agent-md-refactor
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow…
Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7) or workspace questions.
$ npx -y skills add softaworks/agent-toolkit --skill perplexity --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/perplexityContext preview
The summary Claude sees to decide when to auto-load this skill.
Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7) or workspace questions.
name: perplexity description: Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7) or workspace questions.
Use ONLY when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7), gt CLI (use Graphite MCP), or workspace questions (use Nx MCP).
**Which Perplexity tool?**
**NOT Perplexity - use these instead:**
**When to use:**
**Default parameters (ALWAYS USE):**
mcp__perplexity__perplexity_search({
query: "your search query",
max_results: 3, // Default is 10 - too many!
max_tokens_per_page: 512 // Reduce per-result content
})**When to increase limits:** Only if:
// Increased limits (use sparingly)
mcp__perplexity__perplexity_search({
query: "complex topic",
max_results: 5,
max_tokens_per_page: 1024
})**When to use:**
**Usage:**
mcp__perplexity__perplexity_ask({
messages: [
{
role: "user",
content: "Explain how postgres advisory locks work"
}
]
})**NOT for:**
**NEVER use:** `mcp__perplexity__perplexity_research`
**Use instead:** Researcher agent (`/research <topic>`)
**Priority order:** 1. **Context7 MCP** - Library/framework docs 2. **Graphite MCP** - Any `gt` CLI mention 3. **Nx MCP** - THIS workspace questions 4. **Perplexity Search** - Generic searches 5. **Perplexity Ask** - Conversational answers 6. **Researcher agent** - Deep multi-source research 7. **WebSearch** - Last resort (after Perplexity exhausted)
**✅ CORRECT - Use Perplexity Search:**
**✅ CORRECT - Use Perplexity Ask:**
**❌ WRONG - Use Context7 instead:**
**❌ WRONG - Use Graphite MCP instead:**
**❌ WRONG - Use Nx MCP instead:**
Opinionated skills shared by @leonardocouy for improving daily work efficiency with Claude Code. Skills are packaged instructions and scripts that extend agent capabilities across development, documentation, planning, and professional workflows.
Repo: softaworks/agent-toolkit
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow…
Create API handoff documentation for frontend developers. Use when backend work is complete…
Generate architecture documentation using C4 model Mermaid diagrams. Use when asked to create…
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex…
This skill should be used when creating a Claude Code slash command. Use when users ask to…
Create high-quality git commits: review/stage intended changes, split into logical commits,…