Add ai-status-monitor skill

.claude-plugin/marketplace.json

@@ -80,6 +80,13 @@
       "source": "./skills/hugging-face-vision-trainer",
       "skills": "./",
       "description": "Train and fine-tune object detection models (RTDETRv2, YOLOS, DETR and others) and image classification models (timm and transformers models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3) using Transformers Trainer API on Hugging Face Jobs infrastructure or locally. Includes COCO dataset format support, Albumentations augmentation, mAP/mAR metrics, trackio tracking, hardware selection, and Hub persistence."
+    },
+
+    {
+      "name": "ai-status-monitor",
+      "source": "./skills/ai-status-monitor",
+      "skills": "./",
+      "description": "Monitor real-time AI provider status, model availability, pricing, trending usage, benchmark rankings, and incidents from aistatus.cc."
     }
   ]
 }

README.md

@@ -89,6 +89,7 @@ This repository contains a few skills to get you started. You can also contribut
 <!-- BEGIN_SKILLS_TABLE -->
 | Name | Description | Documentation |
 |------|-------------|---------------|
+| `ai-status-monitor` | Monitor real-time AI provider status, model availability, pricing, trending usage, benchmark rankings, and incidents from aistatus.cc. | [SKILL.md](skills/ai-status-monitor/SKILL.md) |
 | `gradio` | Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots. | [SKILL.md](skills/huggingface-gradio/SKILL.md) |
 | `hf-cli` | Execute Hugging Face Hub operations using the hf CLI. Download models/datasets, upload files, manage repos, and run cloud compute jobs. | [SKILL.md](skills/hf-cli/SKILL.md) |
 | `hugging-face-dataset-viewer` | Explore, query, and extract data from any Hugging Face dataset using the Dataset Viewer REST API and npx tooling. Zero Python dependencies — covers split/config discovery, row pagination, text search, filtering, SQL via parquetlens, and dataset upload via CLI. | [SKILL.md](skills/hugging-face-dataset-viewer/SKILL.md) |

agents/AGENTS.md

@@ -3,6 +3,7 @@
 You have additional SKILLs documented in directories containing a "SKILL.md" file.
 
 These skills are:
+ - ai-status-monitor -> "skills/ai-status-monitor/SKILL.md"
  - gradio -> "skills/huggingface-gradio/SKILL.md"
  - hf-cli -> "skills/hf-cli/SKILL.md"
  - hugging-face-dataset-viewer -> "skills/hugging-face-dataset-viewer/SKILL.md"
@@ -20,6 +21,7 @@ IMPORTANT: You MUST read the SKILL.md file whenever the description of the skill
 
 <available_skills>
 
+ai-status-monitor: `Monitor real-time status for major AI providers, search model availability and pricing, and report trending models, benchmark rankings, and incidents from aistatus.cc. Use when users ask if a provider is down, whether a model is available, or what models are trending/high-performing.`
 gradio: `Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.`
 hf-cli: `"Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub. Replaces now deprecated `huggingface-cli` command."`
 hugging-face-dataset-viewer: `Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.`

skills/ai-status-monitor/SKILL.md

@@ -0,0 +1,61 @@
+---
+name: ai-status-monitor
+description: Monitor real-time status for major AI providers, search model availability and pricing, and report trending models, benchmark rankings, and incidents from aistatus.cc. Use when users ask if a provider is down, whether a model is available, or what models are trending/high-performing.
+---
+
+# AI Status Monitor (aistatus.cc)
+
+Use this skill to query public API endpoints from `https://aistatus.cc`.
+
+## Endpoint map
+
+- `GET /api/all`
+  Returns a full snapshot:
+  - `status`: `{ providerStatus: [...], totalModels }`
+  - `trending`: `{ week, models: [...] }`
+  - `mmlu`: `[ ... ]` (top benchmark models)
+  - `incidents`: `[ ... ]` (recent status transitions)
+  - `lastUpdated`
+
+- `GET /api/status`
+  Returns provider-level status:
+  - `providerStatus[]`: `{ slug, name, modelCount, status, statusDetail, ... }`
+  - `totalModels`
+  - `lastUpdated`
+
+- `GET /api/model?q=<query>`
+  Returns model search results:
+  - `query`, `count`, `models[]`, `lastUpdated`
+  - model entries include `id`, `name`, `provider`, `context_length`, `pricing`, `modality`
+
+- `GET /api/trending`
+  Returns OpenRouter weekly usage ranking:
+  - `week`
+  - `models[]`: `{ rank, id, name, provider, tokens, tokensFormatted, ... }`
+  - `lastUpdated`
+
+- `GET /api/mmlu`
+  Returns benchmark leaderboard:
+  - `models[]`: `{ rank, name, avgScore, mmluPro, mathLvl5, gpqa, params, type }`
+  - `lastUpdated`
+
+- `GET /api/incidents`
+  Returns recent provider status changes:
+  - `incidents[]`: `{ slug, name, from, to, detail, timestamp }`
+
+## Request strategy
+
+1. Default to `GET /api/all` for broad or ambiguous requests.
+2. Use `GET /api/status` for provider uptime/outage questions.
+3. Use `GET /api/model?q=...` for model lookup, context length, or price checks.
+4. Use `GET /api/trending` for popularity/usage ranking questions.
+5. Use `GET /api/mmlu` for benchmark leaderboard questions.
+6. Use `GET /api/incidents` for outage history or recent changes.
+
+## Response rules
+
+- Include the API timestamp field (`lastUpdated` or event `timestamp`) when available.
+- For provider status, report `status`, `statusDetail` (if present), and `modelCount`.
+- For model search, show top matches first and include provider status plus pricing.
+- For rankings, preserve rank order and clearly label the metric (`tokens` or `avgScore`).
+- If the query is vague, return a concise summary from `/api/all` and ask one follow-up question.