long-running-server
Enable long-running background task support with LongRunningAgentServer. Use when: (1) Agent tasks may exceed HTTP timeout (~120s), (2) User wants background/async execution, (3) User says 'long running', 'background tasks', or 'async agent'.
82
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./agent-migration-from-model-serving/.claude/skills/long-running-server/SKILL.mdQuality
Discovery
89%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 solid description with excellent completeness and distinctiveness. It clearly states when to use the skill with explicit trigger terms and conditions. The main weakness is that the 'what' portion could be more specific about the concrete actions or capabilities provided beyond just 'enabling support'.
Suggestions
Add 2-3 specific concrete actions to improve specificity, e.g., 'Configures task queuing, status polling, and result retrieval for agent tasks that exceed HTTP timeout limits.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('long-running background task support') and mentions a specific component ('LongRunningAgentServer'), but doesn't list multiple concrete actions—it describes a capability area rather than specific operations like 'queue tasks, poll status, retrieve results'. | 2 / 3 |
Completeness | Clearly answers both 'what' (enable long-running background task support with LongRunningAgentServer) and 'when' (explicit 'Use when' clause with three specific trigger conditions including timeout scenarios and user phrases). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'long running', 'background tasks', 'async agent', 'HTTP timeout', and 'background/async execution'. These cover common variations of how a user would describe this need. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche—'LongRunningAgentServer', 'HTTP timeout (~120s)', and 'async agent' are very specific triggers unlikely to conflict with other skills. The domain is narrow and well-defined. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with complete executable code for enabling long-running agent support. Its main weaknesses are the duplicated code blocks for two SDK variants (which could be split into separate files) and the lack of explicit validation/verification steps after completing the setup. The troubleshooting table is a nice addition that adds practical value.
Suggestions
Add a verification step (e.g., Step 7: 'Test by sending POST /responses with {"background": true} and confirm you get a response ID, then poll GET /responses/{id}') to validate the setup works end-to-end.
Consider splitting OpenAI SDK and LangGraph variants into separate referenced files to reduce duplication and improve progressive disclosure.
Remove or consolidate the near-identical code between the two SDK variants — highlight only the differences inline and share the common structure once.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~200+ lines) with two near-identical code blocks for OpenAI SDK and LangGraph variants that share ~90% of their content. The table explaining request patterns and the constructor reference table add useful information but the duplicated code blocks inflate token usage significantly. Some sections like the LakebaseConfig dataclass could be more concise. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste-ready code for every step including the server setup, utility functions, config dataclass, YAML configuration, and .env setup. Code is complete with imports and is clearly organized by SDK variant. | 3 / 3 |
Workflow Clarity | The 7-step sequence is clearly numbered and logically ordered, but there are no explicit validation checkpoints or feedback loops. After making all these changes, there's no 'verify it works' step — Step 7 just defers to another skill. For a multi-step process involving database configuration and server changes, missing verification (e.g., 'test with curl POST /responses {background: true}') is a gap. | 2 / 3 |
Progressive Disclosure | The skill appropriately references the lakebase-setup skill for prerequisite steps and defers deployment details, which is good. However, the inline content is quite long with two full SDK variants that could be split into separate files. No bundle files are provided to support the references, and the two SDK variants make the single file feel monolithic. | 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
- 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.