Activate when reviewing or modifying dependency resolution, lockfile schema, package downloaders, signature/integrity checks, file integration cleanup, or anything that could expose APM to dependency confusion, typosquatting, malicious packages, or token leakage.

Use only as the composed drive-to-merge stage of an APM batch orchestrator (batch-bug-shepherd, apm-issue-autopilot) that has already selected ONE open pull request in microsoft/apm. Do NOT use for user-facing requests to triage issues, sweep a queue, or open PRs -- the parent orchestrator owns those. Spawn one shepherd-driver subagent per PR: it classifies copilot-pull-request-reviewer[bot] inline review, runs the apm-review-panel, folds (by default) every recommendation inside the PR's stated scope, pushes to the head branch or a superseding PR that preserves authorship via commit trailers, watches CI to green, and iterates under fixed caps until ready-to-merge, advisory-with-deferred, superseded, or blocked. Also provides the cross-PR conflict-resolution and mergeability-gate phase. This is NOT a standalone entrypoint.

Use this skill whenever a pull request is opened, reopened, or synchronized in microsoft/apm to assess whether and how the documentation corpus must change to stay truthful with the proposed code change. Activate even when the PR title or body says nothing about docs -- the skill must run on every PR to detect silent drift between code and docs. Classifies impact as no-change, in-place edit (one to a few paragraphs), or structural change (new page or TOC reshape), then orchestrates a CDO + doc-writer + python-architect + editorial-owner + growth-hacker loop to produce a patch-ready advisory. Does NOT review code quality, security, or test coverage. Does NOT auto-merge or auto-push doc edits.

Deterministic debugging with rr record-replay. Use when debugging crashes, ASAN faults, or when reverse execution is needed. Provides reverse-next, reverse-step, reverse-continue commands and crash trace extraction.

Apply plugin knowledge base updates to an existing generated system. Consults the Ars Contexta research graph for methodology improvements, proposes skill upgrades with research justification. Never auto-implements. Triggers on "/upgrade", "upgrade skills", "check for improvements", "update methodology".

Get research-backed architecture advice for your knowledge system. Describe your use case, constraints, and goals — get specific recommendations grounded in TFT research with rationale for each decision. Triggers on "/recommend", "what would you recommend", "architecture advice", "knowledge system for".

Combined verification — recite (description quality via cold-read prediction) + validate (schema compliance) + review (health checks). Use as a quality gate after creating notes or as periodic maintenance. Triggers on "/verify", "/verify [note]", "verify note quality", "check note health".

Schema validation for notes. Checks against domain-specific templates. Validates required fields, enum values, description quality, and link health. Non-blocking — warns but doesn't prevent capture. Triggers on "/validate", "/validate [note]", "check schema", "validate note", "validate all".

Update old notes with new connections. The backward pass that /reflect doesn't do. Revisit existing notes that predate newer related content, add connections, sharpen claims, consider splits. Triggers on "/reweave", "/reweave [note]", "update old notes", "backward connections", "revisit notes".

Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems. Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned".

Queue processing with fresh context per phase. Processes N tasks from the queue, spawning isolated subagents to prevent context contamination. Supports serial, parallel, batch filter, and dry run modes. Triggers on "/ralph", "/ralph N", "process queue", "run pipeline tasks".

Surface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals. Recommends one specific action with rationale. Triggers on "/next", "what should I do", "what's next".

Research a topic and grow your knowledge graph. Uses Exa deep researcher, web search, or basic search to investigate topics, files results with full provenance, and chains to processing pipeline. Triggers on "/learn", "/learn [topic]", "research this", "find out about".

Interactive knowledge graph analysis. Routes natural language questions to graph scripts, interprets results in domain vocabulary, and suggests concrete actions. Triggers on "/graph", "/graph health", "/graph triangles", "find synthesis opportunities", "graph analysis".

Contextual guidance and command discovery. Three modes — narrative (first-time), contextual (mid-task), compact (quick reference). Shows available commands, active skills, and intelligent suggestions based on vault state. Triggers on "/help", "what can I do", "show commands", "how does this work".

Run condition-based vault health diagnostics. 8 categories — schema compliance, orphan detection, link health, description quality, three-space boundaries, processing throughput, stale notes, MOC coherence. 3 modes — quick (schema+orphans+links), full (all 8), three-space (boundary violations only). Returns actionable FAIL/WARN/PASS report with specific fixes ranked by impact. Triggers on "/health", "check vault health", "maintenance report", "what needs fixing".

Use this skill when diagnosing a bug, unexpected behavior, test failure, or any situation where code does not behave as expected. Follow a structured debugging process instead of randomly changing code.

Resume prior work by rebuilding context from the Basic Memory knowledge graph — pick up where you left off using memory:// URLs, recent activity, and search. Use when starting a session or when the user says 'continue with...', 'back to...', or 'where were we?'

Synthesize GitHub delivery context into a concise Basic Memory project update. Use in CI after `bm ci collect` prepares a ProjectUpdateContext; return only structured AgentSynthesis JSON for `bm ci publish`.

Capture the current state of a working thread or conversation into a single coherent Basic Memory note — synthesize where it landed, don't append a log. On re-capture, rewrite the same note in place instead of duplicating. Use mid-thread or end-of-thread when decisions, insights, or context are worth preserving.