将文档影响判定细化为逐页逐段的同步执行任务清单
该技能材料显示其本质上是一个开源的 prompt-only 文档规划技能,未声明密钥、远程端点或可执行组件,整体风险较低。需注意其设计上会处理 PR diff 与文档内容,但从现有材料看未体现独立的数据外发、代码执行或过度授权红旗。
材料明确标注“无”密钥/环境变量,README 也未要求 API token、账户凭证或外部服务认证;未见明显凭证收集、存储或滥用路径。
材料明确标注无远程端点;作为 prompt-only 技能,文档中未声明会把 PR diff、页面内容或其他用户数据发送到外部主机,未见具体数据外发红旗。
现有材料被系统标记为 prompt-only,未提供可执行脚本、安装命令或本机进程拉起逻辑。README 中提到的 `gh pr diff` 与 `grep` 更像校验示例/工作流上下文,而非该技能自身声明的执行权限。
README 说明该技能会基于 `scope_pages[]`、PR diff 和 `.apm/docs-index.yml` 对文档页面内容进行定位分析,说明其预期工作流会接触仓库内文档与变更信息。就技能类型而言这属于常规最小必要数据处理,未见写入、删除或越权读取更广泛系统资源的证据。
正面因素是来源为 GitHub 且开源,仓库可审计,并且归属 `microsoft/apm` 对来源可信度有加分;但许可证未声明、star 为 0、维护状态未知,社区采用与持续维护信号偏弱,因此建议在接入前做基础仓库与提交历史审查。
复制安装指令,让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "docs-impact-localizer" 技能: 1. 下载 https://raw.githubusercontent.com/microsoft/apm/main/.apm/skills/docs-impact-localizer/SKILL.md 2. 保存为 ~/.claude/skills/docs-impact-localizer/SKILL.md 3. 装好后重载技能,告诉我可以用了
docs-impact-classifier 已返回 verdict=in_place。请基于候选页面列表,读取每页内容,定位受影响的具体章节,并输出逐页任务简报,包含页面名称、需修改章节、修改原因和建议动作。
一份按页面组织的任务清单,明确每页应修改的具体章节及处理建议。
对于这批候选文档页面,不要笼统标记整页更新。请检查实际页面内容,把影响范围缩小到具体标题、段落或说明块,并输出最小可执行的逐页更新计划。
一份更精确的更新范围说明,避免整页返工,便于面板分发执行。
请把 in_place 判定结果转成 docs-sync panel 可直接使用的页面任务简报。基于候选页面和页面正文,逐页说明要改哪里、为什么改、改动边界是什么。
适合下游面板分发的逐页简报,每页都包含改动位置、原因和边界。
Single responsibility: given a list of candidate pages from the classifier, produce a per-page task brief the docs-sync panel can fan out against.
You are NOT the verdict-maker (classifier owns that). You are NOT the writer (doc-writer owns that). You are the work planner.
The docs-sync orchestrator invokes you ONLY when the classifier
returned verdict: in_place. For no_change you don't run.
For structural the architect runs first; you may run after, scoped
to existing pages that need amendment.
scope_pages[] from the classifiergh pr diff $PR).apm/docs-index.yml (per-page metadata)For each path in scope_pages[], read the file. Pages are typically
3-10 KB; total budget for this step is bounded by the candidate
count (the classifier should have kept it to <= 6).
For each page, identify the SPECIFIC section(s) that need to change:
lines 120-145 not the whole pageThe output is a sections_to_edit[] per page, where each entry is:
page: docs/src/content/docs/consumer/install.md
sections_to_edit:
- section: "## From Git"
line_range: [120, 145]
diff_symbol: "--no-cache flag"
edit_kind: add | modify | remove
rationale: "the new --no-cache flag is documented nowhere; section already lists other flags so this is the natural home"
If two pages document the same symbol and the diff changes the symbol's behaviour, BOTH pages need an edit AND they must stay consistent. Flag this in the brief so the CDO synthesizer knows to cross-check coherence between the two redrafts:
cross_page_constraint:
pages: [path1, path2]
shared_symbol: "apm install --target"
consistency_required: "both pages must reflect the same default value"
Return JSON with this shape (one entry per page in scope_pages[]):
{
"tasks": [
{
"page": "docs/src/content/docs/consumer/install.md",
"persona_owner": "consumer",
"promise": 1,
"sections_to_edit": [
{
"section": "## From Git",
"line_range": [120, 145],
"diff_symbol": "--no-cache flag",
"edit_kind": "add",
"rationale": "..."
}
],
"verify_claims": [
{"claim": "the flag is named --no-cache", "verify_with": "apm install --help"},
{"claim": "the flag is documented in click.option decorator", "verify_with": "grep -n no-cache src/apm_cli/commands/install.py"}
]
}
],
"cross_page_constraints": [
{"pages": [...], "shared_symbol": "...", "consistency_required": "..."}
],
"estimated_panel_calls": 8
}
The verify_claims[] per page is consumed by the python-architect
panelist -- it tells the verifier WHICH claims need a S7 tool-call
check (run apm install --help, grep the source) rather than
prose-trusting.
Return a SINGLE JSON document matching the schema in Step 4 as the final message of your task. No prose around the JSON.
verify_claims[] -- that's the S7 tool-bridge hook; the verifier needs it.scope_pages[] -- that's the classifier's job, not yours. If you think the classifier missed a page, return an extra field localizer_concern instead of expanding scope unilaterally.对整套技术文档逐页对照源码审计,并给出精准过时内容修复建议
优化命令行输出、日志与报错文案,提升终端交互可读性与诊断体验
批量分诊并推进疑似缺陷与相关 PR 到可合并状态的工程协作技能
在文档结构需随 PR 调整时,规划目录变更并生成新页面大纲草案。
帮助开发者规划 Python 模块结构、重构类层次并设计跨文件架构变更方案。
帮助团队制定 APM 项目定位、发布沟通与破坏性变更决策策略。
快速判断代码变更对文档的影响级别,决定是否需要同步更新文档
在每次 PR 变更时评估文档影响,并给出可落地的更新建议。
为 AI 代理本地解析 PDF/DOCX,提取文本、表格、元数据并检索关键词
帮助 AI 基于本地代码上下文进行影响分析并判断合并准备度。
将模糊或高风险的产品与工程变更梳理为可验证验收标准与实施要求
引导用户协作撰写文档、方案与技术规格,并通过迭代完善内容质量。