AB volcengine-deploy
Deploy a local project directory or Git repository to Volcengine as a running, reachable cloud service. USE WHEN: deploy to Volcengine, deploy to 火山引擎/火山, deploy this repo/project, publish current code, launch the app, run it in the cloud, expose it as a service, deploy to ECS/VKE/veFaaS, run on ECS, push to VKE, deploy as serverless/FaaS, or the user wants the agent to choose a Volcengine hosting target. If the user only asks which Volcengine deployment target to choose, use `volcengine-prepare` skill first. Not for creating a single standalone resource — use `volcengine-cli` skill for that.
Deploy a local project directory or Git repository to Volcengine as a running, reachable cloud service.
As a process B 78/100 · Nearly there — weak spots: result and completion, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Dangerous commands
cmd-background-processreferences/ecs-deploy-steps.md:307Starts a background / autostarted processsystemctl enable --now docker
-
low Dangerous commands
cmd-background-processreferences/ecs-deploy-steps.md:375Starts a background / autostarted processsystemctl enable --now $repo_name.service"
-
low Concealment
en-hide-from-userSKILL.md:143Instruction to hide actions from the user (negated — the text forbids it)- On failure, print cleanup commands in reverse ledger order. There is currently no one-command cleanup runner; the user must review and run ledger `delete_command` values manually. Do not silently de
negated
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5089 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 78/100
- 30Running it twice. 99 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 5089 tokens
- 85Steps. 75 steps, 3 vague phrases
- 100When it triggers. States when to use and when not to
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 7 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- -33 of 3 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 599: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 75 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (7 of 8)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.