BC mode-switch-machine-stack
Use when you toggle VPN, agents and services by hand. One command flips the whole machine stack together — VPN, background agents, local services, model tier — from one YAML mode matrix; the watchdog repairs the current mode and never revives what you switched off (the part most setups get wrong). Use when: (1) You re-toggle the same five things by hand at every work↔game switch (2) A crash-restart must come back as the mode you are in now, not as whatever was running before it (3) Background agents should all run while you work, one or two while you game, none while you render (4) Local services should free their RAM when you need it, not when you remember (5) VPN on for work, off for low-latency gaming — and the agents must stop with it, or they ride the tunnel Python stdlib only — no pip install, no model calls, no API cost; Windows tested. Prove it first: `python templates/modes_switch.py --selftest` builds a fake stack in a temp dir and switches it end to end — your machine untouched. 中文触发:手动切工作/游戏模式太麻烦 / 一条命令切换整机栈 / 分身与本地服务跟着模式起停 / VPN 跟着模式开关 / 看门狗按模式自愈
One command flips the whole machine stack together — VPN, background agents, local services, model tier — from one YAML mode matrix; the watchdog repairs the…
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Shorten the description to 1024 characters.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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
- error
description-longdescription is 1078 chars, limit 1024 - warning
description-long-hermesdescription is 1078 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 4 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 100Steps. 19 steps
- 100Execution cost. Instruction body is 2144 tokens
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 1078: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 11 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.