GitHub
my-skill
Detailed description of what this skill does and when Claude should use it. Include specific keywords that will trigger this skill. Max 1024 characters.
☆ 2查看技能
research llm ai AI 技能
发现 research llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
分类目录: research llm ai
research llm ai 清除筛选
全部技能
GitHub
skill-builder
Create, structure, and optimize FTC skills for the marketplace. Use when creating a new skill, improving an existing skill, scaffolding a plugin, or needing guidance on skill design patterns, triggers, frontmat...
☆ 2查看技能
GitHub
pedro-pathing
Helps write autonomous and teleop code using Pedro Pathing library. Use when creating paths, building autonomous routines, setting up path following, working with Follower, PathChain, BezierLine, or heading int...
☆ 2查看技能
GitHub
prompt
Use when asked about writing or improving AI prompts, instructions, or system messages.
☆ 2查看技能
GitHub
batch
Process multiple variants for classification with progress tracking and summary generation. Invoked via /batch .
☆ 2查看技能
GitHub
agent-review
Review aviation agent code changes for architecture compliance. Use when reviewing changes to shared/aviation_agent/, web/server/api/aviation_agent_chat.py, or configs/aviation_agent/. Verifies UI payload stabi...
☆ 2查看技能
GitHub
agent-test
Analyze aviation agent planner behavioral test results and apply improvement workflow. Use when: running planner tests, adding test cases to planner_test_cases.json, analyzing test failures, improving planner p...
☆ 2查看技能
GitHub
perplexity-routing
Routing guide for selecting the correct Perplexity tool. Reference before spawning any Perplexity agent.
☆ 2查看技能
GitHub
skill-update
Self-improvement protocol for Neo4j agents. Instructs agents to report skill updates needed.
☆ 2查看技能
GitHub
agent-run
Run prompt with OpenAI or Gemini provider via agent CLI
☆ 2查看技能
GitHub
evidence-standards
Evidence citation and domain scope standards for Neo4j subagents. Prevents hallucination and ensures audit trail.
☆ 2查看技能
GitHub
multi-compare
Run the same prompt with Claude, OpenAI, and Gemini in parallel, then return back exact replies you got back without modifying the results one bit.
☆ 2查看技能
GitHub
perplexity-reason
Multi-step reasoning with Chain-of-Thought. Use for 'why' questions and comparisons.
☆ 2查看技能
GitHub
neo4j-news
Query news articles from Neo4j with fulltext and vector search. Use when fetching news data or searching news content.
☆ 2查看技能
GitHub
sg
Metacognitive oversight. "$sg review" for on-demand evaluation, "$sg init" to set up, "$sg audit" to review decisions.
☆ 2查看技能
GitHub
bottle
Open Horizon Labs orchestration. "$bottle init" for setup, "$bottle dive" to start sessions, "$bottle web-context" for fresh docs.
☆ 2查看技能
GitHub
autonomous-operations
Autonomous homelab operations using OODA loop (Observe, Orient, Decide, Act) - use when reviewing system state, planning autonomous actions, or investigating operational issues
☆ 2查看技能
GitHub
tmux-team
Coordinate with other AI agents running in tmux panes. Use this skill when you need to delegate tasks, request reviews, or collaborate with agents like Codex, Gemini, or other Claude instances.
☆ 2查看技能
GitHub
tmux-team
Communicate with other AI agents in tmux panes. Use when you need to talk to codex, claude, gemini, or other agents.
☆ 2查看技能
GitHub
skill-creation
SOP for creating new Claude Code skills. Use when adding a new skill to any project or globally.
☆ 2查看技能
GitHub
cli-generator
Generate AI-friendly Python CLIs using Click, Pydantic, and uv. Use when user wants to create a new CLI tool that follows best practices for agentic coding environments.
☆ 2查看技能
GitHub
update-claude-md
ユーザと対話してCLAUDE.mdを初期化・更新する
☆ 2查看技能
GitHub
mlai-points
Manage MLAI points system - check balance, book coworking, claim tasks, redeem rewards
☆ 2查看技能
GitHub
session-hook
This skill should be used when the user asks to "create a session hook", "add a temporary hook", "create a hook for this session", "set up a hook that activates immediately", "configure a one-time hook", or men...
☆ 2查看技能
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。