Agent skill

Tianji Worker Operations

by msgbyte in msgbyte/tianji

Operates Tianji Workers: create, test, deploy, invoke, schedule, pause and roll back them, plus manage their environment variables and shared modules.

Apache-2.0Auto-check passedBackend & APIs

Install Tianji Worker Operations

skills CLI
$ npx skills add msgbyte/tianji --skill tianji-worker -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install msgbyte/tianji tianji-worker --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/msgbyte/tianji.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tianji-worker .claude/skills/tianji-worker && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
tianji-worker
GitHub stars
3.1k
Token cost
~1.1k tokens
SKILL.md length
446 words
Files
3 (incl. references)
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

Operates Tianji Workers: create, test, deploy, invoke, schedule, pause and roll back them, plus manage their environment variables and shared modules.

  • Works in 5 steps: Identify the requested operation, Tianji… → Fetch and read the target instance's… → Read Common operations for configuration… → …
  • Creating and deploying a new Tianji Worker
  • SKILL.md covers Start here, Choose the supported interface, Runtime essentials and Verify and report
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Before touching a Worker, the agent identifies the operation, Tianji server, workspace and Worker, and never guesses a target. It fetches the target instance's /open/_document OpenAPI description to confirm which operations exist, falls back to a dashboard tRPC reference for operations missing from OpenAPI, and reads a runtime reference before writing code because the Tianji sandbox differs from Node.js, browsers and Cloudflare Workers.

A table maps tasks to interfaces: tianji worker init and pull for local projects, the dashboard or an OpenAPI upsert for deploying, test code or preview for drafts, an HTTP endpoint for invoking public Workers, and the dashboard edit form for cron, Text and Secret variables and module bindings. For an existing Worker it inspects code, state, cron settings and revisions first, preserves unrelated settings, and treats a request for sample code as not authorizing a deployment.

When your agent uses it

  • Creating and deploying a new Tianji Worker
  • Scheduling, pausing or rolling back a deployed Worker
  • Debugging a Worker run through its executions and logs
  • Managing Worker environment variables and shared modules

Example prompts

  • “Create a Tianji Worker that checks our status page every hour and deploy it to the production workspace.”
  • “Pause the nightly cleanup Worker without changing its other settings.”
  • “Roll the report Worker back to its previous revision.”
  • “Pull the compiled code of the daily-digest Worker so I can edit it locally.”

Requirements

  • Access to a Tianji server and workspace
  • The tianji CLI for local Worker projects

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Identify the requested operation, Tianji server, workspace, and existing Worker ID or new Worker name. Use existing configuration where…
  2. Fetch and read the target instance's /open/_document before operating a Worker. Use its OpenAPI document to confirm exported operations…
  3. Read Common operations for configuration preservation and execution rules. Operations absent from OpenAPI require the separately…
  4. Before writing or modifying code, read Runtime reference. Tianji's sandbox differs from Node.js, browsers, and Cloudflare Workers.
  5. For an existing Worker, inspect its current code, active state, cron settings, and revisions before changing it. Preserve unrelated…

What it can do on your machine

Read from SKILL.md and the folder at commit 28243e9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tianji Worker Operations loads about 1.1k tokens when it runs, and up to ~8.6k if it reads all its reference files. Until then it costs about 47 tokens; SKILL.md has 446 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from msgbyte/tianji at commit 28243e9, republished under its Apache-2.0 licence (© msgbyte). 446 words, ~1,093 tokens.

Download SKILL.mdSave it as .claude/skills/tianji-worker/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
tianji-worker
description
Use when creating, testing, deploying, invoking, debugging, scheduling, pausing, or rolling back Tianji Workers, or managing their environment variables and shared modules.

Tianji Worker

Operate Tianji Workers using the dashboard, CLI, and supported management API.

Start here

  1. Identify the requested operation, Tianji server, workspace, and existing Worker ID or new Worker name. Use existing configuration where available; never guess a target.
  2. Fetch and read the target instance's /open/_document before operating a Worker. Use its OpenAPI document to confirm exported operations, HTTP methods, paths, and parameter/body schemas. Follow Connect and inspect for discovery and unavailable-document handling; bundled examples are not the target's API contract.
  3. Read Common operations for configuration preservation and execution rules. Operations absent from OpenAPI require the separately maintained dashboard tRPC reference; never derive an OpenAPI route from a procedure name.
  4. Before writing or modifying code, read Runtime reference. Tianji's sandbox differs from Node.js, browsers, and Cloudflare Workers.
  5. For an existing Worker, inspect its current code, active state, cron settings, and revisions before changing it. Preserve unrelated settings. Carry out the user's authorized scope; a request for sample code alone does not authorize deployment.

Choose the supported interface

TaskInterface
Create a local project; pull compiled codetianji worker init; tianji worker pull
Create or update a deployed WorkerDashboard or OpenAPI upsert; CLI deploy has configuration side effects
Test draft code and payloadsTarget OpenAPI if exported; otherwise dashboard Test Code / preview
Invoke a public WorkerHTTP /api/worker/{workspaceId}/{workerId}
Run a stored Worker manually; inspect logsTarget OpenAPI if exported; otherwise dashboard Executions / run action
Configure cron, Text/Secret variables, module bindingsDashboard edit form; read preservation rules before API updates
Inspect or roll back code revisionsDashboard Revisions or OpenAPI
Pause/resume; deleteOpenAPI or dashboard; deletion requires workspace admin rights

Use OpenAPI only for operations exported by the target. For missing operations, check the maintained dashboard tRPC reference and target version. OpenAPI discovery does not synchronize tRPC, CLI behavior, the public HTTP trigger, or runtime semantics.

Show full SKILL.md (136 more words)Show less

Runtime essentials

js
export default {
  async fetch(payload, context) {
    return { ok: true, trigger: context.type };
  },
};
  • Use context.env for Text/Secret values and request for outbound HTTP. No Node APIs, process.env, or browser fetch.
  • Validate payloads. context.type is http, cron, manual, or test; only HTTP executions include context.request.
  • kv is temporary Worker-scoped storage. Use kv.workspace only for intentional workspace sharing; neither is a durable database.
  • Draft tests isolate KV, but outbound requests can still cause real side effects. Never print or return Secret values.

Verify and report

For code changes, provide valid and invalid example payloads and required environment-variable names. After a requested mutation, re-read the Worker and verify the intended settings. Check execution results and logs for runtime success: saving code or receiving HTTP 200 alone is insufficient.

Report the target, changes, verification performed, and any remaining uncertainty. Distinguish draft tests, manual executions, public HTTP requests, and actual scheduled runs.

© msgbyte, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/tianji-worker of msgbyte/tianji.

  • SKILL.md
  • references/agent-reference.md
  • references/operations.md

Open the folder on GitHubat commit 28243e9

Compare with similar skills

Tianji Worker Operations next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Tianji Worker Operations compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tianji Worker Operations this skillmsgbyte/tianji3.1k—~1.1kAutomated safety check: PassApache-2.0
Aliyun Esa Managecinience/alicloud-skills397—~4.8kAutomated safety check: PassMIT
Deploy Verceljohnku2011/boilerplates-with-ai-skills240—~660Automated safety check: NotesMIT
Model Deploymentawslabs/agent-plugins9121 repos~1.5kAutomated safety check: PassApache-2.0
C4 Containeraiskillstore/marketplace4306 repos~1.4kAutomated safety check: PassNone
AWS Serverless Deploymentawslabs/agent-plugins912—~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • Aliyun Esa Manage

    cinience/alicloud-skills

    A skill your agent uses when managing Alibaba Cloud ESA — deploy HTML/static sites via Pages, manage Edge Routines (ER) for serverless edge functions, use Edge KV for distributed key-value storage…

    397 GitHub stars~4.8k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Deploy Vercel

    johnku2011/boilerplates-with-ai-skills

    A skill your agent uses when deploying or configuring this project on Vercel — env vars, build settings, serverless limits, and production checks for Next.js or Express.

    240 GitHub stars~660 tokensUpdated 1 mo ago
    Backend & APIsAuto-check: notes
  • Model Deployment

    awslabs/agent-plugins

    Official

    Generates code that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Bedrock.

    912 GitHub starsUsed in 1 repo~1.5k tokens
    Backend & APIsAuto-check passed
  • C4 Container

    aiskillstore/marketplace

    Expert C4 Container-level documentation specialist. An agent skill from aiskillstore/marketplace.

    430 GitHub starsUsed in 6 repos~1.4k tokens
    Backend & APIsAuto-check passed
  • AWS Serverless Deployment

    awslabs/agent-plugins

    Official

    AWS SAM and AWS CDK deployment for serverless applications. An agent skill from awslabs/agent-plugins.

    912 GitHub stars~1.3k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Cloud Provisioning

    elastic/agent-skills

    Official

    Provision and operate Elastic Cloud infrastructure: create, connect to, update, and delete Serverless projects (Elasticsearch, Observability, Security); manage traffic filters (IP and AWS…

    592 GitHub stars~5.4k tokensUpdated 5 days ago
    Backend & APIsAuto-check passed

More from msgbyte/tianji

  • Answers questions about website traffic, monitors, surveys, events and billing from a Tianji instance using read-only GET calls checked against its live OpenAPI document.

    3.1k GitHub stars~1.5k tokensUpdated 4 days ago
    Auto-check passed

Works with

Questions about Tianji Worker Operations

What does Tianji Worker Operations do?

Operates Tianji Workers: create, test, deploy, invoke, schedule, pause and roll back them, plus manage their environment variables and shared modules. Before touching a Worker, the agent identifies the operation, Tianji server, workspace and Worker, and never guesses a target.js, browsers and Cloudflare Workers.

When should I use Tianji Worker Operations?

Tianji Worker Operations fits situations like: creating and deploying a new Tianji Worker; scheduling, pausing or rolling back a deployed Worker; debugging a Worker run through its executions and logs; managing Worker environment variables and shared modules.

How do I install Tianji Worker Operations in Claude Code?

Run `npx skills add msgbyte/tianji --skill tianji-worker -a claude-code`. Or copy the skill folder (skills/tianji-worker in msgbyte/tianji) into .claude/skills/tianji-worker in your project. Claude Code loads it when a task matches its description.

How do I install Tianji Worker Operations in Codex?

Run `npx skills add msgbyte/tianji --skill tianji-worker -a codex`. Or copy the skill folder (skills/tianji-worker in msgbyte/tianji) into .agents/skills/tianji-worker in your project. Codex loads it when a task matches its description.

Can I use Tianji Worker Operations in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add msgbyte/tianji --skill tianji-worker -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tianji-worker, .gemini/skills/tianji-worker, .github/skills/tianji-worker and .opencode/skills/tianji-worker in your project.

What does Tianji Worker Operations need to run?

SKILL.md names no scripts, command-line tools or credentials: Tianji Worker Operations is instructions for the agent only. Our summary lists: Access to a Tianji server and workspace; The tianji CLI for local Worker projects.

Does Tianji Worker Operations access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Tianji Worker Operations safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Tianji Worker Operations use?

Tianji Worker Operations is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tianji Worker Operations use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.5k tokens, read only when the agent opens those files.

What are the alternatives to Tianji Worker Operations?

Skills that share tags, products or a category with Tianji Worker Operations: Aliyun Esa Manage (cinience/alicloud-skills, 397 stars), Deploy Vercel (johnku2011/boilerplates-with-ai-skills, 240 stars), Model Deployment (awslabs/agent-plugins, 912 stars) and C4 Container (aiskillstore/marketplace, 430 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tianji Worker Operations?

msgbyte (a GitHub organization) maintains it in msgbyte/tianji, which has 3,102 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 3, 2026.

Source: msgbyte/tianji on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.