2.4K skills · sorted by relevance
Automate Endorsal operations through Rube MCP, a connection for agent tools. The skill searches for suitable actions, checks that the service connection is active, and executes tasks using the latest tool input requirements.
Build Python features that identify a speaker’s intent and extract details such as names from conversation text using Azure. Get guidance on request structure, authentication, client cleanup, and exception handling.
Collect an X conversation from its root post ID, including replies and nested replies visible to the logged-in account. Return structured text, author details, engagement counts, and reply relationships for reviewing discussions or preparing further analysis.
Turn exported AI chats and agent session logs into dated, searchable pages in gbrain. Check for missing conversations, extract facts, and trace when a topic first appeared or how an idea developed, with quotes and dated references.
Connect a ChatGPT or Claude account to import conversation history into knowledge pages. Sync new and changed conversations incrementally, revisit recent history to catch updates, and optionally enable scheduled syncing.
Assess how applications use encryption, signed tokens, and random values. Identify implementation weaknesses, select relevant testing tools, and document causes and fixes for issues involving encryption modes, RSA parameters, predictable randomness, and key derivation.
Review AI agent spending by conversation, with each session’s start time, message count, main model, and total cost. Use the results to identify expensive sessions and understand typical costs before planning longer work.
End-to-end Coval adversarial / red-team testing workflow. Builds one adversarial test set (12 core attack vectors plus legitimate controls, each with an expected-behavior checklist), creates a persistent "Adversarial User" persona and a Composite Evaluation metric that scores each scenario against its own expected behaviors, launches a multi-iteration run against the agent (voice or chat), polls for completion, builds a per-scenario pass/fail scorecard, and creates a saved report grouped by Test Case. Use when a user wants to follow the Adversarial & Red-Team Testing cookbook (https://docs.coval.dev/guides/adversarial-red-team-testing) without doing each step by hand. Triggers: "adversarial test set", "red team my agent", "jailbreak / prompt-injection testing", "test my agent against bad actors".
The English summary is being prepared. Showing the original description.
Plan and measure defensive deception operations with MITRE Engage. Connect decoy systems and credentials to specific attacker techniques, define measurable objectives, and document operating boundaries, response procedures, and criteria for assessing results.
Automate X direct message workflows by finding conversations awaiting replies, reading history, and sending text prepared by the calling agent. Also search for users, check messaging permissions, start conversations, and verify delivery.
Analyze successful Google and Meta ads to find useful patterns in headlines, body text, and calls to action. Generate new copy variants that preserve those patterns, with platform formatting, test priorities, and suggested pairings for comparison.
Assess web applications for path traversal, a flaw that exposes files outside intended folders. Follow structured checks to identify vulnerable inputs, document demonstrated access, assess data exposure, and prepare remediation guidance.
Draft, confirm, and post a single conversational reply to GitHub PR conversation comments (issue comments). The reply addresses all tracked items in one natural-prose message. Use when the user asks to "reply to PR conversation", "post PR conversation replies", or "draft PR conversation messages".
The English summary is being prepared. Showing the original description.
Conversation patterns and interaction protocols for multi-agent systems. Covers request/response, pub/sub, blackboard, delegation chains, debate, critique, consensus, fan-out/fan-in, supervisor-worker, and peer negotiation. Deep analysis of AutoGen conversation patterns, CrewAI delegation, LangGraph state passing, and FIPA-ACL performatives. Teaches how to design what agents say to each other and in what order. Activate on: "agent conversation", "agent protocol", "multi-agent debate", "agent delegation", "supervisor worker pattern", "agent voting", "consensus protocol", "fan-out fan-in", "agent negotiation", "blackboard pattern", "agent dialogue", "conversation topology", "agent handoff". NOT for: wire format or serialization (use agent-interchange-formats), orchestration infrastructure (use agentic-infrastructure-2026), single agent behavior (use agentic-patterns).
The English summary is being prepared. Showing the original description.
Implement caching and data conversion for syncable entities in Twenty's server code. Build lookup maps, convert stored records and inputs into flat representations, and resolve references to universal identifiers for later validation and processing.
Design memory systems that help AI assistants retain conversation information and retrieve it when relevant. Explore short-term, long-term, and entity memory, along with memory consolidation, prompt integration, storage lifecycle management, and separation between users.
Create evaluation drafts for existing skills using actual conversations and user corrections. Produce criteria and repeatable test cases, distinguish evidence from specification assumptions, and prepare an anonymized draft for human review.
Create paid ad headlines and body copy tailored to each platform's character limits. Use existing performance data to develop variations, explore new messaging angles, and check copy for length, quality, and potential rejection risks.
Review code changes from three critical perspectives: production failures, maintainability, and security. Get a consolidated report that ranks findings by severity and provides merge guidance, helping examine assumptions that an ordinary self-review may overlook.
Request an owner’s permission to use a listed keychain credential needed by a command. An approval card appears in the conversation, and owner approval automatically reruns the blocked command with access shared across that conversation.
Build image conversations with LLaVA, a model that connects image recognition with language. This skill guides setup, image descriptions, visual questions, and follow-up conversations, with examples for Python, command-line use, and a Gradio interface.
Create a new Claude Code session containing only the last quarter of the current conversation. Preserve the most recent work, reduce conversation tokens, and get a command to resume the copied session directly.
Create a new Claude Code session from the later half of the current conversation. Keep recent work while reducing conversation tokens, then receive a command to resume the copied session directly.
Configure a new OpenRig agent seat, a managed place for an agent to run, using a prior Claude or Codex conversation. Covers fork settings, new session identities, and checks that distinguish forking from restoring.