AB autopilot
Fully autonomous end-to-end task run with NO human gates — pulls the work item (via the azure-devops or github skill if installed, or takes an inline task description), plans against the real codebase, executes incrementally with per-increment verification, writes and runs tests, code-reviews and fixes blocking findings, then STOPS before any commit/push/PR and delivers an evidence-backed report with every assumption logged. Replaces interactive questions with a documented-assumption protocol; halts only for destructive actions, missing access, or unimplementable specs. Use this skill whenever the user says "autopilot", "/autopilot", "run task <id> autonomously", "work this task end to end without asking", "full autonomy on this", "do the whole task, skip commits and PR", or launches a headless run with a task id — even if they don't explicitly say "autopilot skill". Do not use when the user wants interactive planning gates (use task-executor) or wants commits/PRs created.
As a process B 78/100 · Nearly there — weak spots: result and completion, 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: 2. 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 78/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 18 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 100Tools and files. No external tools needed
- 100Steps. 24 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2524 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 987: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 16 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.