AD skill-regression
Regression testing framework for AgentSkills. Analyzes a target skill, runs script-layer assertions and AI-layer semantic scoring, and outputs a Markdown report. Supports two backends: OpenAI-compatible LLM (default, works anywhere) or OpenClaw cron-based agent trigger (auto-detected if openclaw CLI present). Use when the user asks to "test a skill", "regression test xxx skill", "run skill QA", or "audit my skill against test cases". Requires SR_LLM_API_KEY env var or interactive setup; supports .env files.
Regression testing framework for AgentSkills.
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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: 15. 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 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 25 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1849 tokens
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
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 4 example trigger phrases
- +3Description length 512: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 10 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.