Add Arize and Phoenix LLM observability skills#1204
Add Arize and Phoenix LLM observability skills#1204jimbobbennett wants to merge 6 commits intogithub:stagedfrom
Conversation
Add skills for Arize AI platform covering trace export, instrumentation, datasets, experiments, evaluators, AI provider integrations, annotations, prompt optimization, and deep linking to the Arize UI. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add skills for Phoenix (Arize open-source) covering CLI debugging, LLM evaluation workflows, and OpenInference tracing/instrumentation. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
jimbobbennett
changed the title
…ll ignore Remove .DS_Store artifact from winmd-api-search asset listing in generated README.skills.md so it matches the CI Linux build output. Add queston to codespell ignore list (intentional misspelling example in arize-dataset skill). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Bundle the 9 Arize skills into an arize-ax plugin and the 3 Phoenix skills into a phoenix plugin for easier installation as single packages. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
There was a problem hiding this comment.
Pull request overview
Adds Arize/Phoenix observability content to the repo as installable Copilot CLI plugins, including new skill documentation for Phoenix tracing/evals and Arize AX workflows.
Changes:
- Introduces new Phoenix plugin with tracing/evals/CLI skills and extensive reference docs.
- Introduces new Arize AX plugin bundling multiple AX-focused skills (trace export, datasets/experiments/evaluators, annotations, prompt optimization, deep links).
- Registers both plugins in the docs index and marketplace metadata; updates codespell ignore list for an intentional example typo.
Reviewed changes
Copilot reviewed 101 out of 101 changed files in this pull request and generated 6 comments.
Show a summary per file
| File | Description |
|---|---|
| skills/phoenix-tracing/SKILL.md | Index for Phoenix tracing skill (setup/instrumentation/span kinds/production/feedback). |
| skills/phoenix-tracing/references/README.md | Reference README describing the tracing docs organization. |
| skills/phoenix-tracing/references/fundamentals-overview.md | Introduces trace/span concepts and hierarchy. |
| skills/phoenix-tracing/references/fundamentals-required-attributes.md | Defines required/recommended attributes and valid OpenInference span kinds. |
| skills/phoenix-tracing/references/fundamentals-universal-attributes.md | Documents cross-cutting attributes like I/O, session/user, metadata. |
| skills/phoenix-tracing/references/fundamentals-flattening.md | Explains dot-notation flattening rules for OpenInference attributes. |
| skills/phoenix-tracing/references/span-llm.md | LLM span attribute guide and examples. |
| skills/phoenix-tracing/references/span-chain.md | CHAIN span attribute guide and examples. |
| skills/phoenix-tracing/references/span-retriever.md | RETRIEVER span schema (flattened documents) and examples. |
| skills/phoenix-tracing/references/span-reranker.md | RERANKER span schema and examples. |
| skills/phoenix-tracing/references/span-tool.md | TOOL span schema and examples. |
| skills/phoenix-tracing/references/span-agent.md | AGENT span overview and example. |
| skills/phoenix-tracing/references/span-embedding.md | EMBEDDING span schema and examples. |
| skills/phoenix-tracing/references/span-guardrail.md | GUARDRAIL span schema and examples. |
| skills/phoenix-tracing/references/span-evaluator.md | EVALUATOR span schema and examples. |
| skills/phoenix-tracing/references/setup-python.md | Python install/config for Phoenix OTEL tracing. |
| skills/phoenix-tracing/references/setup-typescript.md | TypeScript/JS install/config for Phoenix OTEL tracing. |
| skills/phoenix-tracing/references/instrumentation-auto-python.md | Python auto-instrumentation guidance for supported libraries. |
| skills/phoenix-tracing/references/instrumentation-auto-typescript.md | TypeScript auto-instrumentation guidance and limitations. |
| skills/phoenix-tracing/references/instrumentation-manual-python.md | Python manual instrumentation patterns (decorators/context managers). |
| skills/phoenix-tracing/references/instrumentation-manual-typescript.md | TypeScript manual instrumentation patterns (wrappers/withSpan). |
| skills/phoenix-tracing/references/projects-python.md | Project naming/grouping patterns for Phoenix (Python). |
| skills/phoenix-tracing/references/projects-typescript.md | Project naming/grouping patterns for Phoenix (TypeScript). |
| skills/phoenix-tracing/references/sessions-python.md | Session tracking via context propagation (Python). |
| skills/phoenix-tracing/references/sessions-typescript.md | Session tracking patterns using withSpan and/or Context API (TypeScript). |
| skills/phoenix-tracing/references/metadata-python.md | Adding session/user/metadata/tags via openinference instrumentation helpers (Python). |
| skills/phoenix-tracing/references/metadata-typescript.md | Adding custom metadata using context/span APIs (TypeScript). |
| skills/phoenix-tracing/references/production-python.md | Production masking/filtering examples (Python). |
| skills/phoenix-tracing/references/production-typescript.md | Production batching/masking/filtering/shutdown patterns (TypeScript). |
| skills/phoenix-tracing/references/annotations-overview.md | Conceptual overview of annotations and fields. |
| skills/phoenix-tracing/references/annotations-python.md | Python client patterns for span/trace/session/document annotations. |
| skills/phoenix-tracing/references/annotations-typescript.md | TypeScript client patterns for span/trace/session/document annotations. |
| skills/phoenix-evals/SKILL.md | Index for Phoenix evals skill (setup, evaluators, datasets/experiments, production). |
| skills/phoenix-evals/references/setup-python.md | Phoenix evals/experiments package setup (Python) with “Evals 2.0” import guidance. |
| skills/phoenix-evals/references/setup-typescript.md | Phoenix evals/experiments package setup (TypeScript). |
| skills/phoenix-evals/references/fundamentals.md | High-level eval concepts and score structure/patterns. |
| skills/phoenix-evals/references/fundamentals-model-selection.md | Guidance for judge model selection and iteration. |
| skills/phoenix-evals/references/fundamentals-anti-patterns.md | Common mistakes and corrective patterns. |
| skills/phoenix-evals/references/evaluators-overview.md | Framework for when/how to build evaluators. |
| skills/phoenix-evals/references/evaluators-pre-built.md | Notes on pre-built evaluators and validation requirement. |
| skills/phoenix-evals/references/evaluators-code-python.md | Patterns for deterministic evaluators (Python). |
| skills/phoenix-evals/references/evaluators-code-typescript.md | Patterns for deterministic evaluators (TypeScript). |
| skills/phoenix-evals/references/evaluators-llm-python.md | Patterns for LLM-based evaluators (Python). |
| skills/phoenix-evals/references/evaluators-llm-typescript.md | Patterns for LLM-based evaluators (TypeScript). |
| skills/phoenix-evals/references/evaluators-custom-templates.md | Template structure guidance for LLM judges. |
| skills/phoenix-evals/references/evaluators-rag.md | RAG-specific eval approach (retrieval vs generation). |
| skills/phoenix-evals/references/experiments-overview.md | Core structure of dataset/task/evaluators/experiment. |
| skills/phoenix-evals/references/experiments-datasets-python.md | Dataset creation and usage patterns (Python). |
| skills/phoenix-evals/references/experiments-datasets-typescript.md | Dataset creation and usage patterns (TypeScript). |
| skills/phoenix-evals/references/experiments-running-python.md | Running experiments and interpreting results (Python). |
| skills/phoenix-evals/references/experiments-running-typescript.md | Running experiments and interpreting results (TypeScript). |
| skills/phoenix-evals/references/experiments-synthetic-python.md | Synthetic dataset generation patterns (Python). |
| skills/phoenix-evals/references/experiments-synthetic-typescript.md | Synthetic dataset generation patterns (TypeScript). |
| skills/phoenix-evals/references/evaluate-dataframe-python.md | Batch evaluation API details and result extraction (Python). |
| skills/phoenix-evals/references/validation.md | Evaluator validation metrics and dataset practices. |
| skills/phoenix-evals/references/validation-evaluators-python.md | Evaluator validation computations/patterns (Python). |
| skills/phoenix-evals/references/validation-evaluators-typescript.md | Evaluator validation experiment pattern (TypeScript). |
| skills/phoenix-evals/references/observe-tracing-setup.md | Capturing the right tracing attributes to enable eval workflows. |
| skills/phoenix-evals/references/observe-sampling-python.md | Sampling strategies for reviewing production traces (Python). |
| skills/phoenix-evals/references/observe-sampling-typescript.md | Sampling strategies for reviewing production traces (TypeScript). |
| skills/phoenix-evals/references/error-analysis.md | Workflow for discovering failure modes from traces. |
| skills/phoenix-evals/references/error-analysis-multi-turn.md | Guidance for analyzing multi-turn conversation failures. |
| skills/phoenix-evals/references/axial-coding.md | Method to group notes into failure taxonomies and annotate spans. |
| skills/phoenix-evals/references/production-overview.md | CI evals vs production monitoring overview (Python/TS examples). |
| skills/phoenix-evals/references/production-guardrails.md | Guardrails vs evaluators distinction. |
| skills/phoenix-evals/references/production-continuous.md | Continuous evaluation loop and alerting guidance. |
| skills/phoenix-cli/SKILL.md | Phoenix CLI skill describing trace/span/dataset/experiment/query workflows. |
| skills/arize-trace/references/ax-setup.md | AX CLI troubleshooting reference. |
| skills/arize-trace/references/ax-profiles.md | AX profile/auth setup reference and security guidance for keys. |
| skills/arize-prompt-optimization/references/ax-setup.md | AX CLI troubleshooting reference (prompt optimization skill). |
| skills/arize-prompt-optimization/references/ax-profiles.md | AX profile/auth setup reference (prompt optimization skill). |
| skills/arize-link/references/EXAMPLES.md | Concrete Arize UI deep-link URL templates. |
| skills/arize-link/SKILL.md | Deep-link generation skill instructions and templates. |
| skills/arize-instrumentation/references/ax-profiles.md | AX profile/auth setup reference (instrumentation skill). |
| skills/arize-experiment/references/ax-setup.md | AX CLI troubleshooting reference (experiment skill). |
| skills/arize-experiment/references/ax-profiles.md | AX profile/auth setup reference (experiment skill). |
| skills/arize-evaluator/references/ax-setup.md | AX CLI troubleshooting reference (evaluator skill). |
| skills/arize-evaluator/references/ax-profiles.md | AX profile/auth setup reference (evaluator skill). |
| skills/arize-dataset/references/ax-setup.md | AX CLI troubleshooting reference (dataset skill). |
| skills/arize-dataset/references/ax-profiles.md | AX profile/auth setup reference (dataset skill). |
| skills/arize-annotation/references/ax-setup.md | AX CLI troubleshooting reference (annotation skill). |
| skills/arize-annotation/references/ax-profiles.md | AX profile/auth setup reference (annotation skill). |
| skills/arize-ai-provider-integration/references/ax-setup.md | AX CLI troubleshooting reference (AI provider integration skill). |
| skills/arize-ai-provider-integration/references/ax-profiles.md | AX profile/auth setup reference (AI provider integration skill). |
| plugins/phoenix/README.md | Plugin README describing included Phoenix skills. |
| plugins/phoenix/.github/plugin/plugin.json | Plugin manifest for the Phoenix plugin. |
| plugins/arize-ax/README.md | Plugin README describing included Arize AX skills. |
| plugins/arize-ax/.github/plugin/plugin.json | Plugin manifest for the Arize AX plugin. |
| docs/README.plugins.md | Adds both plugins to the plugins documentation table. |
| .github/plugin/marketplace.json | Registers both plugins in the marketplace metadata. |
| .codespellrc | Adds an ignore word for an intentional misspelling example. |
| "./skills/phoenix-cli/", | ||
| "./skills/phoenix-evals/", | ||
| "./skills/phoenix-tracing/" |
There was a problem hiding this comment.
The plugin.json skills entries use paths like ./skills/phoenix-cli/, but there is no skills/ directory under plugins/phoenix/.github/plugin/ (or under plugins/phoenix/). These paths will resolve to non-existent locations when loading the plugin. Update the paths to correctly reference the intended skill directories (likely under the repo root).
| "./skills/phoenix-cli/", | |
| "./skills/phoenix-evals/", | |
| "./skills/phoenix-tracing/" | |
| "../../../skills/phoenix-cli/", | |
| "../../../skills/phoenix-evals/", | |
| "../../../skills/phoenix-tracing/" |
| "./skills/arize-ai-provider-integration/", | ||
| "./skills/arize-annotation/", | ||
| "./skills/arize-dataset/", | ||
| "./skills/arize-evaluator/", | ||
| "./skills/arize-experiment/", | ||
| "./skills/arize-instrumentation/", | ||
| "./skills/arize-link/", | ||
| "./skills/arize-prompt-optimization/", | ||
| "./skills/arize-trace/" |
There was a problem hiding this comment.
The plugin.json skills entries use paths like ./skills/arize-trace/. Unless this plugin includes its own skills/ folder colocated with the plugin.json, these relative paths will point to non-existent locations. Please verify the expected resolution base for plugin item paths and adjust these skill paths accordingly so the plugin loads its skills.
| "./skills/arize-ai-provider-integration/", | |
| "./skills/arize-annotation/", | |
| "./skills/arize-dataset/", | |
| "./skills/arize-evaluator/", | |
| "./skills/arize-experiment/", | |
| "./skills/arize-instrumentation/", | |
| "./skills/arize-link/", | |
| "./skills/arize-prompt-optimization/", | |
| "./skills/arize-trace/" | |
| "../../skills/arize-ai-provider-integration/", | |
| "../../skills/arize-annotation/", | |
| "../../skills/arize-dataset/", | |
| "../../skills/arize-evaluator/", | |
| "../../skills/arize-experiment/", | |
| "../../skills/arize-instrumentation/", | |
| "../../skills/arize-link/", | |
| "../../skills/arize-prompt-optimization/", | |
| "../../skills/arize-trace/" |
| ```bash | ||
| # By category prefix | ||
| rules/setup-* # Installation and configuration | ||
| rules/instrumentation-* # Auto and manual tracing | ||
| rules/span-* # Span type specifications | ||
| rules/sessions-* # Session tracking | ||
| rules/production-* # Production deployment | ||
| rules/fundamentals-* # Core concepts | ||
| rules/attributes-* # Attribute specifications | ||
|
|
||
| # By language | ||
| rules/*-python.md # Python implementations | ||
| rules/*-typescript.md # TypeScript implementations | ||
| ``` |
There was a problem hiding this comment.
The skill docs refer to a rules/ directory (including the navigation examples), but the repository structure for this skill uses references/. This makes the paths in the instructions incorrect and will confuse users following the guidance. Update the references from rules/ to the actual directory name used by this skill (or rename the folder to match).
| ### Reference Files | ||
|
|
||
| - `fundamentals-overview` - Traces, spans, attributes basics | ||
| - `fundamentals-required-attributes` - Required fields per span type | ||
| - `fundamentals-universal-attributes` - Common attributes (user.id, session.id) | ||
| - `fundamentals-flattening` - JSON flattening rules | ||
| - `attributes-messages` - Chat message format | ||
| - `attributes-metadata` - Custom metadata schema | ||
| - `attributes-graph` - Agent workflow attributes | ||
| - `attributes-exceptions` - Error tracking |
There was a problem hiding this comment.
This SKILL index lists several attributes-* reference files (messages/metadata/graph/exceptions), but those files do not exist under skills/phoenix-tracing/references/. Either add the missing reference docs or remove/replace these entries so the index doesn’t point to dead links.
| ## File Organization | ||
|
|
||
| All files in flat `rules/` directory with semantic prefixes: | ||
|
|
||
| - `span-*` - Span kinds (LLM, CHAIN, TOOL, etc.) | ||
| - `setup-*`, `instrumentation-*` - Getting started guides | ||
| - `fundamentals-*`, `attributes-*` - Reference docs | ||
| - `annotations-*`, `export-*` - Advanced features |
There was a problem hiding this comment.
This README states that all files live in a rules/ directory, but the skill actually stores them under references/. Please align the directory name in this description with the real folder structure so users can find the files.
| npx @arizeai/phoenix-cli traces \ | ||
| --endpoint http://localhost:6006 \ | ||
| --project your-app \ | ||
| --format raw \ | ||
| --no-progress | \ | ||
| jq '.[] | select(.spans[0].attributes["session.id"] == "YOUR-SESSION-ID")' |
There was a problem hiding this comment.
The shell example has an extra pipe before the line continuation (--no-progress | \), which will break the command. Remove the stray | so the pipeline to jq works as intended.
Move arize supporting files from references/ to root level and rename phoenix references/ to rules/ to exactly match the original source repository folder structures. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
| import { createClient } from "phoenix-client"; | ||
| const client = createClient(); // Default: http://localhost:6006 |
There was a problem hiding this comment.
The TypeScript examples import from the phoenix-client npm package, which is unrelated to Arize Phoenix and will cause these examples to fail for users following this guide. Use @arizeai/phoenix-client (and the appropriate subpath exports such as @arizeai/phoenix-client/spans) consistently instead.
| // TypeScript | ||
| import { registerPhoenix } from "@arizeai/phoenix-otel"; | ||
|
|
||
| registerPhoenix({ projectName: "my-app", autoInstrument: true }); | ||
| ``` |
There was a problem hiding this comment.
registerPhoenix isn’t an export of @arizeai/phoenix-otel (the init API is register). This snippet will fail to compile as-is; update the import and call to the supported API.
| ```python theme={null} | ||
| @tracer.chain |
There was a problem hiding this comment.
The code fence includes theme={null} after the language tag, which isn’t standard GitHub-flavored markdown and can break rendering/copy-paste. Remove the extra fence attributes so it’s just a normal python code block.
| ```python theme={null} | ||
| def process_query(query: str): |
There was a problem hiding this comment.
This code fence includes theme={null} after the language tag; GitHub markdown doesn’t support that attribute. Use a plain ```python fence so the snippet renders and copies correctly.
| **Note:** `@opentelemetry/api` is NOT needed - it's only for manual span management. | ||
|
|
There was a problem hiding this comment.
This note says @opentelemetry/api is not needed, but the later “Context API Pattern” section imports it. Clarify that it’s not needed for the basic withSpan approach, but is required if readers choose the Context API approach.
|
|
||
| If an `ax` command fails, troubleshoot based on the error: | ||
| - `command not found` or version error → see ax-setup.md | ||
| - `401 Unauthorized` / missing API key → run `ax profiles show` to inspect the current profile. If the profile is missing or the API key is wrong: check `.env` for `ARIZE_API_KEY` and use it to create/update the profile via ax-profiles.md. If `.env` has no key either, ask the user for their Arize API key (https://app.arize.com/admin > API Keys) |
There was a problem hiding this comment.
This troubleshooting step says to “ask the user for their Arize API key”, which risks prompting users to paste secrets into chat/logs. Please align with ax-profiles.md: instruct users to set ARIZE_API_KEY in their own shell (or .env) and never paste the raw key into the conversation.
|
|
||
| If an `ax` command fails, troubleshoot based on the error: | ||
| - `command not found` or version error → see ax-setup.md | ||
| - `401 Unauthorized` / missing API key → run `ax profiles show` to inspect the current profile. If the profile is missing or the API key is wrong: check `.env` for `ARIZE_API_KEY` and use it to create/update the profile via ax-profiles.md. If `.env` has no key either, ask the user for their Arize API key (https://app.arize.com/admin > API Keys) |
There was a problem hiding this comment.
This troubleshooting step says to “ask the user for their Arize API key”, which risks encouraging secret sharing in chat/logs. Please instead direct users to set ARIZE_API_KEY in their own environment (per ax-profiles.md) and explicitly state not to paste the key into the conversation.
|
|
||
| If an `ax` command fails, troubleshoot based on the error: | ||
| - `command not found` or version error → see ax-setup.md | ||
| - `401 Unauthorized` / missing API key → run `ax profiles show` to inspect the current profile. If the profile is missing or the API key is wrong: check `.env` for `ARIZE_API_KEY` and use it to create/update the profile via ax-profiles.md. If `.env` has no key either, ask the user for their Arize API key (https://app.arize.com/admin > API Keys) |
There was a problem hiding this comment.
This suggests asking the user for their Arize API key, which risks prompting users to paste secrets into the conversation. Please update to instruct users to set ARIZE_API_KEY locally and explicitly say not to share the key in chat (see ax-profiles.md).
| - `401 Unauthorized` / missing API key → run `ax profiles show` to inspect the current profile. If the profile is missing or the API key is wrong: check `.env` for `ARIZE_API_KEY` and use it to create/update the profile via ax-profiles.md. If `.env` has no key either, ask the user for their Arize API key (https://app.arize.com/admin > API Keys) | |
| - `401 Unauthorized` / missing API key → run `ax profiles show` to inspect the current profile. If the profile is missing or the API key is wrong: check `.env` for `ARIZE_API_KEY` and use it to create/update the profile via ax-profiles.md. If `.env` has no key either, instruct the user to create or locate an Arize API key in https://app.arize.com/admin and set it locally as the `ARIZE_API_KEY` environment variable (for example in their `.env` file). Explicitly tell the user not to paste or share their API key in this chat or in any logs. |
|
|
||
| If an `ax` command fails, troubleshoot based on the error: | ||
| - `command not found` or version error → see ax-setup.md | ||
| - `401 Unauthorized` / missing API key → run `ax profiles show` to inspect the current profile. If the profile is missing or the API key is wrong: check `.env` for `ARIZE_API_KEY` and use it to create/update the profile via ax-profiles.md. If `.env` has no key either, ask the user for their Arize API key (https://app.arize.com/admin > API Keys) |
There was a problem hiding this comment.
This suggests asking the user for their Arize API key, which can lead to secret leakage in chat logs. Please update to instruct users to set ARIZE_API_KEY locally (env var / .env) and avoid requesting the raw key in the conversation (consistent with ax-profiles.md).
| - `401 Unauthorized` / missing API key → run `ax profiles show` to inspect the current profile. If the profile is missing or the API key is wrong: check `.env` for `ARIZE_API_KEY` and use it to create/update the profile via ax-profiles.md. If `.env` has no key either, ask the user for their Arize API key (https://app.arize.com/admin > API Keys) | |
| - `401 Unauthorized` / missing API key → run `ax profiles show` to inspect the current profile. If the profile is missing or the API key is wrong: check `.env` for `ARIZE_API_KEY` and use it to create/update the profile via ax-profiles.md. If `.env` has no key either, instruct the user (without asking them to paste the key here) to generate an API key in https://app.arize.com/admin > API Keys and set it locally as `ARIZE_API_KEY` (env var or `.env`), then rerun the profile setup |
|
|
||
| If an `ax` command fails, troubleshoot based on the error: | ||
| - `command not found` or version error → see ax-setup.md | ||
| - `401 Unauthorized` / missing API key → run `ax profiles show` to inspect the current profile. If the profile is missing or the API key is wrong: check `.env` for `ARIZE_API_KEY` and use it to create/update the profile via ax-profiles.md. If `.env` has no key either, ask the user for their Arize API key (https://app.arize.com/admin > API Keys) |
There was a problem hiding this comment.
This suggests asking the user for their Arize API key; please avoid prompting users to paste secrets into chat. Align with ax-profiles.md by instructing users to set ARIZE_API_KEY locally and explicitly stating not to share the raw key in the conversation.
| - `401 Unauthorized` / missing API key → run `ax profiles show` to inspect the current profile. If the profile is missing or the API key is wrong: check `.env` for `ARIZE_API_KEY` and use it to create/update the profile via ax-profiles.md. If `.env` has no key either, ask the user for their Arize API key (https://app.arize.com/admin > API Keys) | |
| - `401 Unauthorized` / missing API key → run `ax profiles show` to inspect the current profile. If the profile is missing or the API key is wrong: check `.env` for `ARIZE_API_KEY` and use it locally to create/update the profile via ax-profiles.md. If `.env` has no key either, instruct the user to generate an API key in the Arize UI (https://app.arize.com/admin > API Keys) and set it as `ARIZE_API_KEY` in their local environment or `.env` file. Do **not** ask the user to paste or share the raw API key in this chat. |
aaronpowell
left a comment
aaronpowell
left a comment
There was a problem hiding this comment.
For the skills, can you ensure that they are following the structure from the specification, so you probably want to leverage the references folder for things like ax-profiles.md and ax-setup.md.
Also, these files don't appear to be referenced from their companion SKILL.md file, so the agent using the skill isn't likely to pick them up/know when to use them.
Pull Request Checklist
npm startand verified thatREADME.mdis up to date.stagedbranch for this pull request.Description
Add skills for Arize AI platform covering trace export, instrumentation, datasets, experiments, evaluators, AI provider integrations, annotations, prompt optimization, and deep linking to the Arize UI.
Arize Skills source - https://github.com/Arize-ai/arize-skills
Phoenix Skills source - https://github.com/Arize-ai/phoenix/tree/main/skills
We will be adding an action to auto publish to this repo when we publish changes, as discussed in #1169
Type of Contribution
Additional Notes
By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.