Skip to main content
ClaudeWave
Skill10.1k repo starsupdated today

phoenix-github

This Claude Code skill provides access to GitHub issue, label, and project board management for the Arize-ai/phoenix repository via the gh CLI. Use it when filing roadmap epics, triaging bugs, applying component or priority labels, managing the Phoenix roadmap project board, or querying issue and project state. The skill references a comprehensive label taxonomy covering components like UI, server, traces, evals, datasets, and others, plus priority and status labels for organizing work.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/Arize-ai/phoenix /tmp/phoenix-github && cp -r /tmp/phoenix-github/.agents/skills/phoenix-github ~/.claude/skills/phoenix-github
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Phoenix GitHub

Reference for managing issues, labels, and project boards on the `Arize-ai/phoenix` repository using the `gh` CLI.

## Repository

```
Arize-ai/phoenix
```

## Quick Reference

| Task | See |
|---|---|
| File a roadmap epic | [Roadmap Issues](#roadmap-issues) |
| Apply the right labels | [Label Taxonomy](#label-taxonomy) |
| Add an issue to the roadmap project | [Project Board](#project-board) |
| Set project dates or status | [Project Board](#project-board) |
| Create a bug or feature request | [Standard Issues](#standard-issues) |

---

## Label Taxonomy

### Component Labels (`c/`)

Every issue should have at least one component label.

| Label | Area |
|---|---|
| `c/ui` | Frontend / React UI |
| `c/server` | FastAPI backend / server logic |
| `c/traces` | Tracing, spans, OpenTelemetry ingestion |
| `c/evals` | Evaluations framework |
| `c/datasets` | Datasets CRUD and management |
| `c/experiments` | Experiment runs and comparisons |
| `c/annotations` | Human annotations and queues |
| `c/prompts` | Prompt management and prompt SDK |
| `c/playground` | LLM playground and provider support |
| `c/agents` | In-browser or terminal AI agents for Phoenix (PXI) |
| `c/client` | Python/TypeScript SDK and REST client |
| `c/cli` | `@arizeai/phoenix-cli` |
| `c/api` | REST API surface |
| `c/sessions` | Sessions and session tracking |
| `c/otel` | OpenTelemetry / OTel ingestion |
| `c/rbac` | Role-based access control |
| `c/auth` | Authentication |
| `c/infra` | Infrastructure, jobs, storage connectors |
| `c/helm` | Helm chart / Kubernetes deployment |
| `c/mcp` | MCP (Model Context Protocol) integration |
| `c/filters` | Filter UI and filter logic |
| `c/metrics` | Metrics and aggregations |
| `c/dx` | Developer experience |

### Priority Labels

| Label | Use |
|---|---|
| `priority: highest` | Roadmap epics and critical P0 bugs |
| `priority: high` | Important but not blocking |
| `priority: medium` | Normal queue work |
| `priority: low` | Nice-to-have |

### Type / Status Labels

| Label | Use |
|---|---|
| `roadmap` | High-level roadmap epic |
| `bug` | Something isn't working |
| `enhancement` | New feature or improvement |
| `documentation` | Docs-only change |
| `triage` | Needs triage by the team |
| `blocked` | Blocked on external dependency |
| `backlog` | Acknowledged but not scheduled |
| `needs information` | Awaiting info from the reporter |
| `design` / `needs design` | Needs design work before engineering |
| `onboarding` | Related to new-user onboarding flows |
| `phoenix-cloud` | Arize-hosted Phoenix (cloud) specific |
| `user request` | Requested by a user |
| `good-agent-issue` | Well-scoped enough for an AI agent to pick up |
| `agent-in-progress` | An agent is currently working on this issue |

---

## Roadmap Issues

Roadmap issues are high-level epics representing product initiatives.

### Title Format

```
🗺️ [category] Title
```

The `🗺️` prefix marks an epic. Sub-issues that roll up under an epic use the same `[category]` bracket but drop the emoji (e.g. `[agents] dataset tools`).

**Categories:** `ui/ux`, `agents`, `tools`, `tracing`/`traces`, `sessions`, `evals`, `server-evals`, `sandboxes`, `annotations`, `prompts`, `datasets/experiments`, `infrastructure`, `enterprise`, `sdk/connectors`. A few standalone epics use a product name instead of a bracket (e.g. `@arizeai/phoenix-cli`, `REST API`).

### Labels per Category

Every roadmap epic gets `roadmap` + `enhancement`. Add `priority: highest` for actively-prioritized epics, plus the relevant component label(s):

| Category | Component labels |
|---|---|
| `ui/ux` | `c/ui` |
| `agents` | `c/agents` |
| `tools` | `c/agents` (often none beyond `roadmap`) |
| `tracing` / `traces` | `c/traces` |
| `sessions` | `c/sessions`, `c/ui` |
| `evals` | `c/evals` (add `c/playground` when playground-related) |
| `server-evals` / `sandboxes` | `c/evals`, `c/server` |
| `annotations` | `c/annotations` |
| `prompts` | `c/prompts`, `c/playground` |
| `datasets/experiments` | `c/datasets`, `c/experiments` |
| `infrastructure` | `c/infra` |
| `enterprise` | `c/rbac`, `c/auth` |
| `sdk/connectors` | `c/client` |
| `@arizeai/phoenix-cli` | `c/cli`, `c/dx` |
| `REST API` | `c/api`, `c/server` |

### Body Template

```markdown
<one-line description of the initiative>

## Spike

- [ ]

## Front End

- [ ]

## Back End

- [ ]

## Open Questions

-
```

### Creating a Roadmap Issue

```bash
gh issue create \
  --repo Arize-ai/phoenix \
  --title "🗺️ [category] Title" \
  --label "roadmap,priority: highest,c/ui" \
  --body "$(cat <<'EOF'
Description of the initiative.

## Spike

- [ ]

## Front End

- [ ]

## Back End

- [ ]

## Open Questions

-
EOF
)"
```

---

## Project Board

### Phoenix Roadmap (Project #45)

The canonical roadmap board for open-source Phoenix.

| Field | ID |
|---|---|
| Project ID | `PVT_kwDOA5FfSM4AJaRo` |
| Start Date | `PVTF_lADOA5FfSM4AJaRozgInoCI` |
| Target Date | `PVTF_lADOA5FfSM4AJaRozgInn58` |
| Status | `PVTSSF_lADOA5FfSM4AJaRozgFw9n0` |

**Status option IDs:**

| Status | Option ID |
|---|---|
| Todo | `f75ad846` |
| In Progress | `47fc9ee4` |
| Done | `98236657` |

### Add an Issue to the Project

```bash
# 1. Get the issue node ID
NODE_ID=$(gh api repos/Arize-ai/phoenix/issues/{number} --jq '.node_id')

# 2. Add to project, capture item ID
ITEM_ID=$(gh api graphql -f query='
  mutation($project: ID!, $content: ID!) {
    addProjectV2ItemById(input: {projectId: $project, contentId: $content}) {
      item { id }
    }
  }' \
  -f project="PVT_kwDOA5FfSM4AJaRo" \
  -f content="$NODE_ID" \
  --jq '.data.addProjectV2ItemById.item.id')
```

### Set Start / Target Date

```bash
gh api graphql -f query='
  mutation($project: ID!, $item: ID!, $field: ID!, $value: Date!) {
    updateProjectV2ItemFieldValue(input: {
      projectId: $project, itemId: $item, fieldId: $field,
      value: {date: $value}
    }) { projectV2Item { id } }
  }' \
  -f project="PVT_kwDOA5FfSM4AJaRo" \
  -f item="$
agent-browserSkill

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

mintlifySkill

Build and maintain documentation sites with Mintlify. Use when

phoenix-cliSkill

Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API. Use whenever the user is analyzing traces or spans, investigating LLM/agent failures, deciding what to do after instrumenting an app, building failure taxonomies, choosing what evals to write, or asking "what's going wrong", "what kinds of mistakes", or "where do I focus" — even without naming a technique.

phoenix-designSkill

Design system conventions for the Phoenix frontend — layout, dialogs, error display, BEM CSS class naming, and CSS design tokens. Use when building UI, naming CSS classes, creating or consuming tokens, handling errors, or designing dialog interactions in app/src/.

phoenix-docs-gap-auditSkill

>

phoenix-evals-new-metricSkill

>-

phoenix-evalsSkill

Build and run evaluators for AI/LLM applications using Phoenix.

phoenix-frontendSkill

Frontend development guidelines for the Phoenix AI observability platform. Use when writing, reviewing, or modifying React components, TypeScript code, styles, or UI features in the app/ directory. Triggers on any frontend task — new components, UI changes, styling, accessibility fixes, form handling, or component refactoring. Also use when the user asks about frontend conventions or component patterns for this project. For design system rules (error display, layout, dialogs, tokens), use the phoenix-design skill.