AF marketing-site-dev
Opinionated end-to-end workflow for shipping a bilingual (中文/English) static company marketing site to Volcengine — Astro 6 + React 19 islands + Tailwind 4, deployed to TOS + CDN with HTTPS, force-redirect, HSTS, and HTTP/2, entirely via the `ve` CLI and Node SDKs. Use whenever the user mentions building, scaffolding, deploying, or updating a company / brand / product / 公司官网 / 营销网站 / 品牌站 / marketing site, ESPECIALLY when Volcengine (火山引擎), TOS, CDN, ICP 备案, or Chinese deployment is involved. Also trigger when the user provides a company brief with product list + brand assets and asks for a "single command deploy" or "production-ready landing page", or references files like `astro.config.mjs`, `deploy.config.mjs`, `scripts/cdn-setup.mjs`, `scripts/setup-bucket.mjs`. Prefer this skill over generic web-dev guidance whenever the target deployment is Volcengine + China mainland.
As a process F 48/100 · Will not run — References files that are not bundled: assets/templates/BrandMark.astro, assets/logo/svg/Tenshow_short1.svg, scripts/cdn-payloads/
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: assets/templates/BrandMark.astro - warning
missing-refreference to a missing file: assets/logo/svg/Tenshow_short1.svg - warning
missing-refreference to a missing file: scripts/cdn-payloads/ - warning
missing-refreference to a missing file: scripts/cdn-payloads/apex.json
Process rating: all ten parameters 48/100
- 0Tools and files. 4 referenced file(s) missing: assets/templates/BrandMark.astro, assets/logo/svg/Tenshow_short1.svg, scripts/cdn-payloads/
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 9 branches
- 85Steps. 45 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3791 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +3Description length 886: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Structure: 16 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.