메뉴
Executes Perplexity AI queries via unified Python CLI. Use when conducting web research, asking questions with citations, deep research tasks, reasoning problems, or searching for up-to-date information.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | perplexity-tools |
| type | complex |
| depth | base |
| description | Executes Perplexity AI queries via unified Python CLI. Use when conducting web research, asking questions with citations, deep research tasks, reasoning problems, or searching for up-to-date information. |
Dictum: Specialized models optimize response quality.
Execute Perplexity AI queries via unified Python CLI.
[IMPORTANT] Commands require --query. API key auto-injected via 1Password.
# Quick question—citations (sonar)
uv run .claude/skills/perplexity-tools/scripts/perplexity.py ask --query "What is Effect-TS?"
# Deep research (sonar-deep-research)
uv run .claude/skills/perplexity-tools/scripts/perplexity.py research --query "React 19 new features"
uv run .claude/skills/perplexity-tools/scripts/perplexity.py research --query "Vite 7 migration" --strip-thinking
# Reasoning task (sonar-reasoning-pro)
uv run .claude/skills/perplexity-tools/scripts/perplexity.py reason --query "Compare Vite vs Webpack"
uv run .claude/skills/perplexity-tools/scripts/perplexity.py reason --query "Effect vs RxJS" --strip-thinking
# Web search (sonar)
uv run .claude/skills/perplexity-tools/scripts/perplexity.py search --query "Nx 22 Crystal" --max-results 5
Commands return: {"status": "success|error", ...}.
| [INDEX] | [CMD] | [RESPONSE] |
|---|---|---|
| [1] | ask | {query, response, citations[]} |
| [2] | research | {query, response, citations[]} |
| [3] | reason | {query, response} |
| [4] | search | {query, results[]} |
Creates and configures Claude Code hooks for lifecycle automation. Use when implementing PreToolUse validation, PostToolUse formatting, PermissionRequest auto-approve, custom notifications, session management, or deterministic agent control.
Creates and configures Claude Code agent files (.claude/agents/*.md) with YAML frontmatter, tool permissions, model selection, and system prompt structure. Use when building new agents, configuring agent frontmatter, designing discovery triggers, setting tool permissions, writing system prompts, or selecting agent models.
Creates and configures Claude Code slash commands with YAML frontmatter, argument handling, and tool permissions. Use when building new commands, adding $ARGUMENTS or $1-$N parameters, configuring allowed-tools, organizing command namespaces, or fixing command failures.
Queries Context7 library documentation via unified Python CLI. Use when resolving library IDs, fetching API references, code examples, or conceptual guides for any programming library or framework.
Orchestrates two-round parallel agent research for comprehensive topic exploration. Use when conducting research, exploring complex topics, gathering multi-faceted information, or synthesizing findings from parallel investigation streams.
Synthesizes research findings into design decisions via codebase investigation. Use when (1) translating research into implementation approaches, (2) selecting between design alternatives, (3) executing after /research or deep-research, or (4) preparing input for /plan phase.