AI Agent & Automation Workflows

Autonomous orchestrator for green-light / overnight execution. Takes one task and runs the full engineering cycle (research → plan → sprint → audit → report) end-to-end without approval checkpoints. Uses TeamCreate with explicit file-ownership and blockedBy edges between waves, resolves blockers via ADI (Abduct → Induct → Deduce) instead of asking the user, and only stops on red-line actions (push to main, secret writes, destructive ops, deploys). Use when you want to give one prompt and let it run unattended — overnight runs, bypassPermissions sessions, or when you can't watch checkpoints. Triggers (EN/RU) — "autorun X", "run unattended", "do this overnight", "запусти автопилот", "сделай всё автономно", "ночной прогон", "/autorun".

Export the current Hindsight bank's content for backup or audit — memories, documents, mental models. Use when the user says "back up memory", "export bank", "save Hindsight state", or before doing risky operations like deleting / re-bootstrapping a bank.

Structured report formats for Claude — card-based, human-readable, no ASCII frame noise. Use when finishing a multi-step task (≥5 tool calls, ≥3 files modified, multi-task TaskList, or cross-system effects like git push/PR/deploy). Triggers on: report, summary, summarise, отчёт, итоги, завершение задачи, build complete, audit complete, deployment complete, decision recorded, incident resolved, migration done. Provides 5 templates (build/audit/decision/incident/migration), anchor conventions (section icons, plain-prose TL;DR, confidence labels), required sections (not-done, reversibility, drift-risks, next-steps), and 5 anti-patterns. Not for simple Q&A or single-file edits.

Live reference for the 66 mcpforgeplan MCP tools and the 82 forgeplan CLI subcommands shipped in forgeplan 0.32.1. Agents and humans consult this skill when they know what they want to do (create an artifact, score a graph, dispatch sub-agents, detect anomalies) but don't yet know which tool name to call. Organised by use-case (lifecycle / discovery / quality / health / AI-driven / multi-agent / brownfield / activity / FPF / playbooks / plugins / release / safety) rather than alphabetically. Each section maps tools to canonical use-cases + which Profile A / B / C / D agent or which skill should call them. Includes known safety warnings (forgeplan350 MCP body literal-string-only, forgeplan348 score-all hint typo, forgeplan351 plugins doctor install syntax).

Practical cookbook of forgeplan CLI recipes — 25+ task-oriented how-to guides answering "how do I do X?" for forgeplan CLI users and Claude as an assistant. Use when you need a concrete command sequence, a worked example, or a Common errors table for: PRD creation, Evidence authoring, workflow cycles, plugin versioning, AI-agent dispatch, troubleshooting anomalies, or CLI/MCP quick reference.

One-command project bootstrap for the ForgePlan ecosystem. Probes the forgeplan CLI, runs forgeplan init, wires .mcp.json and .claude/settings.json, then chains /bootstrap (universal CLAUDE.md template) and /setup (docs/agents/ wizard) so a fresh repo is fully wired in one shot. Recommends — but does not install — companion plugins (fpf, laws-of-ux, agents-core, forgeplan-workflow, forgeplan-orchestra). v2.0: Adds optional --canonize step that scaffolds the canonical agent layer (project-agent-matrix.yaml + project-config.yaml + Hindsight mental models) for forgeplan-aware projects per PRD-026 Phase 5. Use on a brand-new project, or on an existing project that has none of .forgeplan/, CLAUDE.md, docs/agents/. Triggers (EN/RU) — "fpl init", "init project", "bootstrap forgeplan", "set up everything", "full project setup", "/fpl-init", "поставь всё", "разверни проект с нуля", "инициализируй проект", "fpl init canonize", "setup agent matrix", "v2 bootstrap".

RIPER methodology orchestrator — Research → Innovate → Plan → Execute → Review — the FOURTH instance of the AD/AID-PDLC sub-cycle contract (ADR-010 / RFC-018). Drives a bug / scoped change / investigation in an EXISTING active system through five modes, MAIN-SESSION-orchestrated (hook-gate=No → no dispatched master, no hook), with a mandatory independent C4 verifier at every mode gate and — uniquely — a dedicated C4+C6 on the non-freezable Research product (a Research NOTE + an Pinned revision EVID + a Plan-gate pin-freshness re-check): RIPER is the first instance to exercise ADR-010's conditional-freeze path end-to-end. Each phase delegates to existing fpl-skills (/research, /refine or /fpf-decompose, /rfc create, /sprint or /forge-cycle, /audit) with explicit phase tracking. MCP-first per PRD-022 Tier A — forgeplan artifact creation uses mcpforgeplanforgeplannew + link + validate when MCP is available; CLI fallback (bash forgeplan ...) only when MCP server not connected. Triggers (EN/RU) — "riper", "research innovate plan execute review", "/riper", "пройди riper", "RIPER цикл", "production bug", "investigate before fixing".

Greenfield-project onboarding skill. For a fresh repo (no CLAUDE.md, no forgeplan, no AGENTS.md), runs an active infrastructure setup (plugin gate → forgeplan MCP auto-wire via forgeplan mcp install → Hindsight detection + env-var remap guidance → .claude/hooks/ baseline bundle → reload + verify) → pre-flight detection → forgeplan init → CLAUDE.md scaffold → AGENTS.md scaffold → plugin install recommendations → first Brief via brief-intake agent → first PRD via specification agent. Output: bootstrap checklist artifact + a confirmed greenfield project ready for the canonical /forge-cycle pipeline.

Educational routing skill. Walks the user through smith's methodology routing matrix without committing to a specific task. Use to learn "when do I apply BMAD vs SPARC?", "what methodology for brownfield?", "explain the bug fix workflow". Pulls from routing-map.md (12 contexts + 25 methodology cards) and sections/NN-.md (detailed playbooks). Output: educational comparison + recommendation when user describes their situation. Does NOT produce a Plan artifact — for that, use /smith-plan.