AI Agent Workflow Collection

Passive scope-clarification skill. Auto-triggers when roll-build receives vague or under-specified input in Fly mode. Summarizes intent and asks 3–5 targeted questions to establish boundaries before planning or coding. This is a passive skill. Never announce "I'm using roll-.clarify." Just do it naturally: summarize, ask, wait.

Nightly code and architecture health scan. Passively triggered by scheduler (cron or GitHub Actions), not invoked by users directly. Detects dead code, architectural drift from domain model, pruning candidates, emerging patterns, doc coverage gaps, and doc staleness (文档新鲜度). Outputs REFACTOR entries to BACKLOG.md and a daily log to docs/dream/. Distinct from roll-sentinel: sentinel monitors runtime behavior; dream reviews code structure and architectural health.

Passive intent clarification skill. Automatically activates when user input is vague, rambling, contradictory, or unclear. Restates the user's intent in structured, concise form and confirms before proceeding. Does NOT activate when intent is already clear — in that case, just execute directly. This is a passive skill. Never announce "I'm using roll-.echo." Just do it naturally: restate, confirm, proceed.

Owner-facing briefing generator. Summarizes what the agent has done since the last brief: completed US/FIX/REFACTOR, in-progress items, BACKLOG queue status, escalations requiring human attention, and a release-readiness verdict. Three trigger modes: auto on Feature completion, daily morning schedule, or manual $roll-brief invocation. Distinct from roll-.changelog (user-facing release notes) — this is an internal digest for the product owner.

Legacy project documentation automation. Scans all docs, builds/updates docs/INDEX.md, identifies undocumented modules, and generates draft fills for gaps. Works on any project.

Fast backlog capture. Analyzes a short description, classifies it as bug or idea, and appends it to BACKLOG.md with an auto-incremented ID.

Autonomous BACKLOG executor. Runs on a schedule (hourly via cron or GitHub Actions), scans BACKLOG.md for 📋 Todo items, and routes each to the appropriate skill: US-XXX → $roll-build, FIX-XXX → $roll-fix, REFACTOR-XXX → $roll-build. Handles agent fallback on token/network failure. Never executes roll-release autonomously — release is always a human decision. Triggers roll-brief when a Feature completes.

Interactive onboarding for legacy projects. Reads existing code, understands the project, asks 9 questions in 3 groups (cognition / scope / privacy), and writes .roll/onboard-plan.yaml as the contract for roll init --apply to execute.

Cross-agent peer review skill. When a task enters a decision phase (planning, high-risk, ambiguous, destructive), triggers a bidirectional negotiation with another AI agent via a unified protocol. Up to 3 rounds. If consensus is not reached, escalates to the human user. Includes adaptive peer routing based on task type and historical success rate. Trigger: /peer, "叫上 peer", "peer review", or auto-triggered at workflow gates.

Human-triggered product proposal generator. Reads project context (BACKLOG, recent commits, existing skills) and generates 1–3 structured US drafts from a user-facing perspective. Writes to PROPOSALS.md for human review — never directly to BACKLOG. Distinct from roll-.dream (which surfaces technical debt from execution experience); roll-propose thinks in user scenarios and feature gaps.

Agent-agnostic PR review skill. Reviews a pull request diff and emits a structured 3-state verdict (APPROVE / REQUESTCHANGES / UNCERTAIN). Used by roll review-pr and loopprreviewexternal.