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.
71
86%
Does it follow best practices?
Impact
—
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 defines its scope around agent code modification and configuration. It excels at providing explicit trigger terms and scenarios, uses proper third-person voice, and covers both what the skill does and when to use it. The numbered use-when clauses with specific user phrases make it easy for Claude to match against user requests.
| 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 concrete, 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. The specificity to agent development makes it highly distinguishable. | 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, actionable skill with excellent code examples covering all major agent modification scenarios. Its main weakness is the lack of validation/verification steps after making changes—there's no guidance on how to confirm modifications work correctly before deploying. The progressive disclosure is well done with clear cross-references to related skills.
Suggestions
Add a validation step after each modification type (e.g., 'Run `python -c "from agent_server.agent import agent; print(agent.mcp_servers)"` to verify MCP servers were added correctly')
Remove the redundant 'Main File' section since agent.py is already the first entry in the Key Files table
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of code examples and tables, but includes some unnecessary elements like the 'Key Files' table that partially duplicates the 'Main File' section, and the instructions example is somewhat verbose. The external resources section is useful but lengthy. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready code for every operation: SDK setup, adding MCP servers, changing models, changing instructions, and running the agent. Each section has concrete, specific examples with real import paths and API calls. | 3 / 3 |
Workflow Clarity | Individual tasks are clearly presented but there's no overall workflow sequence or validation checkpoints. After modifying the agent (e.g., adding MCP servers, changing model), there's no explicit 'verify it works' step before proceeding. The 'After adding MCP servers' note hints at a dependency but doesn't provide a validation loop. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections, a concise overview table, and well-signaled one-level-deep references to other skills (discover-tools, add-tools, run-locally, deploy) and external documentation. Content is appropriately scoped to modification tasks without overloading. | 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
1c88215
- 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.