Claude Code Expert

Auto mode permission handling — classifier-based approvals, PermissionDenied hook, defer permissionDecision, and autonomy profiles for hands-off Claude Code usage

Ultraplan cloud planning — kick off a plan in the cloud from your terminal, review and revise in the browser, then execute remotely or send back to CLI

Idempotent update of an existing Claude Code setup — re-fingerprint the repo, propagate updates to sub-repos, refresh docs/context, section-merge CLAUDE.md/README.md, fix configuration drift. Use this skill whenever the user runs /cc-sync, asks to "update the claude setup", "propagate to sub-repos", "fix drift", "resync", or reports that the .claude/ directory has gone stale.

Deploy or audit the full 5-layer Claude Code stack (CLAUDE.md + skills + hooks + agents + memory) in a repository. Use this skill whenever the user runs /cc-setup, asks to "set up Claude Code on this repo", "configure a new repo for Claude", "audit my Claude Code setup", "generate CLAUDE.md", "install hooks", "wire up the 4-layer stack", or starts work in a repo that lacks .claude/. Also triggers on "bootstrap Claude Code", "add claude setup", or whenever a fresh repo needs Claude Code configuration.

Monitor tool for streaming background process events into conversations — tail logs, watch CI, auto-fix dev server crashes, and /loop self-pacing without Bash sleep loops

Manage the three-tier memory system (engram + Obsidian vault + plugin rules) for Claude Code setups. Use this skill whenever saving CC-setup findings, consolidating engram into durable knowledge, writing repo docs to the Obsidian vault, or running /cc-memory subcommands. Triggers on phrases like "save this pattern", "promote to memory", "update the vault", "consolidate memory", "write an ADR", and whenever work on CC plugins, hooks, agents, skills, or autonomy profiles concludes.

Design, install, and debug Claude Code hooks across the full lifecycle (PreToolUse, PostToolUse, PostToolUseFailure, UserPromptSubmit, Notification, Stop, SessionStart, SessionEnd, PreCompact, SubagentStart, SubagentStop, TeammateIdle, PermissionRequest, Setup). Use this skill whenever a user asks to "install hooks", "add a pre-tool hook", "format on save", "block dangerous commands", "protect sensitive files", "restore context after compact", "enforce tests before stop", capture subagent telemetry, or runs /cc-hooks. Also triggers on "hooks not firing", "hook keeps blocking", or any configuration of .claude/settings.json hook sections.

Git worktree creation, agent isolation, parallel task execution with EnterWorktree/ExitWorktree, branch-per-worktree patterns, and cleanup lifecycle for Claude Code

Checkpoint-between-waves cadence for multi-file refactors. After each logical batch (wave) of edits, run typecheck + tests; commit only on green; roll back the wave (not the whole branch) on red. Use for any refactor touching more than three files or three distinct concerns.

Evidence-driven deep analysis for hard coding problems — architecture decisions, root-cause investigation, high-stakes refactor planning, performance bottleneck isolation. Use this skill whenever the user asks for "the best approach", a "deep analysis", "root cause", "principal engineer review", or runs /cc-intel. Also triggers on hard debugging questions, major architectural choices, tricky performance problems, or any task where a hypothesis tree and evidence table matter more than a fast answer.

Pre-flight check to run before any Agent-tool spawn. Prevents the "Prompt is too long" rejection class by enforcing a 5-section minimum-viable-prompt template and estimating forwarded context cost. Use whenever you are about to call the Agent tool with more than a one-paragraph prompt.

Shared filesystem-backed blackboard for multi-agent runs. Parallel subagents append findings for a given run-id; subsequent-round subagents read them via MCP tools without the orchestrator having to paste everything into their prompts. Use for any fan-out pattern with more than one round of deliberation.