migrating-ai-sdk-to-common-ai

Migrates Airflow projects from airflow-ai-sdk to apache-airflow-providers-common-ai 0.4.0+. Use when replacing airflow-ai-sdk with the official Airflow AI provider - migrating LLM decorators (@task.llm, @task.agent, @task.llm_branch, @task.embed), switching from model strings/objects to connection-based LLM configuration, updating imports from airflow_ai_sdk to the new provider, or upgrading an existing common-ai 0.1.x setup to 0.4.x (multimodal prompts, toolsets, embedding operators); also when common-ai provider, AIP-99, a pydanticai connection or migrating away from airflow-ai-sdk come up.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%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.

The body is a highly actionable, well-sequenced migration guide with strong validation checkpoints and concrete code. Its only weakness is token efficiency and structure: some inline reference material and the trailing features table could be split into separate files or trimmed.

Suggestions

Move the HITL REST endpoint list and the 'Quick reference: New features' table into a separate reference file (e.g. REFERENCE.md) and link to it, reducing the main body length and improving progressive_disclosure.

Trim or consolidate the new-features table, since several rows restate parameters already detailed in Steps 1–4.

Consider shortening the enable_hitl_review prose to the essential constraints (string prompt, incompatible with durable, blocks until acted on) unless the REST endpoints are kept in a separate reference.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's knowledge (no preamble on what Airflow or PydanticAI is), with nearly every token being version-specific migration data Claude lacks; minor instances could be trimmed, e.g. the HITL REST endpoint list and the new-features table that partly restate earlier sections.	4 / 5
Actionability	Provides copy-paste-ready before/after code blocks, exact requirements.txt lines, connection JSON, parameter-mapping tables, and concrete commands covering the common migration cases.	5 / 5
Workflow Clarity	A clearly sequenced Before-starting inventory plus Steps 1–7, with Step 7 providing explicit validation (grep checks) and a checklist with feedback loops for error recovery on a destructive migration.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections with easy navigation, but it is a ~390-line monolithic file with no bundle files; content like the HITL REST endpoints and the new-features quick-reference table could live in separate reference files.	4 / 5
	Total	18 / 20 Passed

Description

100%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.

The description is a strong, specific trigger-rich statement that clearly conveys both the migration scope and the situations that should invoke it. It names concrete decorators and version transitions rather than relying on generic language.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — migrating named LLM decorators (@task.llm, @task.agent, @task.llm_branch, @task.embed), switching from model strings/objects to connection-based config, updating imports, and upgrading 0.1.x to 0.4.x — covering the migration comprehensively.	5 / 5
Completeness	Explicitly answers both what (migrates Airflow projects from airflow-ai-sdk to the official provider, with enumerated actions) and when ('Use when replacing...', 'also when common-ai provider, AIP-99... come up') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including 'airflow-ai-sdk', 'common-ai provider', 'AIP-99', 'pydanticai connection', 'migrating away from airflow-ai-sdk', and the specific decorator names a user would mention.	5 / 5
Distinctiveness Conflict Risk	A clear, narrow niche (this specific provider migration) with distinct triggers and decorator/file references, giving minimal conflict risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: astronomer/agents
Path: skills/migrating-ai-sdk-to-common-ai/SKILL.md
Commit: dbd9bb7

Reviewed: ~23 hours ago

Table of Contents

Discovery Implementation Validation

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.