AB nodejs
Builds, debugs, and hardens Node.js servers, CLIs, and npm packages: async, modules, streams, memory, and process lifecycle. Use when writing or reviewing code that runs on Node, when a process hangs or refuses to exit, leaks memory, gets OOM-killed, pins one CPU core at 100%, or dies on an unhandled rejection; when the error reads EADDRINUSE, EMFILE, ECONNRESET, ERR_MODULE_NOT_FOUND, ERR_REQUIRE_ESM, or "__dirname is not defined"; when import and require interop breaks, streams buffer everything in RAM, a server returns intermittent 502s behind a load balancer, or SIGTERM drops in-flight requests; when npm install, lockfiles, peer dependencies, workspaces, native module builds, or publishing misbehave; when a suite passes locally and fails in CI; or when containerizing, profiling, and shutting down a service cleanly. Not for browser-only JavaScript, TypeScript type-system design, or the Bun and Deno runtimes.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 13 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4177 tokens
- 100Steps. 44 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
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
- +3Description length 923: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.