浏览 TerryTong-Git 维护的已发布 AI 技能，比较用途与说明，并通过来源仓库了解安装方式。
已收录技能
32收录技能的仓库 Stars 合计
0仓库 Forks
0平均每个技能的仓库 Stars
0同一仓库中的多个技能可能共享 Stars，合计包含重复仓库数据。
Use when writing CS research papers (conference, journal, thesis), reviewing scientific manuscripts, improving academic writing clarity, or preparing IEEE/ACM submissions. Invoke when user mentions paper, manus...
Use when LaTeX documents fail to compile, have undefined references, duplicate labels, or citation errors
Transform research ideas into actionable experiments with hypotheses, iteration rewards, and completion criteria. Use when brainstorming experiments, designing research plans, converting vague ideas into struct...
Documentation for the logistic regression MI estimation experiment (exps_logistic)
Setup and troubleshoot GitHub Actions workflows using anthropics/claude-code-action for automated PR reviews. Use when creating CI/CD workflows that leverage Claude for code review, research validation, or auto...
MCP server configuration, troubleshooting, and Todoist REST API workarounds
Clean up after a feature branch or experiment is complete. This skill deletes the git worktree and branch ONLY AFTER the associated PR has been merged. It also closes any related GitHub issues. Use this after y...
Execute research experiments using TDD methodology. Pops plans from .claude/plans/research_tasks/, implements with smoke/unit/integration tests, and documents results to results.md. Use when: (1) executing the...
Format Google Docs with proper native formatting (headings, bold, tables) instead of markdown. Google Docs does NOT render markdown - you must use the formatting API.
Manages all Google Drive operations within the claude-code folder. Use this skill for ANY Google Drive file creation, updates, or organization. Enforces folder restrictions and maintains the centralized INDEX d...
Documentation for the main LLM performance experiments (exps_performance)
Ethan Perez's tips for empirical alignment research - velocity, experimentation, collaboration
Create well-structured Todoist tasks with Description and Definition of Done sections. Use this skill when creating new Todoist tasks to ensure they have enough context for any team member to understand and cle...
Create well-structured Todoist tasks with Description and Definition of Done sections. Use this skill when creating new Todoist tasks to ensure they have enough context for any team member to understand and cle...
MCP server configuration, troubleshooting, and Todoist REST API workarounds
Format Google Docs with proper native formatting (headings, bold, tables) instead of markdown. Google Docs does NOT render markdown - you must use the formatting API.
Manages all Google Drive operations within the claude-code folder. Use this skill for ANY Google Drive file creation, updates, or organization. Enforces folder restrictions and maintains the centralized INDEX d...
Setup and troubleshoot GitHub Actions workflows using anthropics/claude-code-action for automated PR reviews. Use when creating CI/CD workflows that leverage Claude for code review, research validation, or auto...
Transform research ideas into actionable experiments with hypotheses, iteration rewards, and completion criteria. Use when brainstorming experiments, designing research plans, converting vague ideas into struct...
Execute research experiments using TDD methodology. Pops plans from .claude/plans/research_tasks/, implements with smoke/unit/integration tests, and documents results to results.md. Use when: (1) executing the...
Ethan Perez's tips for empirical alignment research - velocity, experimentation, collaboration
Clean up after a feature branch or experiment is complete. This skill deletes the git worktree and branch ONLY AFTER the associated PR has been merged. It also closes any related GitHub issues. Use this after y...
Use when writing CS research papers (conference, journal, thesis), reviewing scientific manuscripts, improving academic writing clarity, or preparing IEEE/ACM submissions. Invoke when user mentions paper, manus...
Use when LaTeX documents fail to compile, have undefined references, duplicate labels, or citation errors
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。