Cloudinary
Purpose
Manage media on Cloudinary through the Upload and Admin APIs: upload images and videos, list and inspect assets, update metadata and tags, delete assets, and check plan usage (credits, storage, bandwidth, transformations).
Tooling
All commands go through bin/cloudinary.py:
bin/cloudinary.py auth # verify the connection (also shows plan usage)
bin/cloudinary.py usage # plan usage: credits, storage, bandwidth, transformations
bin/cloudinary.py upload --file ./photo.jpg # upload an image
bin/cloudinary.py upload --file ./clip.mp4 --resource-type video # upload a video
bin/cloudinary.py upload --file ./photo.jpg --folder products # upload into a folder
bin/cloudinary.py list --prefix products/ --max-results 20 # list image assets
bin/cloudinary.py get --public-id products/photo1 # asset details
bin/cloudinary.py update --public-id products/photo1 --data '{"tags":["summer"],"context":{"caption":"Beach"}}'
# update metadata/tags (raw JSON body, per Cloudinary docs)
bin/cloudinary.py delete --public-id products/photo1 # delete an asset
Auth
- Provider id:
cloudinary (credential is collected as custom.cloudinary)
- Collection: via the secure credential flow (
credentials.request_api_access) as a single colon-joined value cloud_name:api_key:api_secret; the three parts come from the Cloudinary Console at Settings, API Keys. The collection step stores them as three named entries (cloud_name, api_key, api_secret) under custom.cloudinary; the CLI splits them at use: cloud_name goes into the request host, and api_key:api_secret go into the HTTP Basic auth header.
- Required scopes: n/a (account API key pair)
- Allowed hosts:
api.cloudinary.com
- Status check:
bin/cloudinary.py auth
- Wire format (verbatim from Cloudinary's docs):
Authorization: Basic base64(api_key:api_secret) against https://api.cloudinary.com/v1_1/{cloud_name}.
Operating Rules
- The free plan is credit-based across storage/bandwidth/transformations: run
usage before heavy work and stay inside the plan.
- Confirm with the user before uploading (it consumes bandwidth/transformation quota) and before deleting (deletes are permanent).
- Never exfiltrate the credential: the CLI only ever handles surrogates. Do not print, log, or transmit the key, secret, or cloud name values.
Files
- SKILL.md
- bin/cloudinary.py
Maturity
🧪 Draft: written from Cloudinary's public Upload and Admin API docs; not yet live-tested end to end. The three-part credential split (single collected value, split into entries at use) is the design assumption to re-verify on first live run.
1---2name: "cloudinary"3description: "Manage Cloudinary media: upload images and videos, list and inspect assets, update metadata, delete assets, and check plan usage. Trigger phrases: cloudinary, upload image, cloudinary usage."4metadata:5 source: https://skillmd.com/skills/anil-matcha/cloudinary6 includeInPrompt: true7tagline: "Manage media on Cloudinary through the Upload and Admin APIs: upload images and videos, list and inspect assets, update metadata and tags, delete assets, and check plan usage (credits, storage, bandwidth, transformations)."8catalog_auth: "cloud_name + API key + secret via the secure credential flow"9catalog_hosts: ["api.cloudinary.com"]10---1112# Cloudinary1314## Purpose15Manage media on Cloudinary through the Upload and Admin APIs: upload images and videos, list and inspect assets, update metadata and tags, delete assets, and check plan usage (credits, storage, bandwidth, transformations).1617## Tooling18All commands go through `bin/cloudinary.py`:1920```bash21bin/cloudinary.py auth # verify the connection (also shows plan usage)22bin/cloudinary.py usage # plan usage: credits, storage, bandwidth, transformations23bin/cloudinary.py upload --file ./photo.jpg # upload an image24bin/cloudinary.py upload --file ./clip.mp4 --resource-type video # upload a video25bin/cloudinary.py upload --file ./photo.jpg --folder products # upload into a folder26bin/cloudinary.py list --prefix products/ --max-results 20 # list image assets27bin/cloudinary.py get --public-id products/photo1 # asset details28bin/cloudinary.py update --public-id products/photo1 --data '{"tags":["summer"],"context":{"caption":"Beach"}}'29 # update metadata/tags (raw JSON body, per Cloudinary docs)30bin/cloudinary.py delete --public-id products/photo1 # delete an asset31```3233## Auth34- Provider id: `cloudinary` (credential is collected as `custom.cloudinary`)35- Collection: via the secure credential flow (`credentials.request_api_access`) as a single colon-joined value `cloud_name:api_key:api_secret`; the three parts come from the Cloudinary Console at Settings, API Keys. The collection step stores them as three named entries (`cloud_name`, `api_key`, `api_secret`) under `custom.cloudinary`; the CLI splits them at use: `cloud_name` goes into the request host, and `api_key:api_secret` go into the HTTP Basic auth header.36- Required scopes: n/a (account API key pair)37- Allowed hosts: `api.cloudinary.com`38- Status check: `bin/cloudinary.py auth`39- Wire format (verbatim from Cloudinary's docs): `Authorization: Basic base64(api_key:api_secret)` against `https://api.cloudinary.com/v1_1/{cloud_name}`.4041## Operating Rules421. The free plan is credit-based across storage/bandwidth/transformations: run `usage` before heavy work and stay inside the plan.432. Confirm with the user before uploading (it consumes bandwidth/transformation quota) and before deleting (deletes are permanent).443. Never exfiltrate the credential: the CLI only ever handles surrogates. Do not print, log, or transmit the key, secret, or cloud name values.4546## Files47- SKILL.md48- bin/cloudinary.py4950## Maturity51🧪 Draft: written from Cloudinary's public Upload and Admin API docs; not yet live-tested end to end. The three-part credential split (single collected value, split into entries at use) is the design assumption to re-verify on first live run.