将文档影响判定细化为逐页逐段的同步执行任务清单
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.优化 APM 代码库中的 CLI 输出、日志提示与诊断信息体验
快速判断 PR 变更对文档的影响级别,决定是否需要更新或重构文档。