step 1 delegates opaquely to a recipe; not a 3 because checkpoints and a feedback loop are clearly present.	4 / 5
Progressive Disclosure	Single-file skill (~30 lines) organized into clear Workflow and Rules sections, qualifying for a high score under the simple-skill note; bundle is just assets/icon.svg. Not a 5 because the Rules section is a dense bullet block where some paragraph-length rules could be better sub-structured; not a 3 because structure is genuinely good and content is appropriately placed.	4 / 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 specific and distinctive about its Convex niche, but it lacks an explicit 'Use when…' trigger clause, which caps its completeness. Adding a trigger phrase naming the situations that should invoke it would raise both completeness and trigger-term quality.

Suggestions

Add a 'Use when…' clause naming the situations that should invoke this skill (e.g., 'Use when the user wants to scaffold or stand up a Convex + Next.js app from an idea').

Include natural synonyms users actually say — 'scaffold', 'starter', 'Next.js' — to broaden trigger-term coverage.

Mention 1-2 more concrete outcomes (e.g., 'installs deps and starts local dev servers') to lift specificity from a single action to several.

Dimension	Reasoning	Score
Specificity	Quotes 'Get a barebones Convex + web template running' and 'from a one-sentence idea' — names the domain plus 1-2 concrete actions, but coverage is not comprehensive. Not a 4 because it lists only the single action of standing up/running a template rather than several specific actions.	3 / 5
Completeness	Has a clear 'what' (get a barebones Convex + web template running) but no 'Use when…' or equivalent explicit trigger guidance, so per the guideline completeness is capped at 3. Not a 4 because the 'when' is entirely missing rather than weakly implied.	3 / 5
Trigger Term Quality	Includes relevant keywords ('Convex', 'web template', 'one-sentence idea') a user might say, but misses common synonyms like 'scaffold', 'Next.js', or 'starter'. Not a 4 because natural-term coverage has clear gaps, not a 2 because the terms present are domain-specific rather than generic.	3 / 5
Distinctiveness Conflict Risk	'Convex + web template from a one-sentence idea' carves a clear niche with distinct triggers and minimal conflict risk. Not a 5 because 'web template' is somewhat generic and could overlap with general Next.js scaffolding skills.	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-quickstart/SKILL.md
Commit: f98a436

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.