azure-ai-projects-py

Build AI applications on Microsoft Foundry using the azure-ai-projects SDK.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/azure-ai-projects-py/SKILL.md

Quality

Content

72%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 highly actionable with comprehensive executable code and good conciseness, but workflow clarity is capped at 3 by missing validation for batch/destructive operations, and progressive disclosure is undercut because every referenced bundle file is absent from the skill directory.

Suggestions

Add validation/verification checkpoints and retry loops around destructive and batch operations (e.g., confirm agent deletion, validate eval run status and handle failures before proceeding).

Ship the referenced bundle files (references/*.md, scripts/run_batch_evaluation.py) or remove the dangling 'See references/...' pointers so progressive disclosure resolves to real files.

De-duplicate the authentication and get_openai_client snippets shown in multiple sections to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-first with compact tables; minor redundancy (auth and get_openai_client shown twice) but no concept over-explanation. Not a 5 because of duplicated snippets and minor padding that could be trimmed.	4 / 5
Actionability	Extensive copy-paste-ready executable code across agents, tools, threads, eval, async, and memory stores with real env vars and concrete class names covering common cases. Not below 5 — examples are complete and runnable.	5 / 5
Workflow Clarity	The 'Thread and Message Flow' is a clear sequenced 4-step process, but batch/destructive operations (run_batch_evaluation.py, delete_agent) lack validation checkpoints or feedback loops. Per guideline, missing validation in batch/destructive ops caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	References are clearly signaled one-level-deep ('See references/x.md for...') with bulk API content deferred, but none of the referenced files or the scripts directory actually exist in the bundle. Per guideline, score against actual bundle structure — broken/dead references pull this down from a 5 to 3.	3 / 5
	Total	15 / 20 Passed

Description

53%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 concise and names a specific SDK/domain, but it lacks a 'Use when...' trigger clause and natural user-facing keywords, which caps completeness and trigger-term quality at 3. It is mostly distinct but reads slightly broad.

Suggestions

Add an explicit 'Use when...' trigger clause naming concrete scenarios users would describe (e.g., 'Use when building Foundry agents, managing agent threads/runs, or running Azure AI evaluations').

Include natural synonyms and surface forms (e.g., 'Azure AI Foundry', 'AIProjectClient', 'agent runs/threads', 'batch evaluation') rather than only the formal SDK name.

List a few concrete capabilities (create/version agents, file/code tools, evals, connections) to lift specificity from one action to several.

Dimension	Reasoning	Score
Specificity	Names the domain ('Microsoft Foundry', 'azure-ai-projects SDK') with one concrete action ('Build AI applications'), but coverage is not comprehensive — anchor 3. Not a 4 because only one action is listed rather than 'several specific actions'.	3 / 5
Completeness	Has a clear 'what' (build AI applications on Foundry with the SDK) but no 'when'/'Use when...' clause; per guideline, a missing trigger clause caps completeness at 3. Not a 4 because 'when' is entirely absent rather than weakly implied.	3 / 5
Trigger Term Quality	Has relevant technical keywords ('azure-ai-projects SDK', 'Microsoft Foundry', 'AI applications') but no natural synonyms, file extensions, or common variations users would actually say. Not a 4 because natural user phrases are missing.	3 / 5
Distinctiveness Conflict Risk	Specific to the azure-ai-projects / Microsoft Foundry niche with low conflict risk, though 'Build AI applications' is fairly broad. Not a 5 because the niche is not crisply distinct given the generic 'AI applications' framing.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 18 missing	Warning

	Total	14 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/azure-ai-projects-py/SKILL.md
Commit: 1f67c44

Reviewed: about 16 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.