文件操作
文件系统与批量文件任务
update-focus
flonat
"Update current-focus.md with a structured session summary. Preserves the document's rich structure: weekly focus, session history rotation, open loops, mental state. Use at end of work sessions or when the stop hook nudges."
init-project-research
flonat
"Bootstrap a research project: interview for details, scaffold directory, create Overleaf symlink, init git, and sync with context library and Notion. Triggers: 'new research project', 'start a new paper'. Not for lightweight setups — use /init-project-light instead."
consolidate-memory
flonat
"Consolidate MEMORY.md files: prune duplicates, merge overlapping entries, generate abstractions, and remove stale knowledge. Triggers: 'clean up MEMORY.md', 'prune stale knowledge'. Inspired by npcsh sleep/dream cycles."
literature
flonat
"Academic literature discovery, synthesis, and bibliography management. Find papers, verify citations, create .bib files, download PDFs, and synthesize literature narratives. Includes OpenAlex, Scopus, and Web of Science API integration for structured scholarly queries."
latex-autofix
flonat
"LaTeX compilation with autonomous error resolution. Build artifacts go to out/, PDF is copied back to source directory. Parses logs, auto-fixes known errors (missing packages, font conflicts, citation issues, bad paths, stale cache), and runs citation audit on success."
project-safety
flonat
"Set up safety rules and folder structures for research projects. Prevent accidental data loss when Claude reorganizes files. Triggers: 'protect my data', 'set up project safety rules'. Not for auditing structure — use /audit-project-research."
update-project-doc
flonat
"Update a project's own documentation (CLAUDE.md, README.md, docs/*.md) to reflect its current state. Detects stale file trees, timestamps, counts, and next steps. Includes a leanness audit: flags CLAUDE.md > 200 lines, sections > 15 lines of reference material, SKILL.md > 300 lines, agents > 400 lines, and context files > 200 lines — with auto-extraction to docs/ or references/."
save-context
flonat
"Save information from conversations to the user's task management context library. Use when the user says: 'save this to my context', 'remember this', 'add to my profile', 'update my current focus', 'add this person to my contacts', 'save this project info', or any variation of wanting to persist information for future AI sessions."
validate-bib
flonat
"Cross-reference \cite{} keys against .bib files or embedded \bibitem entries. Finds missing, unused, and typo'd citation keys. Deep verification mode spawns parallel agents for DOI/metadata validation at scale. Read-only in standard mode."
insights-deck
flonat
"Generate timestamped Claude Code insights report and Beamer presentation. Runs /insights, archives HTML, then builds a rhetoric-driven deck from the findings. Triggers: 'generate insights report', 'how is my Claude Code doing'."
split-pdf
flonat
Download, split, and deeply read academic PDFs. Use when asked to read, review, or summarize an academic paper. Splits PDFs into 4-page chunks, reads them in small batches, and produces structured reading notes — avoiding context window crashes and shallow comprehension.
beamer-deck
flonat
"Generate academic Beamer presentations with multi-agent review. Builds original themes, applies rhetoric principles, iterates until zero warnings. Triggers: 'make slides', 'create a presentation', 'build a talk'. For web-shareable HTML slides, use /quarto-deck instead."
code-archaeology
flonat
"Systematically review and understand old code, data, and analysis files. For reviving old projects, auditing inherited code, or preparing for R&R. Triggers: 'what does this old code do', 'understand this legacy project', 'revive this project'. Not for active code review — use /code-review."
latex
flonat
"LaTeX document compilation and management. When Claude needs to compile LaTeX documents (.tex files) for papers, presentations, or other academic content. Triggers: 'compile this tex file', 'build my paper'. Prefer /latex-autofix for error-resilient compilation."
figma-designer
zhaono1
Analyzes Figma designs and generates implementation-ready PRDs with detailed visual specifications. Use when user provides Figma link or uploads design screenshots. Requires Figma MCP server connection.
architecting-solutions
zhaono1
Designs technical solutions and architecture. Use when user says "design solution", "architecture design", "technical design", or "方案设计" WITHOUT mentioning PRD. For PRD-specific work, use prd-planner skill instead.
parallel-task
am-will
Only to be triggered by explicit /parallel-task commands.
role-creator
am-will
Create and install Codex custom agent roles in ~/.codex/config.toml, generate role config files, enforce supported keys, and guide users through required role inputs (model, reasoning effort, developer_instructions).
context7
am-will
Fetch up-to-date library documentation via Context7 API. Use PROACTIVELY when: (1) Working with ANY external library (React, Next.js, Supabase, etc.) (2) User asks about library APIs, patterns, or best practices (3) Implementing features that rely on third-party packages (4) Debugging library-specific issues (5) Need current documentation beyond training data cutoff (6) AND MOST IMPORTANTLY, when you are installing dependencies, libraries, or frameworks you should ALWAYS check the docs to see what the latest versions are. Do not rely on outdated knowledge. Always prefer this over guessing library APIs or using outdated knowledge.
swarm-planner
am-will
[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.
read-github
am-will
Read and search GitHub repository documentation via gitmcp.io MCP service. WHEN TO USE: - User provides a GitHub URL - User mentions a specific repo in owner/repo format - User asks "what does this repo do?", "read the docs for X repo", or similar - User wants to search code or docs within a repo
mcp-server
WellApp-ai
Guide for creating new MCP server integrations
team-routing
WellApp-ai
Detect domain from context and find appropriate team member
design-context
WellApp-ai
Refresh UI/UX context from design system, Storybook, and codebase