Menu
Routes tasks to locally installed CLI tools using semantic matching. Triggers on tasks requiring shell commands, file operations, code search, data processing, visualization, or external tool invocation. Uses cli-index for semantic routing.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use this skill whenever the user wants high-quality semantic retrieval, cross-textbook synthesis, reference verification, or authority-ranked question answering over the PageIndex corpus. Trigger on requests like "find which texts cover X", "compare sources", "retrieve semantically", "verify this claim from my textbooks", "build a reading list from the corpus", "cluster by topic", or any PageIndex question where naรฏve filename search would miss relevant material. This skill teaches a state-of-the-art hybrid retrieval workflow over the PageIndex catalog and live MCP extraction surface.
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming. Use when you need to build complex AI systems, program LMs declaratively, optimize prompts automatically, create modular AI pipelines, or build RAG systems and agents.
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
Real-time observability dashboard for multi-agent Claude Code sessions. Visualize agent interactions, tool usage, and session flows in real-time through a web dashboard. Track multiple agents running in parallel with swim lane visualization, event filtering, and live charts. **Key Features:** - ๐ด Real-time event streaming via WebSocket - ๐ Agent swim lanes showing parallel execution - ๐ Event filtering by agent, session, event type - ๐ Live charts for tool usage patterns - ๐พ Filesystem-based (no database required) **Inspired by [@indydevdan](https://github.com/indydevdan)**'s work on multi-agent observability. **Our approach:** Filesystem + in-memory streaming vs. indydevdan's SQLite database approach.
Track and optimize agent specialization during methodology development. Use when agent specialization emerges (generic agents show >5x performance gap), multi-experiment comparison needed, or methodology transferability analysis required. Captures agent set evolution (Aโ tracking), meta-agent evolution (Mโ tracking), specialization decisions (when/why to create specialized agents), and reusability assessment (universal vs domain-specific vs task-specific). Enables systematic cross-experiment learning and optimized Mโ evolution. 2-3 hours overhead per experiment.
Routes tasks to appropriate Task tool agents (subagents). Triggers on complex multi-step tasks, research, code review, exploration, or any task benefiting from specialized agent execution. Matches intent to agent types.
| name | cli-router |
| description | Routes tasks to locally installed CLI tools using semantic matching. Triggers on tasks requiring shell commands, file operations, code search, data processing, visualization, or external tool invocation. Uses cli-index for semantic routing. |
Routes tasks to the most appropriate CLI tool based on semantic intent matching.
Activate when task involves:
| Category | Tools | Triggers |
|---|---|---|
| ai_llm | claude, gemini, codex, amp, aider | AI help, implement, explain |
| semantic_search | ck, ast-grep, osgrep | semantic search, find code, pattern |
| knowledge_graph | cypher-shell, turbovault | graph, neo4j, knowledge |
| data_processing | qsv, csvtk, nu, jq | csv, json, transform, data |
| file_navigation | yazi, broot, fd, rg | browse, find files, navigate |
| code_quality | bat, difftastic, delta | diff, syntax, format |
| visualization | d2, mermaid, mermaid-ascii | diagram, flowchart, visual |
| mcp_tools | mcp-skillset, lootbox, automcp | mcp, skills, tools |
| productivity | fabric, atuin, btop, zellij | patterns, history, monitor |
| document | docling, pdf-search, qmd | pdf, document, markdown |
# Use cli-index for semantic routing
cli-index route "{user_intent}"
# Example output:
# tool: ck
# category: semantic_search
# confidence: 0.85
# command_hint: ck --sem "async functions" src/
CLI Task Detected
โ
โโโ Code search?
โ โโโ Semantic? โ ck --sem
โ โโโ Pattern/AST? โ ast-grep
โ โโโ Grep-like? โ rg
โ
โโโ File operations?
โ โโโ Navigate? โ yazi | broot
โ โโโ Find files? โ fd
โ โโโ Search content? โ rg
โ
โโโ Data processing?
โ โโโ CSV? โ qsv | csvtk
โ โโโ JSON? โ jq | sj
โ โโโ Structured? โ nu
โ
โโโ Visualization?
โ โโโ Diagrams? โ d2
โ โโโ Flowcharts? โ mermaid
โ โโโ ASCII? โ mermaid-ascii
โ
โโโ AI assistance?
โ โโโ Claude preferred? โ claude
โ โโโ Long context? โ gemini
โ โโโ OpenAI? โ codex
โ
โโโ Document processing?
โโโ PDF? โ docling | pdf-search
โโโ Markdown? โ qmd
# Search for matching tools
cli-index search "semantic code search"
# Route to best tool
cli-index route "find async functions in codebase"
# List tools by category
cli-index list semantic_search
# Get tool info
cli-index info ck
# Suggest tool chain
cli-index suggest "search code then visualize dependencies"
# Verify all tools available
cli-index verify
semantic_search: ck --sem "query" path/
pattern_search: ast-grep -p "pattern"
file_find: fd "pattern"
content_search: rg "pattern"
csv_process: qsv [cmd] file.csv
json_query: jq ".path" file.json
diagram: d2 input.d2 output.svg
ai_help: claude -p "query"