AB cursor-agent
Run Cursor Agent CLI for coding tasks — writing, editing, refactoring, reviewing, or planning code — without spending OpenClaw API credits. Use when the user asks to write/fix/refactor/review code, a coding task would otherwise be done inline with Sonnet/Haiku, the user says "do this in cursor" or "use cursor for this", or any substantial file-editing task in a known repo. NOT for conversational questions about code (answer inline) or tiny one-liners that don't warrant a subprocess.
As a process B 66/100 · Nearly there — weak spots: failures and branches, consistency, 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: 5. 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 66/100
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 6 mutating operations with no state check
- 40Consistency. Frontmatter name (cursor-agent) differs from the folder (cursor-agent-openclaw)
- 60Tools and files. Uses tools (git) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 16 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 827 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (4 tags): a typed call is more reliable
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
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 487: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 16 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 100.