一键导入
notify
Inform the user what is happening — skip passive lookups
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Inform the user what is happening — skip passive lookups
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
| name | notify |
| description | Inform the user what is happening — skip passive lookups |
| token_cost | 1 |
| keywords | ["inform","progress","status"] |
Keep the user informed of what the agent is doing.
REQUIRED: message (one-line text)
Every step that produces effects. Editing code, running builds, checking output, fixing errors — always notify. Pure reads (find, read, ls, grep) are passive lookups and do not warrant notification.
{"name": "notify", "input": {"message": "Running test suite"}}
notify("Editing config file") — before editingnotify("Running typecheck") — before runningnotify("Typecheck passed") — after resultsnotify("Done!") — on completionnotify("Starting research") — before web searches beginnotify("Done, writing answer") — when transitioning to outputnotify("Investigating the issue") — at startnotify("Found the cause, applying fix") — on breakthroughnotify("Fix verified, done!") — on completionRenders markdown to self-contained HTML with a custom dark stylesheet and opens in browser. Use when previewing markdown documents, generating styled HTML from README or report files.
Manage version control with Jujutsu (jj) — no staging area, immediate changes, smart rebasing. Use when navigating history, squashing, or pushing to Git remotes.
Programmatic hunk selection for Jujutsu — split, commit, or squash specific hunks without interactive prompts. Use when making partial commits or selective squashes.
Gather facts from the web using evidence-first approach with mandatory citations. Use when researching topics, answering factual questions, or any task requiring web-sourced evidence.
Model minimum-move problems as BFS over a state space. Use when solving bucket pouring puzzles, sliding tiles, or any problem asking for the shortest sequence of moves to reach a goal.
Search on monotonic predicates for sorted arrays, answer spaces, and rotated arrays. Use when finding minimum/maximum values, insertion points, or solving 'minimize the maximum' problems.