prompt-optimize
Load each time you write or fix text that a model reads as instructions: prompts, tool descriptions, skills and skill descriptions, AGENTS.md, lessons, briefs.
- License 许可
- MIT
- 所属仓库
- kfet/fir
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- prompt-optimize
- builtin
- true
- description
- Load each time you write or fix text that a model reads as instructions: prompts, tool descriptions, skills and skill descriptions, AGENTS.md, lessons, briefs.
03 SKILL.md 正文
Optimize a prompt
- If the text is clear and works, keep it. Do not add rules.
- Put the rule where the model decides. Say what to do and why.
- Remove repeats, conflicts and lines that change nothing. Use simple words.
- Test 2–4 versions on a cheap model. Keep the shortest that works best.
04 同仓库更多 Skills
wt
Spawn a fresh fir agent in its own tmux session on its own git worktree. Use whenever the user wants the work — or the conversation about the work — to happen over there, not here. If the user points at this skill, or has directly loaded it in the context, that alone is the cue — spawn, don't inline.
wrap-up
Wrap up work on a project branch — review, fix, and simplify in a loop until clean, then ff-merge to main.
tmux-observer
Attach a tmux window to an already-running fir session — observe its transcript and drive its input via tmux send-keys. Use when you need to watch or steer another fir agent.
tmux-driver
Drive interactive CLIs (python, gdb, etc.) via named tmux sessions with multi-window support. Falls back to fir's built-in PTY driver when tmux is unavailable.
telegram-bot-setup
Set up a new Telegram bot channel for a fir project — install the telegram MCP, create a per-project state dir, drop in the bot token, wire .fir/mcp.json with TELEGRAM_STATE_DIR, pair the user, and verify. Use when the user asks to add, configure, or onboard a Telegram bot for a fir worktree/project.
sync
Sync with an upstream source repo — detect changed files, apply equivalent downstream edits, update the baseline, and report any new features or non-trivial changes picked up.