AB undo
File edit time machine for AI agents. Automatically snapshot file changes after every Write, Edit, or Shell operation, and provide undo/revert capabilities to any previous state. Supports: undo last change, undo N steps, undo to timestamp, undo to named checkpoint, list change history, and create checkpoints. Use this skill after the user says "track changes", "enable undo", or when they want to safely experiment with file edits. Also activates automatically when the user asks to "undo", "revert", "go back", "restore", or "show history" of file changes.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
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: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 14 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1813 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)
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 559: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 14 items
- +3Output format is stated explicitly
- +4Has examples (19 code blocks)
- +3All 6 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.