BC dev
Full-stack Convex development guidelines covering React, Vite, TypeScript, mutations, auth, design system, and documentation practices. Use when building features, writing Convex functions, or making code changes in this project.
A Convex dev reference covering React, Vite, and TypeScript workflows. Promises to handle mutations, auth, and design system guidelines. Single file with 789 tokens, no scripts. Quality score 80, process score 52—documentation exists but structure needs work. No critical findings, linter clean. Never ran on models, no sandbox testing.
Basic reference material for Convex projects—instructions without code examples or real-world validation. Install if you already know the framework and just need local conventions. Won't help beginners.
Full-stack Convex development guidelines covering React, Vite, TypeScript, mutations, auth, design system, and documentation practices.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 51 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 789 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 229: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 51 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.