AB skill-build-wizard
End-to-end guided workflow for building production-quality agent skills. Walks users through 4 stages: pre-flight checks → spec confirmation (3 musts) → coding quality acceptance (4 checks) → release prep (5 requirements). Use when the user says "create a skill", "build a skill", "write an agent skill", "skill-build-wizard", "做个 skill", "帮我创建一个 skill", "skill 全流程向导". Calls skill-creator for actual scaffolding and routes to glic-check / skill-release-audit / skill-release-plus / skill-regression for verification and release. Not for: just writing one quick skill file (use skill-creator directly); just publishing an already-finished skill (use skill-release-plus).
End-to-end guided workflow for building production-quality agent skills.
As a process B 71/100 · 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: 7. 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 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 11 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50Failures and branches. 0 branches, has a failure section
- 85Steps. 50 steps, 3 vague phrases
- 100Tools and files. No external tools needed
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2179 tokens
- 100Progress reporting. Reports progress
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
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 670: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 50 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.