justinjdev/fellowship Skills

Use when joining a new codebase or starting to use AI tooling on an existing project. Interactively walks through the codebase to extract conventions, identify reference files, and generate a project-specific CLAUDE.md conventions section. Run this once per codebase, then maintain with PR feedback capture.

Use at the start of any non-trivial task. Loads focused, task-relevant context by reading CLAUDE.md, scanning for related files, and producing a structured Session Context block. Invoked automatically by quest or standalone via /council.

Multi-quest orchestrator. Coordinates a team of agent teammates (led by Gandalf), each running /quest in an isolated worktree. Use when you have multiple independent tasks to run in parallel.

Use BEFORE writing any code in an unfamiliar area. Studies reference files from CLAUDE.md to extract conventions and patterns. Prevents "wrong approach" code review rework by understanding how things are done before writing anything.

Use between workflow phases or when context feels bloated. Compresses the current conversation into a structured summary capturing task, findings, files, state, and next steps. Invoke standalone or automatically between quest phases.

Use for any non-trivial task. Orchestrates the Research-Plan-Implement cycle with compaction between phases, integrating council, lembas, gather-lore, and warden. Enforces discipline and phase gates.

Use after receiving PR review feedback. Extracts conventions from reviewer comments and offers to add them to CLAUDE.md. Closes the convention learning loop.

View or edit fellowship configuration (~/.claude/fellowship.json). Run /settings to see current settings, change values, or reset to defaults.

Use AFTER writing code and BEFORE submitting a PR. Simulates a strict code reviewer by comparing changes against reference files and documented conventions. Catches "we don't do it that way" feedback before your human reviewer does.