Skills for Real Engineers. Straight from my .agents directory.
descript
Agent skill fromAnil-matcha/awesome-muse-connectors
Work with Descript projects and async Underlord/agent jobs: list projects, submit publish jobs, poll job status. Trigger phrases: descript, video editing, publish video, descript project.
How to install descript
npx skills add Anil-matcha/awesome-muse-connectors# or add only this skill to Claude Code: copy the folder
connectors/descript/
# into
~/.claude/skills/descript/ (all projects)
.claude/skills/descript/ (one project)
1# Descript23## Purpose4Work with Descript's API (open beta): list projects, inspect Underlord/agent jobs, submit a publish job, and poll a job until it finishes. Use when the user wants to drive Descript editing or publishing programmatically.56## Tooling7All commands go through `bin/descript.py`:89```bash10bin/descript.py auth # verify the API key11bin/descript.py projects # list projects12bin/descript.py project --id PROJECT_ID # get one project13bin/descript.py jobs # list Underlord/agent jobs14bin/descript.py job-status --id JOB_ID # get job status once15bin/descript.py job-status --id JOB_ID --wait # poll until job_state is "stopped"16bin/descript.py publish --project-id PROJECT_ID # submit a publish job (confirm first)17bin/descript.py job-delete --id JOB_ID # delete a job (confirm first)18```1920Jobs are async: submit with `publish`, then poll with `job-status --wait` until `job_state` is `stopped`, then check `status` for success/partial/error. The publish body schema follows Descript's API docs; pass `--body` as raw JSON if the default empty body is not enough for your case.2122Auth quirks handled by the CLI: the header name is sent lowercase (`authorization: Bearer <key>`, because a capitalized `Authorization` returns 401) and the key value, which contains a colon, is used whole and never split.2324## Auth25…
Excerpt shown under the repository's MIT license.
More skills in awesome-muse-connectors
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
