agentsclimarketplace

Simplified cli

Skill celeryhq/simplified-ai/skills/simplified-cli

Entry point for the Simplified CLI (`smp MODULE COMMAND`) — covers Project Manager, Media (image/video AI), Assets API (brand kits, projects, assets), Social Media, and the MCP server (`smp serve`). Trigger on any request to use the `smp` CLI, manage Simplified PM boards/tasks, generate or process images/videos, manage brand kits or assets, schedule social media posts, or expose Simplified as MCP tools to Claude Desktop / Cursor / Cline.From its SKILL.md

Install
npx -y skills add celeryhq/simplified-ai --skill simplified-cli

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • reads credentialsReads from 3 credential sources: `SMP_TOKEN` and 2 more.
  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
  • runs commandsInstructs the agent to run 8 commands, including `pipx install simplified-apikit` and 7 more.

SKILL.md

5.7 KB, ~1.3k tokens by cl100k_base, as published. Nobody here has run it

Simplified CLI (smp) — Module Index

smp is the unified CLI for the Simplified API, distributed as the simplified-apikit pip/pipx package. It exposes 4 functional modules plus an MCP server, all auto-generated from OpenAPI specs.

Installation

pipx install simplified-apikit \
  --index-url "https://gitlab.com/api/v4/projects/70495826/packages/pypi/simple" \
  --pip-args="--extra-index-url https://pypi.org/simple"

Authentication

Auth is read from environment variables — set once, use everywhere:

export SMP_TOKEN=your_api_token             # API key (sQL00kSs.xxx) or DRF token
export SMP_WORKSPACE=270                    # required for DRF tokens; inferred for API keys
export SMP_SPACE=42                         # optional, for space-scoped resources
export SMP_URL=https://api.simplified.com   # default; omit for prod

Or pass per-call: smp --token xxx --workspace 270 pm list-boards

Command Syntax

Subcommands use space separation: smp pm list-boards. The legacy colon form (smp pm:list-boards) also works for back-compat.

Modules

The CLI is organised by module. Pick the right one for the task:

smp pm — Project Manager

Boards, statuses, tasks, subtasks, assignees, tags, dependencies, comments, activity. The most stateful module — has a memory-cache discipline for board/status/user IDs.

→ See references/pm.md for full guide.

smp pm list-boards
smp pm create-task --status <uuid> --title "Fix login" --assignees '[196]'
smp pm search-tasks --board <id> --status <id> --search "login"
smp pm add-task-dependency --task-id <a> --target-task-id <b> --relation-type BLOCKS

smp media — Image & Video AI Tools

Background removal, upscaling, generative fill, outpainting, inpainting, format conversion, video merging, B-roll, text/script to video. Mostly async — middleware auto-polls for results.

→ See references/media.md for full guide.

smp media remove-background --image-url "https://..."
smp media upscale-image --image-url "https://..." --scale 4
smp media merge-videos --video-urls '["https://a.mp4","https://b.mp4"]'
smp media text-to-video --payload '{"title":"Sunset timelapse","tone":"calm"}'

smp api — Assets API

Workspaces, brand kits (V2), projects and project items, AI image generation, assets, context documents, brand books, agents.

→ See references/api.md for full guide.

smp api get-workspace
smp api list-brand-kits
smp api generate-image --prompt "sunset over mountains"
smp api create-project --primary-type ASSET --title "Q1 launch"

smp social — Social Media

Connected accounts, posts (publish/draft/schedule), tags, and analytics (range, posts, aggregated, audience).

→ See references/social.md for full guide.

smp social get-social-media-accounts
smp social create-social-media-post --payload '{"caption":"Hello","accounts":[...]}'
smp social get-social-media-analytics-aggregated --account-id <id>

smp comments — Comments

Threaded comments on any commentable Simplified resource. Currently supports tasks; will grow to other types. Generic by design — addressed by content_type + object_pk rather than a resource-specific shortcut.

→ See references/comments.md for full guide.

smp comments list-comments --content-type task --object-pk <task_uuid>
smp comments add-comment --content-type task --object-pk <task_uuid> --comment "LGTM"

smp serve — MCP Server

Exposes every module command above as an MCP tool. Use from Claude Desktop, Cursor, Cline, or any MCP host.

smp serve                              # stdio (default — for Claude Desktop/Cursor)
smp serve --transport http --port 9000 # HTTP transport

The middleware handles pre/post hooks (e.g. inline assignees on pm create-task, auto Quill-Delta description conversion), response normalization, and async task polling — so MCP clients get the same ergonomic interface as the CLI.

Discovering Commands

Don't rely on a static table. The CLI is auto-generated from OpenAPI specs and --help is always current:

smp --help                          # list modules
smp pm --help                       # list pm commands
smp pm create-task --help           # full options for a single command

Output

By default smp pretty-prints JSON. Pass --raw for unformatted output (useful when piping into jq / python3 -c):

smp --raw pm list-boards | jq '.results[].id'

Cross-cutting Patterns

Async tasks. Several endpoints (media/*, api generate-image, some video ops) return a task_id. The middleware polls GET /api/v1/tasks/{task_id} automatically and returns the final result. Default polling is ~3.75 min — video generation may need longer. If it times out you'll get the task_id to poll manually.

Composite fields. pm create-task / pm update-task accept assignees and tags inline; the toolkit makes follow-up sub-resource calls automatically.

JSON args. Array/object options need single quotes around JSON: --assignees '[196, 200]', --payload '{"title":"..."}'.

Pagination. List endpoints default to page_size=10. Add --page-size 100 to get more.

What ships with it: 5 files

23.3 KB alongside SKILL.md

references/

Gives 0 of the 12 instructions most mcp tooling skills give in ~1.3k tokens

Counted across 780 of the 1,136 authors here whose files we hold, read 2026-09-06

  • Use Zod for input validationin 34 of 780, across 21 files
  • Use stdio for local clientsin 27 of 780, across 10 files
  • Restart Claude Code after configurationin 26 of 780, across 23 files
  • Verify MCP server connection before using toolsin 23 of 780, across 17 files
  • Define input schemas for every toolin 20 of 780, across 11 files
  • Use Streamable HTTP for remote clientsin 18 of 780, across 8 files
  • Pin SDK version in package.jsonin 17 of 780, across 6 files
  • Keep server logic independent of transportin 16 of 780, across 6 files
  • Verify SDK methods against official documentationin 15 of 780, across 5 files
  • Format evaluation results as an XML filein 15 of 780, across 12 files
  • Test servers using the MCP Inspectorin 15 of 780, across 14 files
  • Create ten complex and independent evaluation questionsin 14 of 780, across 11 files

Said here and by no other author read

  • Install simplified-apikit using pipx
  • Set SMP_TOKEN and SMP_WORKSPACE environment variables
  • Use space separation for subcommands
  • Pass --raw for unformatted JSON output
  • Use single quotes for JSON array or object arguments
  • Use --page-size to adjust pagination

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 611,919. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.