AB migration-planner
Use when planning the migration of a legacy system or monolith — analyzes the source codebase (current repo, or a repo URL cloned to a temp dir) and produces an evidence-based Strangler Fig migration plan with per-domain SPECs. Default target is .NET (Blazor WebAssembly, .NET MAUI, ASP.NET Core); other stacks allowed by user decision. Do NOT use to implement code or when approved SPECs already cover the migration.
Use when planning the migration of a legacy system or monolith — analyzes the source codebase (current repo, or a repo URL cloned to a temp dir) and produces…
As a process B 77/100 · Nearly there — weak spots: 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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 4, 14, 27, 28, 49, 55): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 77/100
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web, git) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4959 tokens
- 100Steps. 76 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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
- +5Description has no quoted example phrases that should trigger the skill
- -5TODO / placeholder text left in the skill
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 417: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 76 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.