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

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The body is highly actionable with executable code and well-organized sections, and progressive disclosure is handled cleanly through signaled cross-skill references. Weaknesses are duplication-driven verbosity and validation checkpoints that remain implicit rather than gated.

Suggestions

Collapse the OpenAI/LangGraph duplicates for start_server.py and replace_fake_id into a shared base with a small diff table of the SDK-specific lines, to cut roughly a third of the body length.

Add an explicit verify step after Step 7 (e.g., poll GET /responses/{id} on a background task and confirm a persisted result returns) so the workflow has a concrete validation checkpoint.

Replace the vague OpenAI lifespan comment with the concrete table-init call (mirroring the LangGraph try/except) so DB initialization is actionable rather than described.

DimensionReasoningScore

Conciseness

The body is code-first and mostly free of concept padding, but ~340 lines duplicate near-identical OpenAI and LangGraph variants for start_server.py and replace_fake_id; it is mostly efficient but could be tightened, matching the level-2 anchor.

2 / 3

Actionability

It provides fully executable, copy-paste-ready code blocks (server entry point, replace_fake_id, LakebaseConfig), concrete commands ("uv sync"), plus constructor-reference and troubleshooting tables, satisfying the level-3 anchor.

3 / 3

Workflow Clarity

Seven steps are clearly sequenced and a troubleshooting table offers error-recovery feedback, but there is no inline verify/proceed checkpoint and the OpenAI lifespan DB-init is left vague ("If using AsyncDatabricksSession, create a throwaway session and call _ensure_tables()"), so checkpoints are implicit.

2 / 3

Progressive Disclosure

No bundle files exist; the single SKILL.md is well-sectioned (What It Enables, Steps 1–7, Constructor Reference, Troubleshooting) and its cross-references to the lakebase-setup skill are clearly signaled and only one level deep.

3 / 3

Total

10

/

12

Passed

Description

90%

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 is strong: it states a concrete capability, attaches explicit numbered "Use when" triggers using natural user phrasing, and occupies a distinct niche. The only weakness is that the capability statement lists a single action rather than multiple concrete ones.

DimensionReasoningScore

Specificity

The phrase "Enable long-running background task support with LongRunningAgentServer" names the domain and concrete class but states a single capability rather than listing multiple specific actions, matching the level-2 anchor.

2 / 3

Completeness

It answers both what ("Enable long-running background task support with LongRunningAgentServer") and when via an explicit "Use when:" clause with three numbered triggers, satisfying the level-3 anchor.

3 / 3

Trigger Term Quality

Natural user phrasings are explicitly enumerated — "'long running', 'background tasks', or 'async agent'" — alongside "HTTP timeout (~120s)" and "background/async execution", giving good coverage of terms users would actually say.

3 / 3

Distinctiveness Conflict Risk

The niche is narrow (long-running agent server surviving HTTP timeouts) with distinct triggers unlikely to match unrelated skills, so conflict risk is low.

3 / 3

Total

11

/

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.

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.