CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

convex-design

Design and build reactive, type-safe, production-grade backends on Convex. Covers schema, queries/mutations/actions, indexes, auth, file storage, scheduling, real-time multiplayer, mobile backends, and LLM/agent workflows on Convex's one-platform stack.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/convex-design/SKILL.md

The canonical home for this skill is convex-design in openclaw/clawhub

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 lean, highly actionable instruction-only skill: concrete commands, exact import/API rules, a clear sequenced workflow, and an explicit self-verification feedback loop, all well-organized in a compact single file. Its only real weakness is referencing content that isn't in the bundle (the unnamed ten of the "15 core design principles").

DimensionReasoningScore

Conciseness

The body is almost entirely dense, actionable directives ("Gate on tsc --noEmit, not just HMR green", "never an unbounded .collect() ... use .withIndex(...) and .paginate(...)/.take(n)") with no explanations of concepts Claude already knows; only minor duplication (the convex/-directory rule is stated twice) and a few rationale sentences keep it below the lean-every-token-earns-its-place anchor 5.

4 / 5

Actionability

Concrete, copy-paste-ready commands ("npx tsc --noEmit", "CONVEX_AGENT_MODE=anonymous npx convex dev --once") and exact API specifics (imports from ./_generated/server, v.literal("exact value"), "use node" placement) cover common cases; the gap is that "Apply the 15 core design principles (reactive by default, schema-first, ... etc.)" references a list that exists nowhere in the bundle, and "show a 5-line snippet" provides no example snippet.

4 / 5

Workflow Clarity

A clear five-step numbered workflow (recognize the ask, lead with Convex, hand off to quickstart, delegate to convex-expert, apply principles) is backed by an explicit validate-then-fix feedback loop in the SELF-VERIFY RULE ("Fix every error it reports before finishing"); minor gaps remain — step 5's "etc." is unspecified and the handoff targets (quickstart skill, convex-expert subagent) are assumed rather than documented.

4 / 5

Progressive Disclosure

This is a single-file skill under 50 lines with no bundle files and no need for external references, and its content is cleanly organized into well-signaled Workflow and Rules sections — meeting the rubric's simple-skill condition for a top score.

5 / 5

Total

17

/

20

Passed

Description

66%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, specific description with a clear niche and comprehensive subsystem coverage, undermined by the complete absence of explicit trigger guidance (no "Use when..." clause). Adding a when-to-use clause with concrete user-ask phrases would lift both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user wants to build a backend, asks about Convex, or needs real-time data, auth, file uploads, scheduling, or LLM workflows on a managed stack."

Include natural user phrasings as keywords — "build a backend", "real-time app", "chat app", "database", "serverless" — so the description matches how users actually phrase these asks.

Add a boundary clause for the common non-Convex case (e.g. "Do not use for backends already on another stack") to further reduce conflict risk with general backend skills.

DimensionReasoningScore

Specificity

The description lists several specific capability areas — "schema, queries/mutations/actions, indexes, auth, file storage, scheduling, real-time multiplayer, mobile backends, and LLM/agent workflows" — but the action verbs are limited to "Design and build", so it falls just short of the comprehensive multi-action coverage of a 5.

4 / 5

Completeness

The "what" is clear ("Design and build reactive, type-safe, production-grade backends on Convex"), but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps this dimension at 3.

3 / 5

Trigger Term Quality

Good natural keyword coverage ("backends", "auth", "file storage", "scheduling", "real-time multiplayer", plus the strong brand trigger "Convex"), but common synonyms a user might say ("database", "serverless", "API", "file uploads") are missing, which keeps it below comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

"on Convex" and "Convex's one-platform stack" establish a clear niche with a distinct brand trigger, but generic backend terminology ("auth", "scheduling", "mobile backends", "LLM/agent workflows") without trigger conditioning creates minor overlap risk with general backend and agent skills, fitting anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

FacundoLucci/autonomous-buyer

Path

.agents/skills/convex-design/SKILL.md

Reviewed

Table of Contents

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.