arcforge

Use when running autonomous unattended loops — cross-session execution of DAG tasks without human intervention

Use when converting design documents to structured specs, when spec quality is below threshold, or when requirements need formal acceptance criteria

Use when you need to verify work is complete before making completion claims

Use when maintaining ArcForge itself by creating, editing, or verifying ArcForge skills before deployment

Use when optional learning is enabled and observations should become reviewable candidates, inactive drafts, and explicitly activated artifacts.

Use when user asks about behavioral patterns, requests instinct status, or wants to confirm/contradict a detected pattern

Use when executing task lists where each task requires isolated execution

Use when dispatching multiple independent features within a worktree session

Use when the user wants to manually save a pattern or insight as an instinct from the current session context, invokes /arcforge:arc-recalling with a description, or identifies a reusable technique worth preserving

Use when the user asks to reflect on accumulated diaries (/arcforge:arc-reflecting), after 5+ diary entries accumulate, or when asked to summarize preferences from past sessions

Use when specs/<spec-id>/dag.yaml has 2+ ready epics and the lead is staying present to monitor epic-level parallel work via agent teammates. Trigger on mentions of agent teams/teammates for multi-epic work, or after arc-planning yields multiple ready epics. For walk-away unattended execution, use arc-looping.

Use when executing a prepared task list, when running batch implementation, or when tasks are already broken down

Use when implementation is complete and all tests pass, and you need to decide how to integrate — works for both epic worktrees (.arcforge-epic present) and regular branches. Step 0 discriminates on the marker.

Use when orchestrating large project implementation in a worktree

Use when receiving code review feedback, requires technical rigor not performative agreement

Use when completing tasks or features to request code review

Use when an ArcForge task needs routing help or the user asks which ArcForge skill/workflow applies

Use when work needs an isolated workspace — a parallel branch, an experiment, a review checkout, or scoping to one epic — in ANY git repo, even if the user never says "worktree". Epic context auto-escalates to the coordinator; everything else uses the generic worktree CLI.

Use when exploring ideas before implementation or when user wants to design a new feature or iterate on an existing spec

Use when optimizing any measurable metric through autonomous hypothesis-driven experimentation — build times, algorithm efficiency, prompt quality, model performance, or any target with a numeric signal

Use when the user asks to journal session reflections (/arcforge:arc-journaling), when the PreCompact hook triggers, or at end of a significant work session

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when the user explicitly invokes `/arcforge:arc-auditing-spec <spec-id>` for a read-only advisory audit of an SDD spec family (design, spec, dag, decision anchors). Only triggered by direct user invocation; never auto-invoked from any pipeline skill.

Guide for strategic manual compaction timing at workflow phase boundaries

Use when the user wants an Excalidraw diagram or any visual representation — architecture, flowchart, mind map — including casual "draw this" / "show me how this works visually". Also use when arc-maintaining-obsidian delegates Synthesis visuals beyond embedded Mermaid.

Use when the user wants to create, query, audit, or initialize an Obsidian vault — saving notes/ideas/URLs into it ("save this" / "file this back" included), querying vault knowledge, auditing health (missing links, orphans, drift), ingesting files, or registering vaults. Not for Excalidraw diagrams — use arc-diagramming-obsidian.

Use when ending a session and handing off to a future session, summarizing recent context, continuing from where the last turn left off, archiving a session for durable reference, or resuming/listing/aliasing saved sessions

Use when breaking down features into executable tasks, when preparing for implementation, or when tasks need exact code and commands

Use when measuring whether skills, agents, or workflows actually change AI agent behavior — before shipping a new skill, after modifying an existing one, or when comparing alternative approaches

Use this skill whenever the user (an arcforge contributor) says they want to bump arcforge's version, cut a release, "ship vX.Y.Z", "準備發版", "ready to release", or any equivalent intent on the arcforge repo itself — even if they don't use the word "release". Runs the canonical release workflow: pre-flight checks → vault ingest → outdated-doc audit → CHANGELOG → 9-file version bump (incl. website) → commit/push/PR → post-merge tag. Contributor-only; do NOT trigger inside projects that merely install arcforge as a plugin.

Use when breaking down a structured spec into an executable DAG, when a spec has been refined and epics need to be defined, or when planning feature and epic structure for implementation

Use when managing worktrees for multi-epic projects, when specs/<spec-id>/dag.yaml exists, or when coordinating parallel development

Use when implementing any feature or bugfix, before writing implementation code