simplified-cli
Skill4 starsChanged 4 months agoMITView on GitHub
Use when the user explicitly wants the smp command line, shell scripts, JSON pipelines, local Simplified API automation, or a local smp serve MCP server. For conversational tasks through a hosted connector, use the relevant platform skill instead.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- celeryhq/simplified-clitheir own version, first seen Jul 22, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- celeryhq/simplified-cli★ 9same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- campaign-reviewSkill
- content-repurposerSkill
- creative-testingSkill
- cross-platform-campaignSkill
- edit-imageSkill
- evergreen-content-engineSkill
- generate-imageSkill
- generate-videoSkill
- generate-voiceoverSkill
- local-business-marketingSkill
- manage-assetsSkill
- manage-brandSkill
- manage-projectsSkill
- repurpose-videoSkill
- simplified-agentsSkill
- simplified-project-managementSkill
- simplified-socialSkill
- simplified-workflowsSkill
- simplified-workspaceSkill
- social-content-plannerSkill
- social-performance-analystSkill
- transcribe-mediaSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Use your team's supported package source to install simplified-apikit.
- Very specific: line 30
Use the same resolved scope throughout.
- Very specific: line 47
Read the target state, resolve IDs, then execute the user-authorized operation.
- Very specific: line 51
Default output is formatted JSON.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Simplified CLI
smp is supplied by the Python simplified-apikit package. It generates commands from the same OpenAPI specs and runs them through MCP middleware, so request validation and hooks apply across CLI and connector calls. It is different from the npm simplified CLI; do not mix their commands or credentials.
Setup and scope
Use your team's supported package source to install simplified-apikit. Confirm smp --version and command help before scripting. Local CLI calls require configured credentials; hosted app OAuth does not automatically populate local CLI environment variables.
smp --version
smp --help
smp api --helpSet SMP_TOKEN privately in the environment. API keys use their bound workspace; DRF tokens also require numeric SMP_WORKSPACE. Set numeric SMP_SPACE only after resolving the user's chosen teamspace. Omit SMP_URL for production; use overrides only for an explicitly selected environment. Never print credentials or put them into user-facing commands/logs.
Root options such as --space, --workspace, and --raw precede the namespace. Both smp api list-assets and smp api:list-assets work. JSON options take a single shell-quoted JSON value.
smp --raw api:list-assets --search car --asset-type 0 --page 1
smp api:get-workspace-info
smp api:list-teamspacesUse the same resolved scope throughout. Do not guess tenant IDs or select the first board/account/member just to make a script run.
Choose the namespace
| Namespace | Use | Reference |
api | Workspace, brand context, assets, AI generation, marketing projects, comments | API |
pm | Boards, statuses, tasks, dependencies, assignments | PM |
social | Accounts, drafts, scheduling, reviews, analytics | Social |
media | Image/video editing and transcription | Media |
flows, agents | Workflow and agent automation | Current namespace help and the matching automation skill |
notify | Requested notifications | Current command help |
Comments are smp api:list-comments / smp api:add-comment, not a separate comments namespace. See comments.
Execute and verify
Read the target state, resolve IDs, then execute the user-authorized operation. Use --help for the exact required flags. Keep returned IDs for follow-up; verify writes using direct reads. For partial batches, report successful IDs and failed steps without repeating successful creates.
Current image/video generation waits for completion. Pending/timeout responses require continuation using the actual job identifiers, not a duplicate paid request. Video submission task IDs do not establish render completion. Other tools may have different task-result contracts.
Default output is formatted JSON; root --raw makes it suitable for JSON parsers. Read the actual envelope before writing a jq/path expression. Pagination limits and defaults vary by endpoint; retain filters/scope and follow returned pagination metadata.
Generation consumes credits and social scheduling/queueing can publish content. Preserve explicit authorization already given for the concrete operation. Planning is not permission to run it.
Local MCP server
smp serve
smp serve --profile public
smp serve --transport http --port 9000 --profile socialfull is the default local profile. Hosted connector tools/profile are deployed separately; local full access does not prove a hosted client has the same tools. flows, agents, and the generic passthrough require an automation/full surface. See client setup.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.