Results for “agent-evolution”

`task-agent`: use when document, key-value, wide-column, or graph storage changes access, partitioning, consistency, or evolution; skip vendor-only mentions and unchanged storage.

Agent validation overhaul: reward weight overrides, fitness decline gate, pinned data, staged experiments

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

Improve agent reliability over time — diagnose why agents fail and fix the setup. Triggers on: agent keeps failing, same mistake again, agent not improving, make agent smarter, agent quality plateau, agents ignore skills, agent skips tests, fix agent behavior, agent unreliable, improve agent setup, self-improving harness, agents worse over time, tune agent instructions, agent going in circles, agent ignores AGENTS.md, repeated agent errors. Requires harness v0 and eval harness. AUTO-ROUTED from harness-engineering on symptoms. Not first setup — harness-generation first.

Implement iterative evaluation and refinement loops for AI agent outputs, using self-critique, evaluator-optimizer patterns, and rubric-based scoring to improve quality.

Scaffold and develop AI agents using OpenAI Agents SDK patterns, covering agent definition, tools, guardrails, handoffs, context, RAG pipelines, streaming, API routes, testing, and debugging.

Agent validation v4.3.0 — Make agents act effectively by disabling harmful actions, lowering gates, and injecting cross-run learning

Agent skill for agent - invoke with $agent-agent

Casting personas: rapid generation from diverse inputs, registry-based persistence and lifecycle, data-driven evolution, inter-agent sync. Not for UI walkthroughs (Echo) or user research (Field).

Decision-theoretic framework for agents embedded within the environments they model and act upon

Orchestrates three frontier models to debate a question and synthesizes their best insights into a single superior answer.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

Agent Development Standards

Creates or modifies OpenAI Agents SDK tools with Zod parameters, caching, metrics, and agent registration, following established patterns and best practices.

Expert en RAG agentique (retrieval multi-étapes, self-query, chunking adaptatif, tool-augmented generation)

Design reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate graders, baselines, regression gates, and failure analysis. Use when defining agent quality, comparing prompts or models, validating a release, measuring tool-use reliability, investigating regressions, or deciding whether an agent is ready for production.

Continuously monitors system performance, identifies improvement opportunities, and orchestrates skill discovery and creation to autonomously evolve capabilities.

Build or modify a RAG retrieval pipeline with vector store search, corpus routing, citation rendering, and book fidelity enforcement.

Analyzes runtime history to identify failures and inefficiencies, then autonomously writes improvements using a protocol-constrained evolution engine. Communicates with EvoMap Hub via a local Proxy mailbox.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

Defines an agent's identity, personality, voice, and boundaries to create authentic, non-generic assistants.

Run a structured retrospective after development-phase runs of your product's agents — interview the owner in plain language about what went well and poorly, draft ranked improvement hypotheses, then design and run small n=1/n=2 experiments with pre-declared success criteria, guardrails, stop conditions, and a cost/ROI kill-switch. Load when the user says how did that run go, retro this run, the agent output was bad, what should we improve, draft hypotheses, run a small experiment, or after repeated dev runs of an agentic system produce uneven quality. Priority: output quality over performance over cost, each with diminishing-returns stops. NOT a product A/B test (experimentation), NOT coding-agent harness repair (harness-evolution), NOT production-scale learning (runtime-learning-loop).

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.

Guides AI agents through engineering workflows with eval-first execution, task decomposition, cost-aware model routing, and review focus for generated code.

Discovers, installs, and manages AI agent skills from agentskill.sh, including searching, installing mid-session, scanning for security issues, and providing feedback.

Creates or modifies agent tools for OpenAI Agents SDK, covering search, analysis, API integration, and database query patterns with caching and metrics.

Agent skill for refinement - invoke with $agent-refinement

Expert en agent loops (ARIS, Ralph, recherche autonome, build-score-budget, guardrails)

Main agent orchestrator that coordinates a specialized squad of agents