43d32e9b9d
- Refactor major-domo skill: api_client.py, cli.py, and CLI modules (admin, common, injuries, results, schedule, transactions) with significant simplification (-275 lines net) - Update CLI_REFERENCE.md and SKILL.md docs for major-domo - Update create-scheduled-task SKILL.md - Update plugins blocklist.json and known_marketplaces.json - Add patterns/ directory to repo - Update CLAUDE.md Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
44 lines
2.8 KiB
Markdown
44 lines
2.8 KiB
Markdown
# 🚨 CRITICAL: @ MENTION HANDLING 🚨
|
|
When ANY file is mentioned with @ syntax, IMMEDIATELY call Read tool on that file BEFORE responding.
|
|
Automatic loads are NOT enough — Read loads required CLAUDE.md context along the file path.
|
|
|
|
## Behavior
|
|
- User's name is Cal (he/him)
|
|
- If not confident in an answer, say so. Offer hypothesis + options to investigate.
|
|
- When writing tests, include detailed docstrings explaining "what" and "why"
|
|
- Launch sub-agents with Sonnet model unless another model is specified by the user
|
|
- When you need a response from Cal (asking a question, need approval, blocked on input), send a voice notification: `curl -s -X POST http://localhost:8888/notify -H 'Content-Type: application/json' -d '{"message": "your brief message here"}'` — this plays TTS audio through the workstation speakers via the local Piper voice server
|
|
|
|
## Memory Protocol (Cognitive Memory)
|
|
- App: `/mnt/NV2/Development/cognitive-memory/` | Data: `~/.local/share/cognitive-memory/`
|
|
- Use **MCP `memory_recall`** to search for relevant past solutions, decisions, and fixes before starting unfamiliar work
|
|
- Use **MCP `memory_store`** to persist: bug fixes, git commits (mandatory, --episode), architecture decisions, patterns, configs
|
|
- Always tag: project name + technology + category
|
|
- Session end: prompt "Should I store today's learnings?"
|
|
- `claude-memory core` and `claude-memory reflect` available for manual browsing
|
|
- Full docs: `claude-memory --help` or `~/.claude/skills/cognitive-memory/SKILL.md` (skill layer) / `/mnt/NV2/Development/cognitive-memory/` (app code)
|
|
|
|
## Git Commits
|
|
- NEVER commit/add/push/tag without explicit user approval ("commit this", "go ahead")
|
|
- Don't autopilot: find bug → fix → **ASK** → commit. Silence ≠ approval.
|
|
- Applies to: git commit, git add, git tag, git push, deploy scripts
|
|
|
|
## Gitea Operations
|
|
**Prefer the `gitea-mcp` MCP server** for all Gitea operations (PRs, issues, branches, labels, releases, Actions).
|
|
- MCP tools use `owner` + `repo` params (e.g. owner=`cal`, repo=`major-domo-v2`)
|
|
- Common repos: major-domo-v2, major-domo-database, major-domo-bot, paper-dynasty, paper-dynasty-database
|
|
- Never use `gh api --hostname` for Gitea
|
|
|
|
> **Fallback:** If MCP is unavailable, use `tea` CLI. Always pass `--repo owner/name`.
|
|
|
|
## Tech Preferences
|
|
- Python → see [`~/.claude/patterns/python.md`](patterns/python.md) (uv, DI, FastAPI hexagonal architecture)
|
|
- Never add lazy imports to middle of file
|
|
|
|
## SSH
|
|
**ALWAYS use SSH aliases from `~/.ssh/config` — NEVER construct manual `ssh -i` commands.**
|
|
- All homelab and cloud servers have aliases with pre-configured keys/users
|
|
- Just `ssh <alias>` (e.g. `ssh sba-db`, `ssh proxmox`, `ssh manticore`)
|
|
- If unsure of an alias, read `~/.ssh/config` to find the right one
|
|
- Fallback for unlisted homelab hosts: `ssh 10.10.0.x` (wildcard rule handles key/user)
|