AD deslop
当文章/文档/分享稿读起来像 AI 写的、充满套话、缺具体细节时使用。中英文反 AI 味两次 pass 重写。 不适用于代码注释和 commit message 的去 AI 味（用 slopbuster --mode code）。参见 doc-gen (用于生成文档)、human-writing (用于项目级中文写作参考)。
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
GeneratorInfrastructureSoftware developmenttype and topics are labelled automatically from the skill text
The same skill appears in 1 more place: ClawHub
How to improve
For the model run — optional
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 46/100
- 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. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (deslop) differs from the folder (deslop-cn)
- 100Tools and files. No external tools needed
- 100Steps. 34 steps
- 100Execution cost. Instruction body is 1794 tokens
- low 15 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
- +2Single-language instructions
- +3Description length 163: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.
External checks
ClawHub: clean
This is a writing-assistant skill that rewrites user-provided prose and does not request execution, credentials, network access, or persistence.
LLM: benign (high) · VirusTotal: · 29 May 2026