agent-orchestration-improve-agent
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
62
47%
Does it follow best practices?
Impact
82%
1.54xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./docs/v19.7/configuration/agent/skills_external/antigravity-awesome-skills-main/skills/agent-orchestration-improve-agent/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description provides a reasonable high-level overview of agent improvement capabilities but suffers from abstract language and lacks explicit trigger guidance. It would benefit from more concrete actions and a clear 'Use when...' clause to help Claude distinguish this skill from general prompt engineering or performance analysis skills.
Suggestions
Add a 'Use when...' clause with trigger terms like 'improve agent', 'agent performance', 'agent debugging', 'optimize agent', or 'agent iteration'.
Replace abstract terms with concrete actions such as 'analyze agent logs', 'refine system prompts', 'identify failure patterns', or 'A/B test agent responses'.
Include natural user phrases like 'my agent isn't working well', 'make my agent better', or 'agent quality issues' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (agent improvement) and some actions ('performance analysis, prompt engineering, continuous iteration'), but these are somewhat abstract and not fully concrete actions like 'analyze logs' or 'rewrite prompts'. | 2 / 3 |
Completeness | Describes what it does at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'agents', 'prompt engineering', and 'performance analysis', but missing common user phrases like 'improve my agent', 'agent not working', 'optimize prompts', or 'debug agent behavior'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Prompt engineering' could overlap with general prompt writing skills, and 'performance analysis' is generic. However, 'agents' and 'iteration' provide some distinctiveness for agent-specific work. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive framework for agent optimization with strong workflow clarity and explicit validation/rollback procedures. However, it suffers from verbosity, explaining concepts Claude already knows, and uses pseudocode placeholders rather than executable examples. The monolithic structure would benefit from progressive disclosure to external reference files.
Suggestions
Replace pseudocode command blocks (e.g., 'Use: context-manager') with actual executable commands or clarify these are conceptual placeholders
Remove explanatory content about well-known concepts (A/B testing basics, semantic versioning) to improve token efficiency
Split detailed content (evaluation rubrics, test suite templates, rollback procedures) into separate reference files with clear links from the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful content but is verbose in places, explaining concepts Claude likely knows (e.g., what A/B testing is, basic versioning semantics). Some sections like 'Continuous Improvement Cycle' and 'Post-Deployment Review' add padding without actionable specifics. | 2 / 3 |
Actionability | Provides structured guidance and some command examples, but most code blocks are pseudocode or placeholder syntax (e.g., 'Use: context-manager', 'Use: prompt-engineer') rather than executable commands. The metrics templates are useful but not copy-paste ready. | 2 / 3 |
Workflow Clarity | Clear four-phase workflow with explicit sequencing, validation checkpoints (A/B testing, staged rollout), and rollback procedures with specific triggers. The feedback loop for rollback is well-defined with concrete thresholds. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear headers and phases, but it's a monolithic document with no references to external files for detailed content (e.g., test suite templates, evaluation rubrics). The 200+ lines could benefit from splitting advanced topics into separate files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- duclm1x1/Dive-Ai
- Commit
20ba150
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.