AF contract-doc-sync
文档同步工具——检测代码-文档漂移并同步修复。仅读写本地 docs/ 下 Markdown 文件，仅运行本地脚本（git diff、md-sections）。 源码文件只读，无网络请求，无加密操作，无支付/购买功能，无远程下载。 需要: python3, git, bash。 写入范围白名单: docs/modules/*.md, docs/architecture/*.md, docs/conventions/*.md。 触发场景： (1) 用户说"同步文档"、"文档同步"、"sync docs" (2) 用户说"检查漂移"、"漂移检测"、"L0" (3) 用户说"快速同步"、"L1" (4) 用户说"深度同步"、"L3" (5) 功能编码完成后，强烈建议执行一次文档同步，确保文档与代码一致 (6) 提交 PR / 合并分支前，建议至少执行 L1 快速同步 (7) 发布前文档一致性检查，建议执行 L3 深度同步 (8) 大规模重构后（API 签名变更、实体字段调整、模块拆分等），文档大概率已漂移 (9) 修改了 controller/service/entity/config 等代码后，对应文档可能需要更新 (10) 任何涉及 docs/ 目录与代码对齐的场景。 未指定级别时默认使用 L2（常用同步）。 English triggers: "sync docs", "doc sync", "check drift", "documentation alignment", "drift detection", "docs out of date", "update docs after coding"
As a process F 37/100 · Will not run — References files that are not bundled: references/*.md
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 7. 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 37/100
- 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
- 20When it triggers. No condition that starts the skill
- 100Steps. 37 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2264 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -233 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 712: enough signal without eating the budget
- +4Structure: 34 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.