self-improving-agent
Always-on lightweight observer. After EVERY user message, silently check: (1) did the user correct me or express a preference? (2) did the user express…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-06 00:14
25,709 results
Always-on lightweight observer. After EVERY user message, silently check: (1) did the user correct me or express a preference? (2) did the user express…
Use this skill when the user asks to parse, perform multi-format document conversion or spatially extract text from an unstructured file (PDF, DOCX, PPTX,…
Framework for the use of generative AI for State public officials (DINUM/DITP/DGAFP). 5 principles: responsibility, choice of tool according to the data,…
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web…
Use when a task needs multiple subagents or workstreams, when several tasks can run concurrently, or when blockers, shared files, mutable resources, handoffs,…
Use when starting, moving, pausing, resuming, or finishing agent work; maintaining a capped Kanban board, current handoff state, or release-ready changelog; or…
Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity. Use this skill when: (1) deciding which model to use for a task,…
MCP server management for Claude Desktop. Profile-aware - reads MCP server inventory from profile.mcp.servers{} and config path from…
Use Evolver, the official EvoMap GEP-powered self-evolution engine, from WorkBuddy / CodeBuddy. Trigger when the user asks about Evolver, EvoMap, GEP, Genes,…
Helps users discover agent skills from the open ecosystem. Searches skills.sh and presents options for installation via the built-in skill_manager tool.
Build an intelligent people map for a target company by combining Attio CRM, LinkedIn (Anysite MCP), Extruct enrichment, Gmail, and Granola meeting notes. Goes…
Draft a follow-up email after a call. Pulls meeting context from Granola (MCP), recent email history from Gmail (MCP), and pending tasks from Attio. Triggers…
Generate a pre-call briefing for an upcoming meeting. Pulls deal/relationship context from Attio, recent interactions from Gmail (MCP), past meeting notes from…
Use this whenever debugging an iOS DAT app with local DAT Inspector MCP tools, live device events, Meta AI app/device boundary issues, permissions,…
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
Coordinate complex coding and knowledge-work tasks inside a user's target repository with Codex's current main agent and in-task internal subagents. Use for…
Codex ends its turn on the first assistant message with no tool call, and an unattended dispatch never sends another user message. Use when a Codex Agent must…
Explains browser storage patterns including cookies, localStorage, sessionStorage, and when to use each. Use when deciding how to persist client-side data,…
A learning partner skill grounded in neuroscience and philosophy. Use when you want to actually learn a concept (not just get an answer), quiz yourself on a…
Before a session closes, launches an INDEPENDENT auditor sub-agent that reviews the session transcript against the configurator's verifiable rules (CLAUDE.md,…
Schedule recurring AI agent prompts using intervals or cron expressions. Use when users need to run prompts periodically, automate agent tasks on a schedule,…
Hand off work in progress or finished to another agent for continuation or review. Produce a structured summary with enough background context, what was worked…
Use when creating a Firetiger monitoring agent, installing a prebuilt catalog agent, or configuring an agent's triggers and schedules — monitoring something…
Design-first ideation workflow — explore user intent, clarify constraints, propose approaches, and produce an approved design document before planning