AC official-document-skill
Draft, revise, polish, humanize, and quality-check Chinese official documents and government-style practical writing (公文、党政机关公文、事务文书、申论应用文、人民日报风格政务表达), producing deliverable drafts with correct document type, format, restrained institutional tone, concrete facts, People's Daily-inspired expression discipline, humanizer-style AI-pattern cleanup, and reduced AI-flavored phrasing. Use when the user asks for 通知、通报、报告、请示、批复、函、纪要、决定、通告、议案、倡议书、工作方案、工作计划、工作总结、简报、讲话稿、发言稿、汇报材料、调研报告、宣传稿、公开信、感谢信、信访回复、理论评论、政策解读, or asks to 一键生成/润色/改写/降AI味/减少AI味/人味/自然表达/人民日报风格/检查格式/生成可交付公文.
As a process C 60/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6393 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 60/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 18 mutating operations with no state check
- 40Consistency. Frontmatter name (official-document-skill) differs from the folder (document-skill)
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 7 branches
- 70Execution cost. Instruction body is 6393 tokens
- 85Steps. 155 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 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)
- +1No license
- +2Single-language instructions
- +3Description length 566: enough signal without eating the budget
- +4Structure: 59 headings
- +3Step-by-step instructions: 155 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.