Helps detect permission creep in AI agent skills — flags when a skill's actual code accesses resources far beyond what its declared purpose requires, like a "fix typo" skill reading your .env file.

AI-powered search using your local Perplexica instance. Runs deep research (quality mode) with web search and LLM reasoning; returns answers with cited sources in OpenClaw while keeping search/RAG state in Perplexica. Use when the user asks to "search with Perplexica", "ask Perplexica", "deep search", "research with sources", or wants AI search with citations. Local-only; no data exfiltration.

Deep search via Perplexity API. Three modes: search (quick facts), reason (complex analysis), research (in-depth reports). Returns AI-grounded answers with citations.

Use Perplexity API for web-grounded AI search. Use when user needs up-to-date information with source citations, factual queries about current events, or research-style answers. Default when user mentions Perplexity or needs current information with references.

Web Search Skill

Conduct deep research using Perplexity Agent API with web search, reasoning, and multi-model analysis. Use when the user needs current information, market research, trend analysis, investment insights, or comprehensive research on any topic requiring web search and reasoning capabilities.

Add persistent memory to any agent so it can remember prior work, maintain context across sessions, and continue long-running workflows. Use when: (1) remembering facts or preferences for later, (2) recalling stored memories by topic or intent, (3) forgetting/removing memories matching a query. NOT for: web search, file system search, or code search — use other tools for those.

Personal relationship manager powered by Feishu/Lark Bitable. Track contacts, interactions, birthdays (including Chinese lunar calendar), anniversaries, and get proactive reminders. Never forget a birthday again.

Turn any AI agent into a smart shopping research team — Diamond Search methodology with 7 agents in 3 layers

Pull personal data (emails, issues) and propose outbound actions (drafts, replies) through the PersonalDataHub access control gateway. Data is filtered, redacted, and shaped by the owner's policy before reaching the agent.

Pull personal data (emails, issues) and propose outbound actions (drafts, replies) through the PersonalDataHub access control gateway. Data is filtered, redacted, and shaped by the owner's policy before reaching the agent.

Batch-pet Aavegotchis on Base via Bankr with cooldown checks, reminder automation, and natural-language routing.

Generate custom pet portraits using each::sense AI. Create realistic, artistic, and stylized pet portraits from photos - including cartoon, renaissance, watercolor, pop art, anime styles, and custom product mockups.

PR 收口自动化。单 PR 串行合并与多 PR 批量清理，减少重复人工操作。

PostgreSQL vector database skill with pgvector extension. Enables vector similarity search, embeddings storage, RAG (Retrieval-Augmented Generation) pipelines, and hybrid search combining vector and keyword search. Use when: storing/retrieving embeddings, building AI applications with vector search, implementing RAG, similarity matching, semantic search, or any use case requiring vector database functionality.

Control PhantomBuster automation agents via API. List agents, launch automations, get output/results, check status, and abort running agents. Use when the user needs to run LinkedIn scraping, Twitter automation, lead generation phantoms, or any PhantomBuster workflow.

Pharmaceutical System Bidding Information Collection Skill

Literature Agent v1.0.0

Compliant AlphaFold Agent for protein structure retrieval, ESMFold prediction, binding site detection, and RDKit ligand docking. Fetches public PDB/AlphaFold DB structures, predicts folds via ESMFold (HuggingFace), identifies binding pockets, and performs basic molecular docking. Chains from Chemistry Query (receives SMILES for docking) and feeds into IP Expansion and Catalyst Design. Triggers on alphafold, fold, PDB, docking, structure, protein, binding site, pocket, UniProt, KRAS, target.

Fetches and analyzes FAERS (FDA Adverse Event Reporting System) data from openFDA API. Supports drug names and SMILES (resolves via PubChem). Generates: events list, yearly trends (counts), top reactions/outcomes as JSON + matplotlib bar chart PNGs.

Generate a full Phoenix JSON API from an OpenAPI spec or natural language description. Creates contexts, Ecto schemas, migrations, controllers, JSON views/renderers, router entries, ExUnit tests with factories, auth plugs, and tenant scoping. Use when building a new Phoenix REST API, adding CRUD endpoints, scaffolding resources, or converting an OpenAPI YAML into a Phoenix project.

Passive financial tracking plugin for PhoenixClaw. Automatically detects expenses and income from conversations and payment screenshots. Use when: - User mentions money/spending (any language) - User shares payment screenshots (WeChat Pay, Alipay, etc.) - User asks about finances ("How much did I spend?", "My budget") - User wants expense reports ("Monthly summary", "Spending analysis")

Colorize black and white photos using each::sense AI. Bring old family portraits, historical images, vintage photographs, and archival footage to life with intelligent, context-aware colorization.

Personal Insight Engine (PIE) - A strategic analysis tool that scans local session logs (memory/*.md) and extracts 3 strategic insights using LLMs.