dailyherolddailyherold/skills/portkey-status/SKILL.md

portkey-status

Skill0 starsChanged 33 days agoMITView on GitHub

Check Portkey model health with live API tests (basic + tool-use) and list virtual key budget limits. Always use this skill when the user asks about model availability, which providers are working, API latency, Portkey status, virtual key budgets or credits, or anything like "are my models up?", "check my providers", "which models are broken", "run portkey-status", or "test my portkey config". Also trigger when the user wants to validate their Portkey setup is functional or debug why a model isn't responding.

Reads credentials

In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- 1on1Skill
- context-reviewSkill
- gmail-inboxSkill
- lamport-problem-statementSkill
- learning-labSkill
- logseq-db-querySkill
- nix-sandboxSkill
- obsidian-zettelkastenSkill
- peer-reviewSkill
- proton-inboxSkill
- teams-extractorSkill
- theory-of-constraintsSkill

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Check for $PORTKEY_API_KEY in the environment first.
line 12
Distinctive:
After running, reproduce the results as a markdown table in your response (don't just show raw terminal output).
line 30

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Portkey Status

Scripts live in scripts/ under this skill's base directory (shown at the top of this file). Always run with uv run from that directory.

API key

Check for $PORTKEY_API_KEY in the environment first. If it's not set, ask the user where to find it — they may have it in a password manager, a secrets file, or a shell config. Don't assume any particular location.

echo ${PORTKEY_API_KEY:+set}  # check if set

Run commands

SCRIPTS="<skill-base-dir>/scripts"

PORTKEY_API_KEY="..." uv --directory "$SCRIPTS" run python main.py check            # test all models
PORTKEY_API_KEY="..." uv --directory "$SCRIPTS" run python main.py check openai     # filter by substring
PORTKEY_API_KEY="..." uv --directory "$SCRIPTS" run python main.py credits          # list virtual key budgets

Interpreting results

After running, reproduce the results as a markdown table in your response (don't just show raw terminal output). Then:

All passing — confirm everything looks healthy and note any slow models (>5s latency worth flagging).
Some failing — highlight the failing models and their error messages. Use the error text to guide debugging: 4xx errors usually mean a config or auth issue on that virtual key; 5xx means a provider-side problem; timeouts suggest the model may be rate-limited or overloaded. Suggest checking the relevant virtual key in the Portkey dashboard.
All failing — likely an API key or connectivity issue rather than individual model problems. Check the key is valid and Portkey is reachable.

The Tools column shows whether the model supports function/tool calling — failures there specifically matter if the user's app relies on agentic use.

Model config

Edit scripts/config.py to add, remove, or tweak models. Supported per-model fields:

Field	Default	Purpose
`id`	required	Portkey virtual key slug, e.g. `@openai/gpt-5.4`
`endpoint`	`"chat"`	Set to `"responses"` for models needing the Responses API
`skip_temperature`	`false`	Omit `temperature` param (some models reject it)
`tokens_param`	`"max_tokens"`	Use `"max_completion_tokens"` for newer OpenAI models
`skip_tools`	`false`	Skip tool-use test for models that don't support it

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free