DF siluzan-cso
丝路赞内容运营平台（CSO）。**凡涉及以下任一类业务，必须先加载并使用本 skill**。 (1) **文案生成与改稿**：选题、爆款拆解、新写成稿（公众号、小红书、**视频口播/字幕/配音/分镜脚本**、博客、改稿润色、评论区回复等）须走 `three-lib-content-workflow/content-writer.workflow.md`；**热点/资讯生成选题**见 `topic-selection.md`；**单轨 / 多轨**（多轨默认 2 篇、可增减，可主动推断）见 `multi-track.md`；**禁止**直接成稿或聊天润色。 **视频脚本 vs 发布 Caption**：口播/字幕/分镜走 content-writer；上传发布框 Caption 走 `overseas-b2b-social-post`。 (2) **人设管理**：运营账号人设卡（styleGuide）；反推/查询/保存。 (3) **发布与运营**（YouTube/TikTok/Instagram/LinkedIn/X/Facebook）：OAuth、**账号分组**、发布、任务/重试、upload、**extract-cover**、planning、报表。 (4) **RAG 知识库**：品牌/产品问答与写稿事实依据。 **海外 B2B 社媒贴文/Caption**：走独立 skill `overseas-b2b-social-post`，不在本 skill 文案流程内。 **高频误路由**：写文案禁联网代替 rag query；发布/截封面须调 CLI。 **账号不明先问**：仅运营媒体账号；广告账户走 siluzan-tso。
As a process F 31/100 · Will not run — References files that are not bundled: references/*.md
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 5
-
high Dangerous commands
cmd-pipe-to-shellscripts/install.sh:61Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://install-node.vercel.app/lts | bash -s -- --yes
-
high Dangerous commands
cmd-pipe-to-shellscripts/install.sh:75Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://install-node.vercel.app/lts | bash -s -- --yes
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:53Downloads and executes remote code from an unrecognised host (pipe to shell)bash <(curl -fsSL https://unpkg.com/siluzan-cso-cli@latest/dist/skill/scripts/install.sh)
Medium and low: 2
-
low Secrets in code
secret-password-literalreferences/setup.md:128Hard-coded password / key literal (may be an example)apiKey : abcd****1234
-
low Dangerous commands
cmd-pipe-to-shellscripts/install.ps1:91Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment; quoted — discussed, not commanded)# (`bash <(curl -fsSL .../install.sh)`) when the PowerShell channel misbehaves.
commentquoted
Files scanned: 42. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: references/*.md
Process rating: all ten parameters 31/100
- 0Tools and files. 1 referenced file(s) missing: references/*.md
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 9 mutating operations with no state check
- 70Execution cost. Instruction body is 4200 tokens
- 100Steps. 41 steps
- 100Consistency. Name and required fields are in place
- low 14 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 728: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (14 of 14)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.