$ loading_
Assess PR documentation impact and produce actionable update guidance every time.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "docs-sync" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/apm/main/.apm/skills/docs-sync/SKILL.md 2. Save it as ~/.claude/skills/docs-sync/SKILL.md 3. Reload skills and tell me it's ready
Assess whether this PR requires documentation updates. Even if the title and description do not mention docs, check whether the code changes make the docs inaccurate. Classify the impact as no change, in-place edit, or structural change, and provide affected pages, recommended edits, and patch-ready guidance.
A documentation impact assessment with impact level, affected doc locations, edit recommendations, and follow-up collaboration notes.
This PR mainly changes internal implementation, but I am concerned about silent documentation drift. Check whether user-visible behavior, configuration, parameters, outputs, or workflows have changed, and determine whether the current docs remain truthful and accurate.
A clear judgment on possible documentation drift and whether documentation additions or corrections are needed.
Analyze whether the feature changes in this PR go beyond what the existing pages can reasonably cover. If a new documentation page or TOC restructuring is needed, explain why, propose the information architecture, and identify which roles should participate in completing the update.
A conclusion on whether a new page or TOC update is needed, plus a structured documentation update plan.
The docs corpus drifts silently and constantly. This skill catches drift at PR-open time, classifies its impact, and orchestrates a persona panel to produce a patch-ready advisory comment.
The pattern is A1 PANEL + B1 FAN-OUT/SYNTHESIZER + A8 ALIGNMENT LOOP. The classifier is the cost gate (~70% of PRs short-circuit to no-change with ~1 LLM call). When the panel does fan out, every agent reads a bounded context (~10 KB) -- never the full corpus.
This skill is ADVISORY. It does not gate merge, apply verdict labels, or push to the contributor's fork. The orchestrator is the sole writer to the PR: exactly one comment per run (idempotent edit-in-place), plus optional label sweeps.
N/15 for observability.gh write command, post comments, or touch PR state.## Docs sync advisory. Re-runs edit-in-place using gh pr comment --edit-last.docs-sync-confirm label) open from a bot branch in the BASE repo; never pushed to the contributor's fork..apm/docs-index.yml, NOT the corpus itself. The corpus is sampled only by the localizer (which reads the specific candidate pages) and by per-page panelists (which read one page each).apm --help, grep, and python -c commands to verify doc claims, never assert from prose.| Role | Agent | Always active? |
|---|---|---|
| Classifier | doc-analyser inside docs-impact-classifier | Yes (every run) |
| Localizer | docs-impact-localizer | Only on in_place verdict |
| Architect | docs-impact-architect | Only on structural verdict |
| Writer | doc-writer | Per candidate page (fan-out) |
| Verifier | python-architect | Per candidate page (fan-out, S7) |
| Editorial | editorial-owner | Once across all redrafts |
| Growth | oss-growth-hacker | Once across all redrafts |
| Synthesizer | cdo | Once, with ALIGNMENT LOOP up to 3 redrafts |
docs-sync SKILL (orchestrator thread)
|
Step 1: classify (1 LLM call, may exit here)
|
v
verdict?
/ | \
no-change in-place structural
| | |
EXIT | architect (TOC delta)
| |
+----<-----+
|
Step 2: localize (1 LLM call) -- per-page task brief
|
Step 3: FAN-OUT panel via task tool
|
+----+----+----+----+
v v v v v
writer verify edit growth
x N x N once once
(parallel; each <=10 KB context)
|
Step 4: schema-validate returns
|
Step 5: CDO synthesize (1 LLM call)
|
agree?
/ | \
revise (N<=3 redrafts) | agree
|
Step 6: emit ONE comment via safe-outputs.add-comment
Step 7: OPTIONAL companion docs PR (only if structural AND
`docs-sync-confirm` label present)
Spawn ONE task: load the docs-impact-classifier skill, pass it the
…
Audit an entire docs corpus against code and propose precise fixes.
Improve CLI output, logs, errors, and terminal diagnostic user experience.
Triages bug batches and drives related PRs to a mergeable state.
Plan doc TOC changes and outline stubs when PRs require structural updates.
Plan Python architecture, refactor class hierarchies, and design multi-file code changes.
Guide APM positioning, release communication, and breaking-change strategy decisions.
Classify PR doc impact to decide whether documentation updates are needed.
Write complete, evidence-backed PR descriptions for microsoft/apm pull requests.
Run a multi-expert advisory review for labelled microsoft/apm pull requests.
Guide users to co-author docs, proposals, and specs through iterative refinement.
Helps teams handle APM positioning, release communication, and breaking-change decisions.
Create and maintain ADRs with checks, references, and planning support.