- name
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add sickn33/agentic-awesome-skills --skill agent-orchestration-improve-agent -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add sickn33/agentic-awesome-skills --skill agent-orchestration-improve-agent -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add sickn33/agentic-awesome-skills --skill agent-orchestration-improve-agent -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add sickn33/agentic-awesome-skills --skill agent-orchestration-improve-agent -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/sickn33/agentic-awesome-skills/tree/HEAD/plugins/agentic-awesome-skills-claude/skills/agent-orchestration-improve-agentFrom the publisher
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
[Extended thinking: Agent optimization requires a data-driven approach combining performance metrics, user feedback analysis, and advanced prompt engineering techniques. Success depends on systematic evaluation, targeted improvements, and rigorous testing with rollback capabilities for production safety.]
Do not run hosted evaluations, delegate, message teams, configure recurring reports or deploy merely because a phase names them. Follow the user's existing authorization and actual host workflow. Keep traces private/redacted, cap cost and steps, isolate candidate changes, and require supported exact-version checks. parallel-test-runner and named agent roles are not bundled; use a real harness or report the gap.
Analyze supplied traces and available metrics. Named roles below are optional roles, not installed executables or permission to delegate.
Use: context-manager
Task: analyze the authorized trace window using actual available tools
No analyze-agent-performance command is bundled.
Collect metrics including:
Identify recurring patterns in user interactions:
Categorize failures by root cause:
Generate quantitative baseline metrics:
Performance Baseline:
- Task Success Rate: [X%]
- Average Corrections per Task: [Y]
- Tool Call Efficiency: [Z%]
- User Satisfaction Score: [1-10]
- Average Response Latency: [Xms]
- Token Efficiency Ratio: [X:Y]
Apply advanced prompt optimization techniques using prompt-engineer agent.
Implement structured reasoning patterns:
Use: prompt-engineer
Technique: chain-of-thought-optimization
Curate high-quality examples from successful interactions:
Example structure:
Good Example:
Input: [User request]
Evidence: [Concise rationale and observable checks]
Output: [Successful response]
Why this works: [Key success factors]
Bad Example:
Input: [Similar request]
Output: [Failed response]
Why this fails: [Specific issues]
Correct approach: [Fixed version]
Strengthen agent identity and capabilities:
Implement self-correction mechanisms:
Constitutional Principles:
1. Verify factual accuracy before responding
2. Self-check for potential biases or harmful content
3. Validate output format matches requirements
4. Ensure response completeness
5. Maintain consistency with previous responses
Add critique-and-revise loops:
Optimize response structure:
Comprehensive testing framework with A/B comparison.
Create representative test scenarios:
Test Categories:
1. Golden path scenarios (common successful cases)
2. Previously failed tasks (regression testing)
3. Edge cases and corner scenarios
4. Stress tests (complex, multi-step tasks)
5. Adversarial inputs (potential breaking points)
6. Cross-domain tasks (combining capabilities)
Compare original vs improved agent:
Use: parallel-test-runner
Config:
- Agent A: Original version
- Agent B: Improved version
- Test set: 100 representative tasks
- Metrics: Success rate, speed, token usage
- Evaluation: Blind human review + automated scoring
Statistical significance testing:
Comprehensive scoring framework:
Task-Level Metrics:
Quality Metrics:
Performance Metrics:
Structured human review process:
Safe rollout with monitoring and rollback capabilities.
Systematic versioning strategy:
Version Format: agent-name-v[MAJOR].[MINOR].[PATCH]
Example: customer-support-v2.3.1
MAJOR: Significant capability changes
MINOR: Prompt improvements, new examples
PATCH: Bug fixes, minor adjustments
Maintain version history:
Progressive deployment strategy:
Quick recovery mechanism:
Rollback Triggers:
- Success rate drops >10% from baseline
- Critical errors increase >5%
- User complaints spike
- Cost per task increases >20%
- Safety violations detected
Rollback Process:
1. Detect issue via monitoring
2. Alert team immediately
3. Switch to previous stable version
4. Analyze root cause
5. Fix and re-test before retry
Real-time performance tracking:
The following are illustrative targets, not universal success conditions. Choose the actual criteria before testing, distinguish relative changes from percentage points and report uncertainty:
After 30 days of production use:
Establish regular improvement cadence:
Remember: Agent optimization is an iterative process. Each cycle builds upon previous learnings, gradually improving performance while maintaining stability and safety.
© 2026 Skills Rack.
---name: agent-orchestration-improve-agentdescription: Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous…---# plugins/agentic-awesome-skills-claude/skills/agent-orchestration-improve-agent/SKILL.mdFAQ
Download plugins/agentic-awesome-skills-claude/skills/agent-orchestration-improve-agent/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/sickn33/agentic-awesome-skills.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.