Temps Plugin

Organization

gotempsh

temps-plugin

Design, build, test, and distribute external Temps plugins with TypeScript/Bun; provide development and local-testing guidance for existing Rust plugins. Use for creating a plugin, adding an embedded console UI or deployment-event automation, testing host permissions and AI, installing from GitHub, or submitting a plugin to the public catalog. End-to-end publishing covers TypeScript GitHub-source plugins, not Rust native-package releases or in-process TempsPlugin backend crates.

Overview

Publisher	gotempsh
Repository	`temps`
Skill name	`temps-plugin`
Stars	836
Forks	68
Bundled files	3
License	Apache-2.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
3 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by gotempsh on GitHub. Read the source before you install it.

Installation

Install the Temps Plugin AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/gotempsh/temps/tree/main/skills/temps-plugin
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/gotempsh/temps.git /tmp/temps
mkdir -p .claude/skills
cp -r /tmp/temps/skills/temps-plugin .claude/skills/temps-plugin

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Temps Plugin in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Temps Plugin on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Temps Plugin is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Create and ship a Temps plugin

For TypeScript/Bun, deliver a working external plugin, an installable source repository, and evidence of what was verified. Continue an existing project when provided; preserve its identity, storage, and user changes. Publishing is a separate outcome from building or installing.

Rust support here is limited to development and local simulator testing. Rust distribution requires the separate signed native npm-package/catalog pipeline, which this skill does not teach. Do not route a Cargo repository through the TypeScript GitHub installer or suggest copying/symlinking a binary into the host plugin directory. If Rust publication is requested, establish the supported native release procedure before claiming an end-to-end plan; do not silently change the user's implementation language.

1. Establish the contract

Record the plugin's purpose, intended user, entry point in Temps, input/output, persisted data, required host permissions, resource limits, and supported host/SDK versions. Resolve only missing decisions that affect the implementation. Prefer TypeScript + Bun for a new GitHub-installable plugin; retain Rust for existing Rust plugins or an explicit choice.

Read applicable repository instructions. Inspect the installed CLI's plugin --help and the SDK's exports instead of assuming commands from another release exist. The canonical TypeScript starter is gotempsh/temps-plugin-template. Use its current README, manifest, lockfile, and CI. The template may evolve ahead of the npm CLI; lack of a CLI command is not a reason to invent one.

Current evidence sources in a Temps checkout:

apps/temps-cli/src/commands/plugin/: init, build, install, update, grants and dev simulator.
crates/temps-external-plugins/src/repository.rs: actual source-installer build contract.
crates/temps-core/src/external_plugin/: protocol, permissions, manifest and events.
sdks/node/packages/plugin-sdk/src/ and crates/temps-plugin-sdk/src/: SDK APIs.
Root DESIGN.md, web/src/components/ui/, and web/src/globals.css: current console design.

Read development.md when scaffolding or changing runtime behavior, design.md for UI work, and publishing.md before preparing a distributable repository.

2. Scaffold an independently buildable project

Use the GitHub template or, when supported by the installed CLI:

sh
bunx --bun @temps-sdk/cli plugin init my-plugin --name @your-scope/my-plugin

This command scaffolds local files; it does not publish. Inspect generated files before continuing. Replace placeholder identity, author, repository, version and description; keep package metadata and runtime manifest consistent. Add only tested platforms. Commit the lockfile. Keep credentials, local databases, logs, auth material, and simulator session files out of Git.

For GitHub installation, select either the repository root or a self-contained plugin subdirectory with --path. Use --ref for a branch, tag, or commit. Verify that a clean checkout compiles through the host installer path: lifecycle scripts and custom UI build commands are not implicitly run. See the publishing reference for the embedded-asset consequence.

3. Build the product

Use the SDK to own the protocol handshake and transport. Keep protocol stdout clean; log diagnostics to stderr. Use verified caller context for authorization, typed errors, and plugin-owned storage in its assigned data directory. Host data and host-brokered AI come through the SDK, never database/provider credentials copied from the host.

Declare the minimum host permissions and handle absent configuration and revoked grants visibly. Manifest declarations request permissions; administrators grant them. Permissions protect host APIs: native plugins still run with the host OS account's permissions. Do not describe the installed plugin as sandboxed.

Register discoverable navigation for a UI plugin. Use the selected Temps design standard, embed assets, and test its real proxy path. For deployment automation, subscribe to deployment.succeeded, keep receipt handling quick, and use bounded persistent jobs, idempotency, cancellation and explicit environment/project settings.

4. Verify the TypeScript lifecycle at three levels

Unit and integration checks: success, validation, failures, persistence/restart, bounded work, and relevant security cases. Typecheck and compile the actual binary.
Local plugin simulator: real binary + SDK protocol + mock host. Exercise sidebar UI, event delivery, duplicates, denied/granted/revoked permissions, and role restrictions.
Installed Temps instance: install a reviewed repository revision, open the plugin through Temps, trigger the intended user workflow, change permissions, and update the same source. Verify persistence and relevant actor/audit attribution where supported.

Read development.md for simulator commands. A standalone unauthenticated UI preview proves layout only. Simulator/mock AI results are not real provider calls or a full host installation. A received event is not proof the job finished. Do not label end-to-end verification complete unless the installed workflow was exercised; record a concrete limitation when that environment is unavailable.

5. Distribute, list, and maintain TypeScript plugins

The default workflow is GitHub repository → reviewed source installation → catalog PR. No npm publication, cloud publisher token, or registry signing key is needed for this path. Read publishing.md for exact metadata and installation examples. plugin publish is a separate native npm/signed-catalog flow, not shorthand for listing a GitHub repository; use it only when that distribution channel is explicitly requested.

Prepare and validate all artifacts before an external publication step. Respect the user's existing authorization: creating a skill or building a plugin does not itself request public npm publication, a release tag, or installation into production. When publication is requested, show the concrete repository/version/permissions and execute only that scope. Never ask users to paste credentials into chat.

Finish with source location, preview/install instructions, declared permissions, verification evidence, distribution/catalog state and remaining limitations. For updates, retain the stable identity, version deliberately, migrate storage safely, and test a same-source upgrade. Pushing a commit does not automatically update installed plugins.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Temps Plugin AI skill do?

Why use Temps Plugin on TypingMind?

Because you install it once and use it with any model. Temps Plugin is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Temps Plugin in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/gotempsh/temps/tree/main/skills/temps-plugin. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Temps Plugin?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Temps Plugin?

As many as you like. As long as a model supports skills, you can use Temps Plugin with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Temps Plugin AI skill free?

Yes. It is published on GitHub by gotempsh under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Release Openclaw Maintainer

openclaw

OrganizationPopular

Prepare, publish, recover, or verify OpenClaw beta, stable, and extended-stable releases, including approved backports.

Release Openclaw Plugin Testing

openclaw

OrganizationPopular

Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E,…

Solid

Write, port, review, or test Solid 2 UI in OpenClaw (Control UI, plugin views, Canvas hosts), including state ownership, Lit interop during the migration, native overlays, testing, performance, and…

Auto Qa

Run OpenClaw-wide autonomous QA and live/stress campaigns across independent subsystem lanes, with verified fixes and a resumable evidence report.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Create and ship a Temps plugin

1. Establish the contract

2. Scaffold an independently buildable project

3. Build the product

4. Verify the TypeScript lifecycle at three levels

5. Distribute, list, and maintain TypeScript plugins

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now