modify-agent
Modify agent code, add tools, or change configuration. Use when: (1) User says 'modify agent', 'add tool', 'change model', or 'edit agent.py', (2) Adding MCP servers to agent, (3) Changing agent instructions, (4) Understanding SDK patterns.
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates specific capabilities and provides explicit trigger guidance. It uses third person voice, lists concrete actions, and includes natural user phrases. The numbered trigger scenarios make it easy for Claude to determine when to select this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Modify agent code', 'add tools', 'change configuration', 'Adding MCP servers', 'Changing agent instructions', 'Understanding SDK patterns'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (modify agent code, add tools, change configuration) and 'when' with an explicit 'Use when:' clause listing four specific trigger scenarios including exact user phrases and task types. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'modify agent', 'add tool', 'change model', 'edit agent.py', 'MCP servers', 'agent instructions', 'SDK patterns'. These cover common variations of how users would phrase requests about agent modification. | 3 / 3 |
Distinctiveness Conflict Risk | Targets a clear niche of agent code modification with distinct triggers like 'agent.py', 'MCP servers', 'SDK patterns' that are unlikely to conflict with general coding or configuration skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, well-organized skill that provides actionable code examples for modifying a Databricks agent. Its main strengths are concrete, executable code snippets and good progressive disclosure with clear cross-references to related skills. The primary weakness is the lack of validation/verification steps after making modifications, and some sections (like changing instructions) add little value beyond what Claude already knows.
Suggestions
Add a validation step after modifications, e.g., 'After changes, run `python -c "from agent_server.agent import agent; print(agent.name)"` to verify the agent loads without errors'
Remove or condense the 'Changing Instructions' section—it's just a string assignment that Claude doesn't need demonstrated
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of code examples and tables, but includes some unnecessary elements like the 'Changing Instructions' section which just shows a string assignment—something Claude already knows how to do. The external resources section is somewhat lengthy. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples for every major task: SDK setup, adding MCP servers, changing models, running the agent with both streaming and non-streaming modes. Specific model names and URL patterns are included. | 3 / 3 |
Workflow Clarity | The skill covers multiple modification tasks clearly but lacks validation checkpoints. After modifying agent code, there's no explicit 'verify it works' step or error recovery guidance. The 'After adding MCP servers' note about permissions is helpful but there's no validate-then-proceed workflow. | 2 / 3 |
Progressive Disclosure | Well-structured with a clear overview table of key files, concise inline examples for common tasks, and well-signaled references to other skills (discover-tools, add-tools, run-locally, deploy) and external resources. Navigation is easy and references are one level deep. | 3 / 3 |
Total | 10 / 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
- databricks/app-templates
- Commit
dfeb4ac
- 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.