CF kingdoc
金山文档 AI 协作助手 — 6 品类在线文档全生命周期管理 （文字/电子表格/演示文稿/多维表格/收集表/附件），覆盖创建、编辑、 管理、权限、版本历史、回收站全链路。对标腾讯文档、覆盖其全部 8 大功能。 额外支持：回收站、版本历史、格式转换、纯文本提取、通知推送、 多维表格 Webhook、批量异步任务。
金山文档 AI 协作助手 — 6 品类在线文档全生命周期管理 （文字/电子表格/演示文稿/多维表格/收集表/附件），覆盖创建、编辑、 管理、权限、版本历史、回收站全链路。对标腾讯文档、覆盖其全部 8 大功能。 额外支持：回收站、版本历史、格式转换、纯文本提取、通知推送、 多维表格 Webhook、批量异步任务。
As a process F 28/100 · Will not run — References files that are not bundled: references/et_references.md, references/office_references.md, references/rate_limit.md
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Dangerous commands
cmd-execpolicy-bypassREADME.md:22Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File D:\skill\kingdoc\setup.ps1
-
medium Dangerous commands
cmd-execpolicy-bypassSKILL.md:46Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File setup.ps1
-
medium Dangerous commands
cmd-execpolicy-bypassSKILL.md:375Runs PowerShell with execution policy bypassedpowershell -ExecutionPolicy Bypass -File setup.ps1
-
low Dangerous commands
cmd-execpolicy-bypasssetup.ps1:2Runs PowerShell with execution policy bypassed (code comment)# 用法: powershell -ExecutionPolicy Bypass -File setup.ps1
comment
Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 157 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - warning
missing-refreference to a missing file: references/et_references.md - warning
missing-refreference to a missing file: references/office_references.md - warning
missing-refreference to a missing file: references/rate_limit.md - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "description_zh" - note
frontmatter-keyunknown frontmatter key "requires_api_key"
Process rating: all ten parameters 28/100
- 0Tools and files. 3 referenced file(s) missing: references/et_references.md, references/office_references.md, references/rate_limit.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. 10 mutating operations with no state check
- 40Consistency. Frontmatter name (kingdoc) differs from the folder (kingdoc-2-1-0)
- 100Steps. 44 steps
- 100Execution cost. Instruction body is 2263 tokens
- low 14 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -273 emoji in the instructions: noise for the model
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 156: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 44 items
- +4Has examples (13 code blocks)
- +4Reference files are cited in the instructions (3 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 51.