CtrlK
BlogDocsLog inGet started
Tessl Logo

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/.

65

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/phoenix-server/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A well-organized backend guide that routes tasks to real one-level-deep references and supplies executable everyday commands. Its main weakness is workflow clarity: verification steps are not tied to specific tasks as explicit checkpoints, particularly for destructive migration work.

Suggestions

Add a per-task verification line in the 'What Are You Doing?' table (e.g. after a migration: run make graphql, then make typecheck-python, then uv run pytest tests/unit/server/) so validation is sequenced rather than left as generic everyday commands.

For migration/model changes, include an explicit validate->fix->retry checkpoint note (or pointer to the matching section in references/database-patterns.md) given their destructive nature.

Trim the editorial rationale in the Naming and Docstrings sections to the rule plus a one-line why, reducing over-explanation.

DimensionReasoningScore

Conciseness

Mostly lean with compact command blocks and a structured directory listing; rationale prose in Hard Rules/Naming/Docstrings is largely justified context rather than padding, with only minor editorial over-explanation.

4 / 5

Actionability

Provides concrete executable commands (make dev-backend, uv run pytest), a real directory map, and a task-to-reference routing table with specific class names; full pattern code lives in references rather than inline, leaving minor gaps.

4 / 5

Workflow Clarity

The task table gives a clear routing sequence and verification commands exist (typecheck, test), but validation checkpoints are not sequenced per task and destructive migration work lacks inline validate/verify steps, capping it at 3.

3 / 5

Progressive Disclosure

Four real reference files are each clearly signaled one level deep via the task table and inline pointers (e.g. "See references/graphql-patterns.md → 'Query vs Mutation'"), with the overview appropriately split from detail.

5 / 5

Total

16

/

20

Passed

Description

87%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.

A strong, well-scoped description that clearly states purpose, concrete actions, and explicit trigger conditions tied to specific repo paths. It is third-person and free of fluff; the only minor gap is synonym coverage in trigger terms.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ("writing or modifying Python server code", "adding mutations, types, migrations, or tests"); not quite a comprehensive exhaustive action list, so a 4 rather than 5.

4 / 5

Completeness

Explicitly answers both what ("Backend development guide for the Phoenix AI observability platform...") and when ("Use this skill when...", "Trigger on any backend task touching...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural coverage ("backend task", "mutations, types, migrations, or tests") plus concrete path triggers, though a few common synonyms are absent, placing it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

Scoped to a single named repo with specific path triggers (src/phoenix/server/, src/phoenix/db/, tests/unit/server/), giving a clear niche with minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.