Improve/skill review optimization

.github/workflows/skill-preview.yml

@@ -0,0 +1,13 @@
+name: Skill Review
+on:
+  pull_request:
+    paths: ['**/SKILL.md']
+jobs:
+  review:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+      contents: read
+    steps:
+      - uses: actions/checkout@v4
+      - uses: tesslio/skill-review@22e928dd837202b2b1d1397e0114c92e0fae5ead # main

add-key/SKILL.md

@@ -1,8 +1,6 @@
 ---
 name: add-key
-description: >
-  Generate a new API key on a live LiteLLM proxy. Asks for alias, scope
-  (user/team), budget, models, and expiry, then calls POST /key/generate.
+description: "Generate a new API key on a live LiteLLM proxy. Asks for alias, scope (user/team), budget, models, and expiry, then calls POST /key/generate. Use when the user wants to create, generate, or provision an API key on a LiteLLM proxy instance."
 license: MIT
 compatibility: Requires curl.
 metadata:
@@ -36,6 +34,9 @@ API reference: https://litellm.vercel.app/docs/proxy/virtual_keys
 ## Run
 
 ```bash
+BASE="$LITELLM_BASE_URL"
+KEY="$LITELLM_API_KEY"
+
 curl -s -X POST "$BASE/key/generate" \
   -H "Authorization: Bearer $KEY" \
   -H "Content-Type: application/json" \
@@ -49,10 +50,29 @@ curl -s -X POST "$BASE/key/generate" \
   }'
 ```
 
+## Verify
+
+Confirm the key was created:
+```bash
+curl -s "$BASE/key/info" \
+  -H "Authorization: Bearer <new_key>" | python3 -c "
+import sys, json
+d = json.load(sys.stdin)
+info = d.get('info', {})
+print(f'Alias: {info.get(\"key_alias\")}')
+print(f'Expires: {info.get(\"expires\")}')
+print(f'Budget: {info.get(\"max_budget\")}')
+print(f'Models: {info.get(\"models\")}')
+"
+```
+
 ## Output
 
 Show the user:
 - `key` — the actual key value (only shown once, tell them to save it)
 - `key_alias`, `expires`, `max_budget`, `models`
 
-On error show `detail` and the likely fix.
+On error:
+- **401** — check that `LITELLM_API_KEY` is a valid admin key
+- **400** — check required fields; verify `team_id`/`user_id` exists
+- Other errors — show `detail` and the likely fix

add-model/SKILL.md

@@ -1,9 +1,6 @@
 ---
 name: add-model
-description: >
-  Add a new model to a live LiteLLM proxy. Walks the user through picking a
-  provider, entering the deployment name and credentials, calls POST /model/new,
-  then test-calls the model to confirm it routes correctly.
+description: "Add a new model to a live LiteLLM proxy. Walks the user through picking a provider, entering the deployment name and credentials, calls POST /model/new, then test-calls the model to confirm it routes correctly. Use when the user wants to add, register, deploy, or configure a new model on a LiteLLM proxy instance."
 license: MIT
 compatibility: Requires curl.
 metadata:

add-team/SKILL.md

@@ -1,8 +1,6 @@
 ---
 name: add-team
-description: >
-  Create a new team on a live LiteLLM proxy. Asks for team name, budget, and
-  allowed models, then calls POST /team/new and shows the result.
+description: "Create a new team on a live LiteLLM proxy. Asks for team name, budget, and allowed models, then calls POST /team/new and shows the result. Use when the user wants to create a new team, set up team budgets, or configure model access for a team on the proxy."
 license: MIT
 compatibility: Requires curl.
 metadata:
@@ -35,6 +33,9 @@ API reference: https://litellm.vercel.app/docs/proxy/team_based_routing
 ## Run
 
 ```bash
+BASE="$LITELLM_BASE_URL"
+KEY="$LITELLM_API_KEY"
+
 curl -s -X POST "$BASE/team/new" \
   -H "Authorization: Bearer $KEY" \
   -H "Content-Type: application/json" \
@@ -47,10 +48,21 @@ curl -s -X POST "$BASE/team/new" \
   }'
 ```
 
+## Verify
+
+Confirm the team was created:
+```bash
+curl -s "$BASE/team/info?team_id=<team_id>" \
+  -H "Authorization: Bearer $KEY"
+```
+
 ## Output
 
 Show the user:
 - `team_id` — they'll need this to generate keys for the team
 - `team_alias`, `max_budget`, `models`
 
-On error show `detail` and the likely fix.
+On error:
+- **401** — check that `LITELLM_API_KEY` is a valid admin key
+- **400** — check required fields (team_alias is required)
+- Other errors — show `detail` and the likely fix

delete-model/SKILL.md

@@ -1,8 +1,6 @@
 ---
 name: delete-model
-description: >
-  Delete a model from a live LiteLLM proxy. Ask for the model name or model_id
-  and confirm before calling POST /model/delete.
+description: "Delete a model from a live LiteLLM proxy. Asks for the model name or model_id and confirms before calling POST /model/delete. Use when the user wants to remove, delete, or unregister a model from a LiteLLM proxy instance."
 license: MIT
 compatibility: Requires curl.
 metadata:

view-usage/SKILL.md

@@ -1,9 +1,6 @@
 ---
 name: view-usage
-description: >
-  Query spend and token activity on a live LiteLLM proxy. Shows daily usage
-  broken down by user, team, org, or model. Use when the user wants to see
-  costs, token counts, or request volume for a given date range.
+description: "Query spend and token activity on a live LiteLLM proxy. Shows daily usage broken down by user, team, org, or model. Use when the user wants to see costs, token counts, or request volume for a given date range."
 license: MIT
 compatibility: Requires curl and python3.
 metadata:
@@ -111,11 +108,19 @@ print(f'{'TOTAL':<12} {'':>10} {'':>12} \${total_spend:>9.4f}')
 "
 ```
 
+## Error handling
+
+Before processing results, check the HTTP status:
+- **401/403** — invalid or expired `LITELLM_API_KEY`; ask the user to verify
+- **404** — endpoint not available; check LiteLLM proxy version supports activity endpoints
+- **Empty results** — no activity in the given date range; confirm dates are correct
+
 ## Instructions
 
 1. Ask for date range — default to current month.
 2. Run the appropriate endpoint.
-3. Print a table: Date | Requests | Tokens | Spend.
-4. Show totals row at the bottom.
-5. Highlight any days with `failed_requests > 0`.
-6. If `metadata.total_pages > 1`, offer to fetch remaining pages.
+3. Validate the response (check for errors before parsing).
+4. Print a table: Date | Requests | Tokens | Spend.
+5. Show totals row at the bottom.
+6. Highlight any days with `failed_requests > 0`.
+7. If `metadata.total_pages > 1`, offer to fetch remaining pages.