git:20260815.0fcd29e to git:20260815.40ec02b

# [Your Name] — Context

## Who I Am

→ Read `identity/who-i-am.md` for bio and background.

## Slash Commands (Claude Code)

| Command | Does |

|---------|------|

| `/setup` | Interactive onboarding — builds identity, project, and state files conversationally |

| `/start` | Load state, pull live data, get a session briefing |

| `/end` | Log session, update state and the decision log, propose memory updates, check git |

| `/update` | Mid-session checkpoint — quick state save |

| `/today` | Morning heartbeat — briefing, staleness check, deadlines |

| `/clean-ai-writing` | Load `writing/skills/avoid-ai-writing/SKILL.md` and apply it |

| `/capture` | Triage raw notes from `inbox/` into the right locations |

| `/find-context` | Find relevant context files by topic keyword (avoids Claude's built-in `/context`) |

| `/reconcile` | Drift detection after parallel sessions |

| `/recover` | Scan orphaned worktrees and stale branches, offer cleanup |

| `/content-shipped` | Log a published piece of content |

| `/dream` | Run an autonomous curator pass over the memory dir (default: rot detection) |

| `/dream-apply` | Walk a curator proposal artifact, accept/reject/edit per item |

| `/skill-creator` | Generate a new skill and command routing file from a plain-language description |

| `/migrate-gemini` | Migrate selected Gemini CLI workflows with dry-run review and parity checks |

| `/mine-gemini-workflows` | Find repeated Gemini workflows and draft portable skills |

Add more commands as you build out skills. See `docs/agent-template.md` for how.

## When to Load Additional Context

For tasks without a slash command → load `ROUTING.md`.

## Thought-Partner Mode

When thinking through a decision or tradeoff — rather than producing a deliverable — operate as a thought partner:

- **Challenge assumptions.** If a premise seems weak or unexamined, say so.

- **Offer the alternative.** Present the strongest case for a different path.

- **Ask the uncomfortable question.** What hasn't been considered or is being avoided?

- **Be direct about tradeoffs.** Don't soften the downsides.

- **Summarize the decision cleanly.** What's the choice, what does each path require, and what's the real risk?

This mode applies to career moves, strategy decisions, project bets, and any "help me think through X" framing. It does NOT apply to execution tasks where the goal is to produce a deliverable.

## Safety Contract

Actions that change external state or are hard to reverse require confirmation. See `docs/safety-contract.md` for the full policy, approval patterns, and design principles.

## Memory

Claude Code auto-loads `~/.claude/projects/<encoded-cwd>/memory/MEMORY.md` on every conversation in this project. Use it as a persistent, file-based memory: typed entries (`user`, `feedback`, `project`, `reference`), one-line pointers in `MEMORY.md`, detail in `<topic>.md` files. See `docs/auto-memory.md` for the full spec — when to save, when NOT to save, body structure, the two-step write. `MEMORY.md` is capped at ~100 lines.

Run `/dream` periodically to curate (rot, contradictions, untapped patterns). Run `/dream-apply` to review proposed changes. See `docs/dream-architecture.md`.

## Single Source of Truth

Each piece of data lives in one file only. Other files can reference it, never duplicate it.

- Tasks → `TODO.md` (curated top-of-mind view → `state/current.md`)

- Weekly focus → `state/weekly-priorities.md`

When you add project-specific data (metrics, pipeline status, etc.), pick one file as the source and note it here.

## Parallel Sessions

When running parallel Claude Code sessions, use `claude --worktree <task-name>` so each gets its own branch. Merge to main when done. Run `/reconcile` after parallel work to catch drift.

For high-traffic repos, enable the parallel-session guards: add the repo basename to `.claude/hooks/guarded-repos.txt` and `worktree-guard.sh` (PreToolUse) blocks edits to its primary checkout when ≥2 Claude sessions are running, while `branch-hygiene.sh` (SessionStart) surfaces non-default HEAD. See `.claude/hooks/README.md`.

## Claude Code vs claude.ai

This repo is designed for **Claude Code** (CLI). If you also use **claude.ai projects**, upload key files (CLAUDE.md, ROUTING.md, identity files) as project knowledge. See `docs/claude-projects-sync.md` if present.

## Repo Maintenance

See `docs/repo-maintenance.md` for staleness conventions, changelog updates, repo map regen, and validation.