BB Go
Writes, debugs, and reviews Go: goroutine leaks, data races, nil interfaces, slices and maps, go.mod, and net/http. Use when Go panics or misbehaves — "all goroutines are asleep - deadlock!", "concurrent map writes", "send on closed channel", "assignment to entry in nil map", or a WARNING: DATA RACE from `go test -race`; when a goroutine, timer, or connection leaks and memory climbs; when a service hangs for want of a timeout; when errors.Is or errors.As stops matching after a %v wrap; when a slice mutates its parent, a map iterates in a new order, or a typed nil returned as error compares non-nil; when go.mod, go.sum, workspaces, replace, or a /v2 path fight over dependencies; when cross-compiling, cgo, build tags, go:embed, or a static container binary fail; when tests are flaky under -race or -parallel or benchmarks lie; when GOGC, GOMEMLIMIT, GOMAXPROCS, or escape analysis need tuning; or when writing handlers, CLIs, database access, or generics. Not for Kubernetes operators or framework internals.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-agent-memory-dumpmemory.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensmemory.md
Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 5704 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "changelog" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 22 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5704 tokens
- 100Steps. 44 steps
- 100Failures and branches. 2 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 11 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
- +3Description length 1017: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 11 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.