By Qencode-Corp
Skills for the Qencode Transcoding API — let agents compose, submit, monitor, and troubleshoot encoding jobs. v1 covers transcoding only; CDN/streaming/player coming later.
Use when the user asks what a Qencode Transcoding API attribute means, what values it accepts, where it lives in the query structure, what its default is, or whether it's required. Examples — "what does `resize_mode` do?", "is `keyframe` required?", "what values does `output` accept?", "where do I put `framerate` for HLS?", "what's the difference between `width` and `resolution`?". Reads the generated schema index/digest and applies the project's composition defaults.
Use when the user asks to transcode, encode, convert, re-encode, or process a video — or to produce HLS, DASH, MP4, MP3, thumbnails, or any other Qencode output. Composes a validated `query` JSON payload for `POST /v1/start_encode2`. Pure composition; does not submit the job. Hand the JSON to `qencode-transcode` (or paste into the user's own tooling) to actually run it.
Use when the user wants to check, poll, or wait for a Qencode transcoding job — phrases like "check the status of token X", "is the job done?", "wait for the encode to finish", "poll until ready", "what's the progress?". Queries `POST /v1/status` (or the equivalent MCP tool) once or in a loop until terminal. Summarizes percent done, output URLs, errors, and warnings.
Use when the user wants to actually run a Qencode transcoding job — phrases like "submit", "start the job", "run this", "transcode it now", "encode and post the status", or any time the user has a video URL and wants encoded output back. Submits a `query` JSON to `POST /v1/start_encode2` via the qencode MCP server when present, falling back to raw HTTP. Returns the task_token and status_url. For status polling, hand off to `qencode-job-status` afterwards.
Use when a Qencode transcoding job or API call has failed and the user wants help understanding why. Triggers — "what does error N mean?", "my job failed", "why is this error happening?", "Qencode returned error 19", "the status shows error_description X", or any time the user pastes a non-zero `error` code or a `failed`/`error` status payload. Maps the error to its likely cause, suggests concrete fixes, and (when relevant) inspects the original query JSON for misconfigurations.
External network access
Connects to servers outside your machine
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code plugin that gives agents the knowledge and recipes to use the Qencode Transcoding API end-to-end: compose a query JSON, submit a job, poll for status, and troubleshoot failures.
v1 scope: transcoding API only. CDN, streaming, and player APIs are deferred.
| Skill | Status | When it runs |
|---|---|---|
qencode-build-query | ✅ shipped | The user asks to transcode/encode/convert a video. Composes a validated query JSON without submitting. |
qencode-api-reference | ✅ shipped | The user asks what an attribute means or what values it accepts. |
qencode-transcode | ✅ shipped | End-to-end job submission. Uses MCP if connected; falls back to raw HTTP. |
qencode-job-status | ✅ shipped | Poll or wait for a running job. |
qencode-troubleshoot | ✅ shipped | Map a Qencode error code (or failed-job error_description) to a likely cause and fix. |
The skills read from a shared knowledge base under assets/:
| File | Purpose |
|---|---|
assets/schema-digest.md | Generated digest of every endpoint and query attribute |
assets/schema-index.json | Path-keyed index for fast attribute lookup |
assets/best-practices.md | Composition defaults (encoder v2, libfdk_aac, CRF + per-title, ABR stream-level params, …) |
assets/storage.md | Output destinations — supported prefixes, per-provider param compatibility, fan-out, cache headers |
assets/gotchas.md | Non-obvious operational quirks (query double-wrap, status_url, retries, …) |
assets/error-codes.md | Error code → cause → fix table |
assets/recipes/*.md | Named recipes (HLS ABR, MP4 ladder, thumbnails, …) |
This repo is a self-hosted Claude Code marketplace. Two commands in any Claude Code session:
/plugin marketplace add Qencode-Corp/qencode-skills
/plugin install qencode-skills@qencode
The first registers this repo as a marketplace named qencode. The second installs the qencode-skills plugin from it.
On install, Claude Code will also prompt you to approve adding the qencode MCP server pointing at https://mcp-qa.qencode.com/mcp. On first tool use the browser opens for the OAuth handshake (no API key in client config — see .mcp.json).
/plugin update qencode-skills@qencode
Or /plugin marketplace update qencode to pull the latest entries.
/plugin uninstall qencode-skills@qencode
/plugin marketplace remove qencode
When iterating on the plugin itself, point Claude Code at your working copy instead of GitHub:
/plugin marketplace add /path/to/qencode-skills
/plugin install qencode-skills@qencode
The MCP server installed with the plugin uses OAuth — there's nothing to configure in this plugin's settings. On first tool use, your browser opens auth-qa.qencode.com for consent and the token is persisted locally by Claude Code.
The qencode-transcode and qencode-job-status skills can also call the public API directly via scripts/http_fallback.py when no MCP is connected. The fallback uses a project API key:
export QENCODE_API_KEY=... # from https://portal.qencode.com/project/my_projects
MCP is preferred — it handles OAuth, session-token caching, and retries on transient disconnects. Use the fallback only if you can't run MCP in your environment.
The skills read a digest generated from the canonical schema in the docs repo. Regenerate after any schema change:
# point the script at your docs checkout
export QENCODE_DOCS_PATH=~/projects/qencode/docs_getsby5
python plugins/qencode-skills/scripts/build_assets.py
# or pass the path explicitly:
python plugins/qencode-skills/scripts/build_assets.py --docs-path ~/projects/qencode/docs_getsby5
The script reads <docs>/src/data/api/transcoding.json and writes assets/schema-digest.md and assets/schema-index.json. Commit the regenerated assets.
npx claudepluginhub qencode-corp/qencode-skills --plugin qencode-skillsComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review