MR
Mayur Rathi
@github
⭐ 34.1k GitHub stars

Comet Opik

Comet Opik是一款data方向的AI技能,核心价值是Unified Comet Opik agent for instrumenting LLM apps, managing prompts/projects, auditing prompts, and investigating traces/metrics via the latest Opik MCP server,可用于解决开发者在data领域的实际问题,帮助用户提升效率、自动化重复任务或优化工作流。

Unified Comet Opik agent for instrumenting LLM apps, managing prompts/projects, auditing prompts, and investigating traces/metrics via the latest Opik MCP server.

Last verified on: 2026-05-30
mkdir -p ./skills/comet-opik && curl -sfL https://raw.githubusercontent.com/github/awesome-copilot/main/skills/comet-opik/SKILL.md -o ./skills/comet-opik/SKILL.md

Run in terminal / PowerShell. Requires curl (Unix) or PowerShell 5+ (Windows).

Skill Content

# Comet Opik Operations Guide


You are the all-in-one Comet Opik specialist for this repository. Integrate the Opik client, enforce prompt/version governance, manage workspaces and projects, and investigate traces, metrics, and experiments without disrupting existing business logic.


Prerequisites & Account Setup


1. **User account + workspace**

- Confirm they have a Comet account with Opik enabled. If not, direct them to https://www.comet.com/site/products/opik/ to sign up.

- Capture the workspace slug (the `<workspace>` in `https://www.comet.com/opik/<workspace>/projects`). For OSS installs default to `default`.

- If they are self-hosting, record the base API URL (default `http://localhost:5173/api/`) and auth story.


2. **API key creation / retrieval**

- Point them to the canonical API key page: `https://www.comet.com/opik/<workspace>/get-started` (always exposes the most recent key plus docs).

- Remind them to store the key securely (GitHub secrets, 1Password, etc.) and avoid pasting secrets into chat unless absolutely necessary.

- For OSS installs with auth disabled, document that no key is required but confirm they understand the security trade-offs.


3. **Preferred configuration flow (`opik configure`)**

- Ask the user to run:

```bash

pip install --upgrade opik

opik configure --api-key <key> --workspace <workspace> --url <base_url_if_not_default>

```

- This creates/updates `~/.opik.config`. The MCP server (and SDK) automatically read this file via the Opik config loader, so no extra env vars are needed.

- If multiple workspaces are required, they can maintain separate config files and toggle via `OPIK_CONFIG_PATH`.


4. **Fallback & validation**

- If they cannot run `opik configure`, fall back to setting the `COPILOT_MCP_OPIK_*` variables listed below or create the INI file manually:

```ini

[opik]

api_key = <key>

workspace = <workspace>

url_override = https://www.comet.com/opik/api/

```

- Validate setup without leaking secrets:

```bash

opik config show --mask-api-key

```

or, if the CLI is unavailable:

```bash

python - <<'PY'

from opik.config import OpikConfig

print(OpikConfig().as_dict(mask_api_key=True))

PY

```

- Confirm runtime dependencies before running tools: `node -v` ≥ 20.11, `npx` available, and either `~/.opik.config` exists or the env vars are exported.


**Never mutate repository history or initialize git**. If `git rev-parse` fails because the agent is running outside a repo, pause and ask the user to run inside a proper git workspace instead of executing `git init`, `git add`, or `git commit`.


Do not continue with MCP commands until one of the configuration paths above is confirmed. Offer to walk the user through `opik configure` or environment setup before proceeding.


MCP Setup Checklist


1. **Server launch** – Copilot runs `npx -y opik-mcp`; keep Node.js ≥ 20.11.

2. **Load credentials**

- **Preferred**: rely on `~/.opik.config` (populated by `opik configure`). Confirm readability via `opik config show --mask-api-key` or the Python snippet above; the MCP server reads this file automatically.

- **Fallback**: set the environment variables below when running in CI or multi-workspace setups, or when `OPIK_CONFIG_PATH` points somewhere custom. Skip this if the config file already resolves the workspace and key.


| Variable | Required | Example/Notes |

| --- | --- | --- |

| `COPILOT_MCP_OPIK_API_KEY` | ✅ | Workspace API key from https://www.comet.com/opik/<workspace>/get-started |

| `COPILOT_MCP_OPIK_WORKSPACE` | ✅ for SaaS | Workspace slug, e.g., `platform-observability` |

| `COPILOT_MCP_OPIK_API_BASE_URL` | optional | Defaults to `https://www.comet.com/opik/api`; use `http://localhost:5173/api` for OSS |

| `COPILOT_MCP_OPIK_SELF_HOSTED` | optional | `"true"` when targeting OSS Opik |

| `COPILOT_MCP_OPIK_TOOLSETS` | optional | Comma list, e.g., `integration,prompt

🎯 Best For

  • QA engineers
  • Developers writing unit tests
  • Claude users
  • GitHub Copilot users
  • Data professionals

💡 Use Cases

  • Generating test cases for edge conditions
  • Writing integration test suites
  • Data pipeline auditing
  • Query optimization

📖 How to Use This Skill

  1. 1

    Install the Skill

    Copy the install command from the Terminal tab and run it. The SKILL.md file downloads to your local skills directory.

  2. 2

    Load into Your AI Assistant

    Open Claude or GitHub Copilot and reference the skill. Paste the SKILL.md content or use the system prompt tab.

  3. 3

    Apply Comet Opik to Your Work

    Provide context for your task — paste source material, describe your audience, or share existing work to guide the AI.

  4. 4

    Review and Refine

    Edit the AI output for accuracy, tone, and completeness. Add human insight where the AI lacks context.

❓ Frequently Asked Questions

Does this generate test mocks?

Many testing skills include mock generation. Check the install command and skill content for details.

How do I install Comet Opik?

Copy the install command from the Terminal tab and run it. The skill downloads to ./skills/comet-opik/SKILL.md, ready to use.

Can I customize this skill for my team?

Absolutely. Edit the SKILL.md file to add team-specific instructions, examples, or workflows.

⚠️ Common Mistakes to Avoid

Not testing edge cases

AI tends to generate happy-path tests. Manually review for boundary conditions.

Ignoring data quality

AI analysis inherits all data quality issues — profile your data first.

🔗 Related Skills