CtrlK
BlogDocsLog inGet started
Tessl Logo

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'.

68

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

76%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concrete, actionable deployment guide with executable dual-SDK code and useful reference/troubleshooting tables. Its main weakness is the absence of explicit verification steps in a database-and-deploy workflow, which caps workflow clarity, plus some duplicated code across SDK variants.

Suggestions

Add an explicit validation/verification step after deployment (e.g., curl the background endpoint, confirm Lakebase tables exist, run a smoke test of background+poll) to lift workflow clarity above the destructive/DB-operation cap of 3.

Reduce token cost by factoring the shared structure of the OpenAI and LangGraph start_server.py blocks into one base example, then showing only the differing imports/lifespan lines per SDK.

Consider moving the Constructor Reference and/or Troubleshooting tables into a reference file to better split the monolithic body and improve progressive disclosure.

DimensionReasoningScore

Conciseness

Mostly lean prose with step headers and code blocks, assuming Claude's competence without explaining basic concepts. It is not a 5 because the OpenAI and LangGraph start_server.py and replace_fake_id blocks are largely duplicated, adding tokens that could be factored out.

4 / 5

Actionability

Provides copy-paste-ready executable code for both SDK variants, pinned dependency versions ('>=0.18.0'), concrete commands ('uv sync'), named env vars, and a full constructor parameter table. It is not below 5 because the common cases are concretely covered.

5 / 5

Workflow Clarity

Steps 1-7 are clearly sequenced, but there is no explicit validation or verification checkpoint (e.g., test the background endpoint, confirm tables created) in a workflow that performs database initialization and deployment. Per the rubric cap, missing validation for database operations holds this at 3 rather than 4.

3 / 5

Progressive Disclosure

Well-organized with clear section headers and one-level-deep, clearly signaled references to the lakebase-setup skill, with no nested references. It is not a 5 because all content is inlined monolithically (~330 lines) with no bundle files, so nothing is actually split across files.

4 / 5

Total

16

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-structured description that clearly states the capability and provides explicit, numbered use-when triggers with natural user phrasing. Minor room to expand trigger synonyms, but it cleanly answers what and when.

DimensionReasoningScore

Specificity

Names a concrete component ('LongRunningAgentServer') and a concrete action ('Enable long-running background task support') plus specific trigger scenarios (HTTP timeout ~120s, background/async execution). It is not a 5 because only one primary action is described rather than multiple distinct concrete actions.

4 / 5

Completeness

Explicitly answers both 'what' (enable long-running background task support with LongRunningAgentServer) and 'when' via a numbered 'Use when:' clause with concrete trigger phrases, matching the anchor-5 example structure. It is not below 5 because both what and when are present and concrete.

5 / 5

Trigger Term Quality

Includes natural phrases a user would actually say ('long running', 'background tasks', 'async agent') alongside scenario cues ('HTTP timeout', 'background/async execution'). Not a 5 because synonymous terms like 'polling', 'streaming', or job-related phrasing are not covered as triggers.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (long-running agent servers) with distinct, specific triggers and a named class, minimizing overlap with generic agent-server skills. There is no neighboring anchor that fits better.

5 / 5

Total

18

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
databricks/app-templates
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.