agent-orchestration-improve-agent
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
Install with Tessl CLI
npx tessl i github:duclm1x1/Dive-Ai --skill agent-orchestration-improve-agent60
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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 identifies a clear domain (agent improvement) but relies on abstract terminology rather than concrete actions. The complete absence of a 'Use when...' clause significantly weakens its utility for skill selection, and the trigger terms used are more technical than what users would naturally say.
Suggestions
Add an explicit 'Use when...' clause with natural trigger terms like 'agent not working', 'improve my agent', 'agent performance issues', 'fix agent behavior', or 'optimize agent prompts'.
Replace abstract actions with concrete specifics: instead of 'performance analysis', say 'analyze agent logs and error patterns, identify failure modes, measure success rates'.
Include file type or artifact triggers if applicable, such as 'when working with agent configuration files, system prompts, or agent evaluation results'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (agent improvement) and some actions (performance analysis, prompt engineering, continuous iteration), but these are somewhat abstract rather than concrete specific actions like 'analyze error logs' or 'rewrite system prompts'. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance caps completeness at 2, and this is weaker than that threshold. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'agents', 'prompt engineering', and 'performance analysis', but missing common variations users might say like 'fix my agent', 'agent not working', 'improve prompts', 'debug agent', or 'optimize agent'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on 'agents' provides some specificity, but 'prompt engineering' and 'performance analysis' could overlap with general coding skills, debugging skills, or other AI-related skills. | 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 excellent workflow structure and clear phases. However, it suffers from verbosity and lacks truly executable examples - the referenced tools (context-manager, prompt-engineer, parallel-test-runner) appear to be placeholders rather than real implementations. The content would benefit from being more concise and splitting detailed reference material into separate files.
Suggestions
Replace placeholder tool commands with actual executable code or clearly document that these are conceptual frameworks requiring implementation
Move detailed reference content (evaluation metrics, test categories, constitutional principles) to separate files and link to them from the main skill
Trim explanatory content that Claude already knows (e.g., what A/B testing is, basic versioning concepts) to improve token efficiency
Add concrete, copy-paste ready examples for at least one complete optimization cycle with real code
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful information but is verbose in places, with some sections that could be tightened (e.g., the extensive lists of metrics, the detailed rollback procedures). Some content explains concepts Claude would already understand, like what A/B testing is or basic versioning semantics. | 2 / 3 |
Actionability | The skill provides structured guidance but lacks truly executable code. Commands like 'context-manager analyze-agent-performance' and 'prompt-engineer' reference tools without concrete implementation. Most examples are templates or pseudocode rather than copy-paste ready commands. | 2 / 3 |
Workflow Clarity | The four-phase workflow is clearly sequenced with explicit validation checkpoints (Phase 3 testing, Phase 4 staged rollout with rollback triggers). The rollback procedures include specific thresholds and a clear recovery process, demonstrating good feedback loops for error recovery. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and headers, but it's monolithic - all content is inline rather than appropriately split across reference files. Advanced topics like Constitutional AI integration or the full evaluation metrics framework could be separate documents. | 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.
- 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.