Tag: llm-agents
Event-driven background processing for AI agents
This skill facilitates decoupled, event-driven background workflows for agents, allowing complex processes to run asynchronously outside the main chat request lifecycle. Developers define pipelines using structured sources, semantic signals…
Dingo Article Fact-Checker
Extracts and verifies factual claims from Markdown, text, or JSONL files using the Dingo SDK and web search integration. It provides a structured report including accuracy scores and evidence for disputed claims.
Meta-Agent Supervisor for Parallel Development Workflows
This meta-agent supervisor manages multiple parallel development agents within a single tmux session. It automates worktree lifecycle management, monitors agent status, handles checkpoints, and safely recycles completed work.
Managed persistent memory layer for AI agents
Mem0 provides a managed, API-driven memory layer enabling AI applications to store, retrieve, and manage long-term user context. Developers can integrate this persistent memory via Python or TypeScript SDKs, enhancing agent capabilities thr…
Migrates Agent Markdown Memory to Enforcement System
This utility bridges the agent-architect-kit's markdown memory structure to the ThumbGate feedback system. It parses per-role markdown files, converting structured learnings and mistakes into actionable, queryable feedback signals for runti…
Agent Run Governance and Guardrails
This skill provides comprehensive governance for programmatic agent runs, ensuring controlled execution across local, cloud, or self-hosted environments. It enforces pre-flight checks, scope bounding, and evidence capture before agents can …
Dingo Article Fact-Checker
An agentic skill that extracts and verifies factual claims within articles using web search evidence. It generates detailed reports including accuracy scores and evidence for identified false claims.
Agent Safety Gates and Failure Pattern Prevention
ThumbGate implements pre-action gates for AI agents, capturing structured thumbs-up/down feedback on tool usage. It automatically generates prevention rules from repeated failures, blocking known-bad patterns before execution via the MCP Pr…
ACP Coding Agent Request Router
This skill routes plain-language requests for various external coding agents (e.g., Copilot, Claude, Gemini) into the appropriate execution context. It manages flow selection between the OpenClaw ACP runtime sessions and direct acpx CLI int…
Skill Creation and Iterative Improvement Agent
This skill guides users through the entire lifecycle of developing agentic skills. It assists with drafting, running quantitative evaluations, analysing benchmarks, and iteratively refining the skill description for optimal triggering accur…
Agent Skill Authoring and Evaluation
Design, refine, and audit reusable agent skills by creating structured SKILL.md files and evaluating trigger precision. The process includes auditing skill collections for redundancy and designing testable behaviour through evaluation promp…
Programmatic Coding Agent Management
Enables the programmatic launch and management of coding agents, such as Claude Code and Codex CLI, as background processes.
Memory Consolidation and Cleanup Protocol
A protocol for cleaning and consolidating stored memories by removing duplicates, deleting expired entries, and rewriting vague information. It automates the transformation of raw observations into structured, high-quality knowledge.
Mem0 Managed Memory Layer for AI Agents
A managed memory layer for AI applications that provides persistent, long-term user context via Python and TypeScript SDKs. It enables developers to store, retrieve, and manage user memories through an API to personalise agentic interaction…
Mem0 MCP Memory Management Protocol
A protocol for agents to maintain persistent context across sessions using Mem0 MCP tools, featuring strategic memory retrieval and structured storage with metadata filtering.
OpenAI Developer Documentation Retrieval
Provides a workflow for retrieving authoritative OpenAI API documentation, schemas, and endpoint specifications via MCP server tools. It enables agents to fetch exact markdown and OpenAPI specs to ensure accurate responses regarding models,…
TradeMemory: AI Trading Memory and Strategy Evolution
An MCP-compatible protocol providing persistent trading memory with outcome-weighted recall and an LLM-powered strategy evolution engine. It enables agents to record trades, analyse behavioural patterns, and autonomously discover trading st…
Coding Skill with Humorous Comments
An agentic skill for general programming tasks that ensures all generated code includes a humorous comment.