phoenix-server

Backend development guide for the Phoenix AI observability platform (Strawberry GraphQL, SQLAlchemy async, FastAPI). Use this skill when writing or modifying Python server code in the phoenix repo — adding mutations, types, migrations, or tests. Trigger on any backend task touching src/phoenix/server/, src/phoenix/db/, or tests/unit/server/.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

87%

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

The body is an efficient, actionable index with excellent progressive disclosure of detail into reference files. The only gap is that the destructive database/migration workflow lacks an explicit inline validation feedback loop, capping workflow clarity at 2.

Suggestions

Add a short inline validate-to-fix-to-retry note for the migration/database path (e.g. run `uv run pytest tests/unit/server/ -n auto` after a migration, and re-run `make typecheck-python` before committing) rather than relying solely on references/database-patterns.md.

Surface the `make check-graphql-permissions` CI guard as an explicit local pre-commit checkpoint in the 'Everyday Commands' or 'Hard Rules' section so the feedback loop is runnable before push.

Consider a one-line 'Before you finish' checklist (format → typecheck → relevant tests) to make the validation sequence explicit for multi-step backend changes.

Dimension	Reasoning	Score
Conciseness	The body is lean — a command table, an annotated directory tree, a task-to-reference routing table, and tightly-scoped rule sections — with no general-concept filler; it assumes Claude's competence and every line earns its place.	3 / 3
Actionability	Provides copy-paste-ready commands ('make dev-backend', 'uv run pytest ... -n auto', 'make graphql'), a concrete directory map, a routing table, and an actionable hard rule ('MUST be a @strawberry.mutation with permission_classes=[...]'), matching the fully-executable anchor.	3 / 3
Workflow Clarity	Task routing and validation commands (check-graphql-permissions, typecheck-python) are present, but the risky migration/database path is delegated to an external reference without an inline validate-to-fix-to-retry feedback loop, leaving checkpoints implicit rather than explicit.	2 / 3
Progressive Disclosure	SKILL.md is a clear overview that routes tasks to four verified, one-level-deep reference files (graphql-patterns, test-patterns, llm-trace-tests, database-patterns), with content appropriately split and well-signaled navigation.	3 / 3
	Total	11 / 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.

The description is specific, uses third-person voice, and explicitly covers both what the skill does and when to trigger it with concrete repo-path triggers. It is concise and distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'writing or modifying Python server code', 'adding mutations, types, migrations, or tests' — tied to a specific domain, matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (backend dev guide for the Phoenix platform) and when ('Use this skill when...', 'Trigger on any backend task touching...'), with explicit trigger guidance.	3 / 3
Trigger Term Quality	Covers natural phrasings a user would say ('writing or modifying Python server code', 'backend task', 'adding mutations/types/migrations/tests') plus explicit path-based triggers, giving good natural-term coverage.	3 / 3
Distinctiveness Conflict Risk	Narrowly scoped to the Phoenix AI observability platform backend with exact repo paths, giving a clear niche unlikely to conflict with generic skills.	3 / 3
	Total	12 / 12 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: Arize-ai/phoenix
Commit: 27a4ecc

Reviewed: 4 days 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.