Skills

The hub skill that orchestrates everything. Takes a task description, creates an isolated worktree, and walks through six phases: Onboard, Research, Plan, Implement, Review, Complete. In standard mode, each phase has a hard gate requiring approval before proceeding. Uses /council for context, /gather-lore for conventions, /lembas for context compression between phases, and /warden for pre-PR review. Supports plan-driven mode: provide a pre-existing plan file and the quest skips Research and Plan, jumping straight to Implement. Supports promoted mode: when a quest is promoted from a scout, Phase 1 enters validation mode — verifying and supplementing scout findings instead of researching from scratch. Includes a bulletin board for cross-quest knowledge sharing: quests scan the bulletin at Research start and post discoveries during Research and Implement. The bulletin is shared across all worktrees via the main repo root.

For multiple independent tasks, Gandalf (the coordinator) spawns quest and scout teammates. Quests run in isolated worktrees and produce PRs. Scouts research questions and deliver findings. Say ‘status’ during a fellowship for a progress table. Gates surface to you for approval by default. Supports plan-driven quests: provide a plan file and Gandalf spawns quests that skip to Implement. For large plans, Gandalf can fan out into multiple parallel quests after confirming the split with you. Supports scout-to-quest promotion: say ‘promote scout-X to a quest’ and Gandalf spawns a quest pre-loaded with the scout’s findings. The bulletin board enables cross-quest knowledge sharing — cleared automatically on disband.

Autonomous research agent that investigates questions with configurable depth. For complex questions, spawns a fresh adversarial validator subagent to verify findings. Produces a structured report with confidence levels. Writes findings to a namespaced file (.fellowship/scout-findings-{name}.md) that can be promoted into a quest. Use alongside /quest in a fellowship for research questions that don’t need code changes.

Loads task-relevant files, conventions, and architecture. Checks for lembas checkpoints from previous sessions and offers to resume. Scopes to the relevant package in monorepos. Run at the start of any session or quest.

Analyzes your codebase to extract patterns before writing code. Examines existing implementations to understand naming conventions, file organization, testing patterns, and architectural decisions. Prevents ‘wrong approach’ rework by learning from what’s already there.

Compacts the conversation context at phase transitions. Keeps the context window in the reasoning sweet spot by summarizing what’s been done and what needs to happen next. Invoked automatically at all four phase transitions during a quest.

Compares your changes against reference files and documented patterns in CLAUDE.md. Catches convention violations before they reach PR review. Checks naming, file organization, testing patterns, and architectural consistency.

Walks through your project to extract conventions into CLAUDE.md. Run once when setting up Fellowship in a new codebase. Examines your code structure, testing patterns, naming conventions, and documents them for future quests.

After a PR review, extracts conventions from reviewer comments and adds them to CLAUDE.md. Closes the convention learning loop — reviewer feedback becomes documented patterns that future quests will follow.

Analyzes a completed fellowship’s gate history, palantir alerts, and quest metrics to surface patterns. Identifies which gates added value, which phases caused delays, and interactively recommends configuration changes like auto-approving gates with zero rejection rates.

Pulls structured context from GitHub issues via gh CLI — title, body, labels, and recent comments. Returns a package with issue context, a suggested branch name incorporating the issue number, and PR closing keywords (Closes #N). Gandalf invokes it automatically when issue references (#N) are detected in quest descriptions. Also usable standalone: /missive 42 to preview what context a quest would receive.

Invoked at the start of each quest phase when your spawn prompt includes a TEMPLATE: assignment. Resolves the template file from project (.claude/fellowship-templates/) or user (~/.claude/fellowship-templates/) directories, reads the section matching the current phase, and applies the guidance as advisory context. Created via /scribe.

Interactive setup for all configuration options in ~/.claude/fellowship.json. View current settings, edit individual values, or reset to defaults.

Analyzes your project to create quest templates that encode project-specific knowledge — conventions Claude wouldn’t know, domain rules that aren’t in code, team workflows that matter. Templates provide phase-specific guidance loaded automatically by /lorebook during quests. Stored in .claude/fellowship-templates/ (project) or ~/.claude/fellowship-templates/ (personal).

Interactive walkthrough that teaches fellowship by running a real task on your codebase. Walks you through research, planning, and implementation with natural-language checkpoints at each stage. Produces a real PR. Afterward, introduces /quest and /fellowship for continued use. Designed for people new to agent orchestration.

Scans worktrees and state files to reconstruct fellowship state from on-disk artifacts. Presents a recovery dashboard showing which quests are resumable (have checkpoints), stale (no checkpoint), or already complete (branch merged). On confirmation, re-spawns Gandalf and quest runners with recovered context.