AC post-dev-verification
Post-development full-stack verification skill. Automatically triggered after Agent completes a development task. Executes production-level validation (unit + integration + E2E) with real-execution-first philosophy. Use when: (1) Development task is complete and needs verification, (2) User says "run tests", "verify", "validate", "quality check", (3) User says "交付", "验证", "跑测试", "质量检查", "验收", (4) Before creating PRs or merging code, (5) After implementing features, bug fixes, or refactoring, (6) User asks "does this work?", "can we ship this?", "is this ready?". Covers: test design (MFT/INV/DIR taxonomy), quality metrics (4 layers, 15 metrics), feedback-driven fix loop, anti-pattern detection, visible/hidden test separation, reusable test script generation.
As a process C 60/100 · Has gaps — weak spots: result and completion, when it triggers, 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 60/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 5 branches
- 70Execution cost. Instruction body is 4037 tokens
- 85Steps. 80 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 767: enough signal without eating the budget
- +4Structure: 36 headings
- +3Step-by-step instructions: 80 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.