magic3007

magic3007/dotfiles

Instructions file CodexOpenCode

Instructions for magic3007/dotfiles, covering agents.md, commands, architecture, two-phase installation (install.conf.yaml) and symlink model.

magic3007/dotfiles

Instructions file

Instructions for magic3007/dotfiles, covering claude.md, commands, ⚠️ 重要约束, architecture and two-phase installation (install.conf.yaml).

magic3007/dotfiles

Command

Rebase from the latest origin/main, squash the commits from it, and then create a PR on github with intelligent commit messages based on staged changes. Invoke with /create-pr.

magic3007/dotfiles

Command

Generate intelligent commit messages based on staged changes. Invoke with /gen-commit-msg.

magic3007/dotfiles

Command

Intelligent PR code review with dynamic agent allocation based on change types.

magic3007/dotfiles

Command

Automatically scan the repository for unstaged/untracked changes, group them into logical commits using hunk-level analysis, stage and commit them following Conventional Commits. Invoke with /scan-commit.

magic3007/dotfiles

Command

Analyze staged changes and split them into multiple logical commits following Conventional Commits. Invoke with /smart-commit.

magic3007/dotfiles

Skill Claude CodeCodex

Analyze a GitHub/GitLab Pull Request by fetching its diff, reading its web description, and generating a comprehensive document. Use when the user provides a PR link and wants to understand what changes the PR introduces, or asks to review/analyze/summarize a pull request.

magic3007/dotfiles

Skill Claude CodeCodex

Run Claude Code commands (including /insights, /doctor, custom prompts) via system crontab in non-interactive mode. Use when: (1) setting up daily/weekly automated Claude Code tasks, (2) scheduling reports or analysis via cron, (3) running Claude Code with third-party API backends (DeepSeek, Qwen, etc.) in headless…

magic3007/dotfiles

Skill Claude CodeCodex

Claudeception is a continuous learning system that extracts reusable knowledge from work sessions. Triggers: (1) /claudeception command to review session learnings, (2) "save this as a skill" or "extract a skill from this", (3) "what did we learn?", (4) After any task involving non-obvious debugging, workarounds, or…

magic3007/dotfiles

Skill Claude CodeCodex

Debug getServerSideProps and getStaticProps errors in Next.js. Use when: (1) Page shows generic error but browser console is empty, (2) API routes return 500 with no details, (3) Server-side code fails silently, (4) Error only occurs on refresh not client navigation. Check terminal/server logs instead of browser for…

magic3007/dotfiles

Skill Claude CodeCodex

Fix Prisma "Too many connections" and connection pool exhaustion errors in serverless environments (Vercel, AWS Lambda, Netlify). Use when: (1) Error "P2024: Timed out fetching a new connection from the pool", (2) PostgreSQL "too many connections for role", (3) Database works locally but fails in production…

magic3007/dotfiles

Skill Claude CodeCodex

Detect and resolve TypeScript/JavaScript circular import dependencies. Use when: (1) "Cannot access 'X' before initialization" at runtime, (2) Import returns undefined unexpectedly, (3) "ReferenceError: Cannot access X before initialization", (4) Type errors that disappear when you change import order, (5) Jest/Vitest…

magic3007/dotfiles

Skill Claude CodeCodex

Rebase from the latest origin/main, squash the commits from it, and then create a PR on github with intelligent commit messages based on staged changes.

magic3007/dotfiles

Skill Claude CodeCodex

A guide for sending correctly formatted messages through a Feishu custom bot webhook. Feishu is a workplace messaging platform, and a webhook is a URL that accepts automated messages from another program.

magic3007/dotfiles

Skill Claude CodeCodex

Generate intelligent commit messages based on staged changes following Conventional Commits format.

magic3007/dotfiles

Skill Claude CodeCodex

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

magic3007/dotfiles

Skill Claude CodeCodex

Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires…

magic3007/dotfiles

Skill Claude CodeCodex

A Chinese-language text editor that removes common signs of machine-written prose and makes writing sound more natural. It keeps the original meaning while adjusting tone, rhythm, structure, and overly generic wording.

magic3007/dotfiles

Skill Claude CodeCodex

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…

magic3007/dotfiles

Skill Claude CodeCodex

Use when the user wants to learn or understand a technical concept (an algorithm, a math derivation, an ML architecture, a systems internal) rather than just get a one-shot answer — triggers include "explain X", "teach me X", "help me understand X", or being stuck on a concept while reading a paper or code. Probe the…

magic3007/dotfiles

Skill Claude CodeCodex

Use when the user asks to create, scaffold, or edit Jupyter notebooks (.ipynb) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script newnotebook.py to generate a clean starting notebook.

magic3007/dotfiles

Skill Claude CodeCodex

A usage guide for connecting AI agents to Notion databases through MCP. Notion is a workspace for documents and databases, while a database view is a saved way of displaying database records.

magic3007/dotfiles

Skill Claude CodeCodex

Intelligent PR code review with dynamic agent allocation based on change types. Analyzes PR changes and generates targeted review tasks.