AC download-guard
AI Agent download guard (Windows only). Auto-activates on: download, install, git clone, pip install, npm install -g, pnpm add -g, bun install -g, conda install, cargo install, go install, uv pip install, docker pull, ollama pull, huggingface-cli download, winget/choco/scoop install, curl/wget. Checks disk space, validates path availability, logs every download, prevents C-drive fill-up and broken-path fallback. Use when: user runs pip install, npm install -g, git clone, docker pull, ollama pull, cargo install, go install, or any download/install command. Also use when user asks "where did it download", "disk space", "download log", "scan cache", "migrate cache". NOT for: managing already-installed applications, uninstalling programs, or non-download file operations. Say "download guard" / "download guard status" / "where did it download" / "disk space" / "download guard version". 当用户说"下载/安装/克隆/拉取模型/pull镜像/磁盘空间/下载到哪/下载版本"时自动激活。
AI Agent download guard (Windows only).
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions
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 "slug" - note
frontmatter-keyunknown frontmatter key "triggers" - note
frontmatter-keyunknown frontmatter key "agent_created" - note
frontmatter-keyunknown frontmatter key "platform"
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, read, web, git, python, node) that frontmatter does not declare
- 85Steps. 55 steps, 2 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2670 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- 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
- +3Description length 941: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 24 headings
- +3Step-by-step instructions: 55 items
- +4Has examples (12 code blocks)
- +3All 4 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.