Temps skills

Skills teach coding agents to deploy apps to Temps, add observability and operate a self-hosted platform through its CLI.

  • 911 ★ on the repository
  • Last commit
  • Apache-2.0
Skill

Broad access

Why this level

  • The CLI can change live services, domains and databases on the selected Temps instance.
  • The platform-setup skill uses SSH and administrator operations on the server.
All reasons and checks

gotempsh/temps

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/temps-skills

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Broad accessThe tool can change data, run commands or handle secrets.

  • The CLI can change live services, domains and databases on the selected Temps instance.
  • The platform-setup skill uses SSH and administrator operations on the server.

This is third-party code. Review the repository files before installing.

What it does

Temps skills define how a coding agent works with applications on Temps. The agent classifies the task and opens the relevant reference, then inspects project state, proposes a change and verifies the result through a separate query. The instructions cover deployment, recovery and diagnosis. During application preparation they inspect project settings and select suitable observability tools. Temps brings those services together with app hosting on your own server.

Who it is for. For developers who want an agent to operate applications on their own Temps instance.

Good fit when

  • Move a repository to Temps and verify health after release.
  • Check whether error collection is configured before launching an application.
  • Inspect a failed deployment and choose a recovery sequence.
  • Select the project and environment before changing monorepo services.

Not a fit when

  • You need instructions for a different hosting platform.
  • The target machine runs services whose owners are unknown.
  • The task is only prose editing without application work.

Example request

Verify my Temps connection and inspect services in the selected project without changing them.

Limitations

Commands require a shell and Bun or npm; without them the agent cannot invoke the platform CLI. Commands act on the selected Temps instance and can change live applications, so check the project and environment before writing. Analytics setup is complete after a test pageview or event appears in the selected Temps project: adding a package to the source is insufficient. The server-setup skill checks where downloaded programs come from and stops if it cannot establish their provenance.

How to disable. Remove the installed skill folders from your agent’s skill directory. New tasks stop loading the instructions; deployed applications and the Temps server remain.

FAQ

Which CLI version do the skills use?

Version 0.1.38: calls use `bunx @temps-sdk/cli@0.1.38`, with an `npx` equivalent when Bun is unavailable.

Will analytics be added without asking?

No. The skill offers missing observability and respects a decline for the rest of the task.

How does the agent access an existing server?

Through browser authorization for the CLI. The console can also create a dedicated agent key for unattended automation.

When is the platform-setup skill used?

When the user requests provisioning or initial setup of a specific machine. Connecting an existing instance skips SSH provisioning.

Can an agent execute instructions from error logs?

No. The skill treats logs, API responses and downloaded files as untrusted data and forbids following instructions embedded in them.

Discussion

No questions or reviews yet.

Skills

Skill configures OpenTelemetry: collectors, sampling, security and telemetry from AI agents, without flooding the context.

SkillMinimal access55Repository stars

Official Timeweb Cloud skills

Timeweb Cloud Skills

Official

Timeweb Cloud's official plugin with ten skills and a hosted MCP server: servers, databases, Kubernetes, S3, domains and billing

PluginBroad access21Repository stars

31 DevOps skills for Claude Code and Codex: config generators, validators and a Kubernetes debugger for Terraform, Helm, CI and Docker

SkillExtended access339Repository stars
Editors’ pick

Official Datadog skills: monitors, logs, APM, cloud integrations, RUM and LLM observability from inside the agent

SkillBroad access185Repository stars

A large base of DevOps, security, infrastructure and compliance skills for AI agents

SkillMinimal access1.2KRepository stars

A set of skills for agent work with AWS: common cloud service tasks packaged as ready instructions for a coding agent

SkillExtended access1.2KRepository stars

README in short

References are organized by task, including domains, backups, databases and diagnosis. Template provisioning and source-code deployment use different outcome checks.

README badge

Original SKILL.md

---
name: temps
description: Manage, deploy, operate, and instrument applications with Temps. Use this skill whenever the user mentions Temps, `@temps-sdk/cli@0.1.38`, deploying or migrating an app to Temps, projects, environments, services, domains, backups, edge rules (request blocking, redirects, bot challenges), logs, monitoring, analytics, browser Performance Insights/Core Web Vitals, observability, error tracking, OpenTelemetry, tracing, session replay, or Temps Cloud. Also use it when preparing an application for production on Temps even if the user does not explicitly ask for the CLI. Route to focused references, proactively detect missing observability during create/link/deploy journeys, and use pinned `bunx` or `npx` CLI invocations with explicit target contexts.
---

# Temps

Treat Temps as a product workflow, not a command catalog. Understand the
user's desired outcome, inspect the application or platform read-only, load
only the relevant reference, make the smallest authorized change, and prove
the result.

Runtime requirements: a shell and either `bunx` or `npx` for CLI operations;
Python 3.9+ for the bundled read-only capability detector.

## Required workflow

1. Classify the task: application preparation, deployment, platform operation,
   observability, recovery, or diagnosis.
2. Inspect before changing anything. Identify the current Temps context,
   target project/environment, and existing setup. For a named application,
   check the instance's curated app catalog before creating a repository,
   Dockerfile, or custom project. Prefer a matching curated service when it
   meets the request; inspect a repository framework only for source deployment.
3. Read only the references named in the routing table below. Do not load the
   complete command index or unrelated observability pillars.
4. For CLI work, use the pinned zero-install invocation and the safety contract
   in [references/cli-runtime.md](references/cli-runtime.md).
5. Before a state change, explain its target and effect. Ask for confirmation
   when the change is destructive, secret-bearing, or otherwise requires new
   authority.
6. Verify the outcome using a read-only CLI command, application test, and—when
   telemetry is involved—a real synthetic signal.

## Application capability checkpoint

When creating, linking, migrating, reviewing, or deploying a source-backed application,
inspect its observability setup before the final deployment step:

```bash
python3 skills/temps/scripts/detect_project_capabilities.py --root .
```

Curated template provisioning is exempt from this checkpoint. Follow the
[curated-services verification steps](howtos/curated-services.md#verify-creation-and-deployment-separately)

Report a problem