AB supercoder
Trigger when the user provides a requirement, PRD, specification, or feature request and wants it analyzed and implemented against the codebase. Use when the user asks to "implement a feature," "build this," "review a spec," "analyze requirements," "plan implementation," "assess feasibility," or provides a PRD/spec and expects end-to-end delivery. DO NOT TRIGGER for bug fixes, refactoring, code explanation, single-file edits, or questions about existing code.
As a process B 69/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
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
- 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-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Agent AskUserQuestion TaskCreate TaskUpdate Read Write Edit Bash Glob Grep LSP WebFetch
Files scanned: 8. 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 69/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 716 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 463: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.