Goal-Seeking Agent Pattern
Guides architects on when and how to use goal-seeking agents as a design pattern. This skill helps evaluate whether autonomous agents are appropriate for a given problem, how to structure their objectives, integrate with goal_agent_generator, and reference real amplihack examples like AKS SRE automation, CI diagnostics, pre-commit workflows, and fix-agent pattern matching.
npx skills add majiayu000/claude-skill-registry --skill goal-seeking-agent-pattern --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Goal-Seeking Agent Pattern describes autonomous agents that pursue high-level objectives by planning multi-phase executions, adapting based on intermediate results, and self-assessing progress against success criteria. It emphasizes autonomy in choosing how to achieve goals, handling failures with recovery strategies, and coordinating across phases with dependencies and potential parallelism. It also provides a decision framework and architecture guidance for when to use this pattern.
How it works
The skill outlines a four-part execution flow: 1) GOAL ANALYSIS extracts the objective, domain, constraints, and success criteria from a natural language prompt; 2) PLANNING decomposes the goal into phases with dependencies to form an ExecutionPlan; 3) SKILL SYNTHESIS maps required capabilities to skills and identifies agents; 4) AGENT ASSEMBLY combines GoalDefinition, ExecutionPlan, and Skills into a GoalAgentBundle for execution. The flow includes state management across phases and three error recovery strategies: Retry with Backoff, Alternative Strategy, and Graceful Degradation. It also specifies integration with goal_agent_generator components: PromptAnalyzer, ObjectivePlanner, SkillSynthesizer, AgentAssembler, etc.
When to use it
The skill lists triggers such as complex workflow, autonomous agent, goal-seeking, adaptive behavior, multi-phase processing, task automation design, autonomous decision-making, multi-step process, workflow orchestration, and self-directed agent to indicate applicability. It provides a pattern-based evaluation including problem indicators (workflow variability, multi-phase complexity, autonomous recovery, adaptive decision making, domain expertise), and a five-question decision framework to decide applicability.
What it can touch
Allowed tools are Read, Grep, Glob, WebSearch. The workflow describes exposing and using components like PromptAnalyzer, ObjectivePlanner, SkillSynthesizer, AgentAssembler, and GoalAgentPackager, and code blocks in Python illustrating data structures and execution steps. It references tool names exactly as shown, including the module goal_agent_generator and function/class names in code blocks.
Caveats
License is MIT. Declares tools and components but does not guarantee success outcomes; evaluation is based on provided patterns, indicators, and branching logic. No explicit limitations beyond what is stated in the design sections.
# Goal-Seeking Agent Pattern Skill ## 1. What Are Goal-Seeking Agents? Goal-seeking agents are autonomous AI agents that execute multi-phase objectives by: 1. **Understanding High-Level Goals**: Accept natural language objectives without explicit step-by-step instructions 2. **Planning Execution**: Break goals into phases with dependencies and success criteria 3. **Autonomous Execution**: Make decisions and adapt behavior based on intermediate results 4. **Self-Assessment**: Evaluate progress against success criteria and adjust approach 5. **Resilient Operation**: Handle failures gracefully and explore alternative solutions ### Core Characteristics **Autonomy**: Agents decide HOW to achieve goals, not just follow prescriptive steps **Adaptability**: Adjust strategy based on runtime conditions and intermediate results **Goal-Oriented**: Focus on outcomes (what to achieve) rather than procedures (how to achieve) **Multi-Phase**: Complex objectives decomposed into manageable phases with dependencies **Self-Monitoring**: Track progress, detect failures, and course-correct autonomously ### Distinction from Traditional Agents | Traditional Agent | Goal-Seeking Agent | | -----------------
- 1. What Are Goal-Seeking Agents?
- Core Characteristics
- Distinction from Traditional Agents
- When Goal-Seeking Makes Sense
- When to Avoid Goal-Seeking
- 2. When to Use This Pattern
- Problem Indicators
- Decision Framework
- Decision Matrix
- 3. Architecture Pattern
- Component Architecture
- Execution Flow
- Phase Dependency Management
- State Management
Generate agent from prompt file amplihack goal-agent-generator create \ Generate agent from inline prompt List generated agents amplihack goal-agent-generator list Test agent execution amplihack goal-agent-generator test \ Execute via CLI amplihack goal-agent-generator execute \ Or programmatically:
What does the Goal-Seeking Agent Pattern skill do?
Guides architects on when and how to use goal-seeking agents as a design pattern. This skill helps evaluate whether autonomous agents are appropriate for a given problem, how to structure their objectives, integrate with goal_agent_generator, and reference real amplihack examples like AKS SRE automation, CI diagnostics, pre-commit workflows, and fix-agent pattern matching.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill goal-seeking-agent-pattern --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.