fix(skills): hide every non-end-user skill, use Azure deployment names, keep the restart block out of the user's shell

This commit is contained in:
mateo-berri 2026-10-28 14:11:01 -07:00
parent e189d5683b
commit 335e252e13
10 changed files with 32 additions and 8 deletions

View file

@ -1,6 +1,8 @@
---
name: rust-error
description: Define, wrap, convert, classify, report or test Rust error types in litellm-rust with thiserror. Use when adding an error type or variant, mapping one crate's error into another, turning an error into a gateway response or Python exception, deciding retry or fault from an error, or replacing call sites that build errors from strings
metadata:
internal: true
---
# Rust errors

View file

@ -1,6 +1,8 @@
---
name: rust-gateway
description: Add or change an HTTP route, extractor, response envelope, stream or router mount in the litellm-rust gateway crates (crates/gateway and crates/gateway-*). Use when adding an endpoint, parsing a request body, choosing an error envelope for an API surface, relaying SSE, or writing a router-level test
metadata:
internal: true
---
# Rust gateway

View file

@ -1,6 +1,8 @@
---
name: rust-string-enums
description: Define or refactor Rust string-valued enums and their Serde adapters in litellm-rust, using Strum and serde_with while preserving parsing, wire values, and schemas
metadata:
internal: true
---
# Rust string enums

View file

@ -1,6 +1,8 @@
---
name: rust-tracing
description: Add or change Rust diagnostic tracing in litellm-rust, including route spans, subscriber layers, and Python logger delivery
metadata:
internal: true
---
# Rust tracing

View file

@ -122,7 +122,7 @@ general_settings:
master_key: os.environ/LITELLM_MASTER_KEY
```
Add one entry per model. Providers that need more than a key, like Azure or Bedrock, list their `litellm_params` on their page under https://docs.litellm.ai/docs/providers. Point every secret at `.env` through `os.environ/NAME` the same way
Add one entry per model. On Azure, ask the user for each deployment's name and use `azure/<deployment name>` as `model`, since Azure routes by deployment and a name from the lookup works only when the deployment has that same name. Providers that need more than a key, like Azure or Bedrock, list their `litellm_params` on their page under https://docs.litellm.ai/docs/providers. Point every secret at `.env` through `os.environ/NAME` the same way
## 6. Their own Postgres, on the uv path
@ -186,7 +186,7 @@ Tell the user, without printing any secret:
- The base URL is `http://127.0.0.1:4000`. Any OpenAI-compatible client works with it as the base URL and the master key or a virtual key as the API key
- The master key is `LITELLM_MASTER_KEY` in the folder's `.env`, or `general_settings.master_key` in `litellm_config.yaml` when they used `litellm --setup`
- To stop it, `kill "$(cat litellm.pid)"` (uv), `docker stop litellm` (Docker), `<folder>/litellm-gateway stop` (quickstart), or Ctrl+C in its window (`litellm --setup`). To start it again, `docker start litellm`, `<folder>/litellm-gateway start`, on uv the whole step 7 command as you ran it, loader line and PATH export included, shown as a code block and never paraphrased, since a new shell has neither, or for `litellm --setup` `LITELLM_MODE=PRODUCTION <bin>/litellm --config litellm_config.yaml --host 127.0.0.1 --port <port>` in a terminal window in that folder, with `<bin>` and `<port>` filled in, since running the wizard again writes a new config with a new master key. `update` and `uninstall` update or remove a quickstart install. Give the quickstart commands with the folder's full path, since a bare `litellm-gateway` is on PATH only when `~/.local/bin` is, and can belong to an earlier install
- To stop it, `kill "$(cat litellm.pid)"` (uv), `docker stop litellm` (Docker), `<folder>/litellm-gateway stop` (quickstart), or Ctrl+C in its window (`litellm --setup`). To start it again, `docker start litellm`, `<folder>/litellm-gateway start`, on uv the whole step 7 command as you ran it, loader line and PATH export included, wrapped in `( ... )` so their shell keeps its own settings, shown as a code block and never paraphrased, since a new shell has neither, or for `litellm --setup` `LITELLM_MODE=PRODUCTION <bin>/litellm --config litellm_config.yaml --host 127.0.0.1 --port <port>` in a terminal window in that folder, with `<bin>` and `<port>` filled in, since running the wizard again writes a new config with a new master key. `update` and `uninstall` update or remove a quickstart install. Give the quickstart commands with the folder's full path, since a bare `litellm-gateway` is on PATH only when `~/.local/bin` is, and can belong to an earlier install
- With Postgres, the Admin UI is at `http://127.0.0.1:4000/ui` (user `admin`, password the master key), and `POST /key/generate` with the master key creates virtual keys with their own budgets and model lists. Without Postgres, both need step 3 or 6 first
- The Admin UI warns that the master-key login is a shared secret, which is fine while only this machine reaches the proxy. Before anyone else can reach it, invite an admin with their own password on the Internal Users page, then set `general_settings.disable_env_credential_login: true` in the proxy config
- To manage the running proxy from a coding agent (keys, teams, users, models, MCP servers), install `npx skills add BerriAI/litellm-skills -g`

View file

@ -1,6 +1,8 @@
---
name: slack-gif-creator
description: Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."
metadata:
internal: true
---
# Slack GIF Creator

View file

@ -1,6 +1,8 @@
---
name: test-delete-skill
description: A test skill created specifically for deletion testing
metadata:
internal: true
---
# Test Delete Skill

View file

@ -1,6 +1,8 @@
---
name: test-skill-litellm
description: A test skill created by LiteLLM automated tests
metadata:
internal: true
---
# Test Skill

View file

@ -1,3 +1,4 @@
import subprocess
from pathlib import Path
from typing import Final
@ -7,8 +8,14 @@ import yaml
_REPO_ROOT: Final = Path(__file__).resolve().parents[2]
_SKILLS_DIR: Final = _REPO_ROOT / "skills"
_SKILL_DIRECTORIES: Final = tuple(sorted(skill_file.parent for skill_file in _SKILLS_DIR.glob("*/SKILL.md")))
_CONTRIBUTOR_SKILL_DIRECTORIES: Final = tuple(
sorted(skill_file.parent for skill_file in _REPO_ROOT.glob(".*/skills/*/SKILL.md"))
_TRACKED_SKILL_FILES: Final = tuple(
_REPO_ROOT / tracked_path
for tracked_path in subprocess.run(
["git", "ls-files", "SKILL.md", "*/SKILL.md"], cwd=_REPO_ROOT, check=True, capture_output=True, text=True
).stdout.splitlines()
)
_NON_END_USER_SKILL_DIRECTORIES: Final = tuple(
sorted(skill_file.parent for skill_file in _TRACKED_SKILL_FILES if skill_file.parent.parent != _SKILLS_DIR)
)
@ -29,14 +36,15 @@ def test_skill_frontmatter_has_string_name_matching_its_directory_and_a_descript
@pytest.mark.parametrize(
"skill_directory",
_CONTRIBUTOR_SKILL_DIRECTORIES,
ids=lambda path: f"{path.parent.parent.name}/{path.name}",
_NON_END_USER_SKILL_DIRECTORIES,
ids=lambda path: str(path.relative_to(_REPO_ROOT)),
)
def test_contributor_skill_at_repo_root_is_hidden_from_end_user_skill_installs(skill_directory: Path) -> None:
def test_skill_outside_skills_folder_is_hidden_from_end_user_skill_installs(skill_directory: Path) -> None:
frontmatter: Final = _frontmatter(skill_directory)
assert isinstance(frontmatter, dict), frontmatter
metadata: Final = frontmatter.get("metadata")
assert isinstance(metadata, dict) and metadata.get("internal") is True, (
f"{skill_directory} needs `metadata: {{internal: true}}`, or `npx skills add BerriAI/litellm` installs it "
"for end users next to skills/ (skills CLI docs/creating-skills.md, checked on 1.7.4 2026-10-28)"
"for end users, from a root dot-folder always and from anywhere with --full-depth (skills CLI 1.7.4, "
"checked 2026-10-28)"
)

View file

@ -1,6 +1,8 @@
---
name: url-state
description: Read or write dashboard URL query state (tabs, filters, pagination, deep links, demo flags) with nuqs instead of raw history or URLSearchParams
metadata:
internal: true
---
# URL state