AC minimal-edit
Apply minimal, tone-preserving edits to existing written text. 对既有文本做最小化局部修改：只动该动的，保持语气、篇幅与结构，不展开、不强调、不标注改动。Use when the user asks to revise, correct, change, delete, soften, reword, or adjust a specific part of an existing Chinese or English document, report, article, prompt, meeting minutes, or message, especially when the edit should not be expanded, emphasized, marked, or look like a patch. 中文触发词：不要展开、不要强调、别把改动标出来、改动处不要标出来、改得自然一点、不要 AI 味、删掉就好、只改观点、改完像伤疤。English triggers: don't expand, don't emphasize, don't mark the change, keep it natural, remove the AI tone, just delete it, change only the opinion. Do not use for full rewrites, repackaging, or net-new writing unless the user explicitly requests a large transformation.
Apply minimal, tone-preserving edits to existing written text.
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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 "display_name" - note
frontmatter-keyunknown frontmatter key "display_name_en"
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 17 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Failures and branches. 4 branches
- 100Steps. 30 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1438 tokens
- 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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 733: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.