CtrlK
BlogDocsLog inGet started
Tessl Logo

supervisor-api-background-mode

Enable Supervisor API background mode for long-running agent tasks. Use when: (1) Agent needs to run tasks longer than HTTP timeout limits, (2) User says 'background mode', 'long-running', 'supervisor api', (3) Converting from streaming to background polling pattern, (4) Agent needs resilience to connection drops during execution.

72

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

77%

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

A highly actionable, well-sequenced implementation skill with complete executable code and strong error-handling feedback loops. Its main weaknesses are token bulk from pervasive logging and a monolithic single-file structure that does not leverage progressive disclosure.

Suggestions

Trim the many logger.info f-string lines in the code examples (or move them to a reference file) — they pad the body without aiding execution.

Extract the full utils.py and agent.py modules into reference files under scripts/ or references/, keeping SKILL.md as a concise overview with the key diff from the base supervisor-api skill and links to the full code.

Reduce overlap between the ASCII architecture diagram, the 'What Changes' comparison table, and the Step 1 prose, which restate the same streaming/polling flow three times.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence and avoids explaining basic concepts, but ~500 lines include many verbose logger.info f-string statements and some prose redundancy (Architecture diagram vs. comparison table vs. Step 1 prose) that could be tightened.

2 / 3

Actionability

Provides two complete, executable Python modules with imports and concrete curl-based test commands — copy-paste ready; the only placeholder (TOOLS=[...]) is explicitly justified by reference to the supervisor-api skill.

3 / 3

Workflow Clarity

Clear prerequisite → Step 1 → Step 2 → Testing sequence with real feedback loops: retrieve-failure retry, break-on-incomplete ordering, and failed/cancelled terminal handling, plus a verification section.

3 / 3

Progressive Disclosure

Everything lives in a single ~500-line SKILL.md with large inline code modules (~230 lines of utils.py, ~120 of agent.py) that could be split into reference files; no bundle files are provided, so it reads as a monolith rather than an overview pointing to details.

2 / 3

Total

10

/

12

Passed

Description

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.

A strong, third-person description that concisely states the capability and provides an explicit, enumerated 'Use when' trigger list with natural user phrasings. It clearly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Enable Supervisor API background mode', 'Converting from streaming to background polling pattern', and 'resilience to connection drops' — rather than vague language.

3 / 3

Completeness

Clearly states what it does ('Enable Supervisor API background mode for long-running agent tasks') and when to use it via an explicit 'Use when: (1)...(4)' clause.

3 / 3

Trigger Term Quality

Explicitly quotes natural terms a user would say — 'background mode', 'long-running', 'supervisor api' — giving good coverage of likely phrasings.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (background mode for long-running tasks) with distinct triggers; though it extends the base supervisor-api skill, the 'background mode' framing is unlikely to misfire.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (505 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

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.