mrkeyoor.com_
Thu 10 Sept 18:04 UTC
AI Toolsevaluationupdated 10 Sept 2026

agency-agents-zh review

agency-agents-zh is a Chinese-language collection of 277 ready-made AI expert roles, with English documentation available through its linked upstream project. It gives teams reusable role instructions and workflows for coding assistants, including 64 roles tailored to Chinese platforms and industries, so they do not have to draft every specialist persona from scratch.

trackingstars / 7d
Verdict

Our install finished in 4 seconds with 0 packages added. Use agency-agents-zh as a well-stocked Chinese role library, especially when its platform-specific experts save you from translating or localizing the English upstream yourself. Do not mistake its popularity and breadth for verified agent quality: there is no build or automated test target, so serious teams should review, trim, and evaluate the roles they actually deploy.

We ran it

Install✓ · 4s0 packages · 11 MB
Buildn/ano build script
Testsn/ano test script
Known vulns00 critical · 0 high · 0 moderate · 0 low (npm audit)
Repo366 files~2,645 lines of source · 6.2 MB · 4 CI workflows

Answers from our run

Does agency-agents-zh build from source?

Dependencies installed in 4 seconds (0 packages), and the project has no separate build step. We cloned commit e00aed9 into a clean Debian container with 3 CPUs and no project-specific setup.

Does agency-agents-zh have tests you can run?

Not through a standard command: the project exposes no test script or target that our harness could run.

Does agency-agents-zh have known vulnerabilities in its dependencies?

npm audit found none in the dependency tree at the time of our run.

Who should not use agency-agents-zh?

Teams expecting an autonomous multi-agent runtime, because this repository is mainly role content

What are the alternatives to agency-agents-zh?

Agency Agents upstream, Awesome Claude Code Subagents, Anthropic Skills. Our install finished in 4 seconds with 0 packages added.

Setup4/54-second install, but useful adoption still needs manual role selection
Docs4/5Clear scope, tool coverage, desktop option, and linked courses
Community5/520,550 stars, 1 open issue, and a push on review day
Maturity3/5Large active catalog, but no automated build or test target

Who it’s for

Chinese-speaking teams that want a large, browsable library of specialist AI roles
Claude Code, Cursor, or Copilot users who prefer adapting written agent definitions
Operators working with Chinese platforms such as WeChat, Douyin, Bilibili, Feishu, or DingTalk
Teams willing to review and customize prompts before using their outputs

Who it’s NOT for

Teams expecting an autonomous multi-agent runtime, because this repository is mainly role content
Buyers who require English-first local documentation, because the maintained edition is Chinese
Regulated teams seeking tested policy enforcement or guaranteed output quality
Developers who want a conventional library with a build and automated test suite

Setup reality

Our sandbox install succeeded in 4 seconds, added 0 packages, and occupied 11 MB, which confirms that this is much closer to a content pack than a conventional Node application. There was no build script and no test target, so both steps were skipped; npm audit found 0 known vulnerabilities. The README's plug-and-play message is fair for browsing or copying roles, but meaningful adoption still requires choosing the right definitions, placing them in one of the 20 supported tools, and checking how each role behaves in your own workflow.

It is a localized expert library, not an AI workforce in a box

agency-agents-zh takes the role-library idea from msitarzewski/agency-agents and turns it into a Chinese-first collection. The headline number is 277 specialists across 20 departments, from executive roles such as CEO and CFO to engineering, design, marketing, security, finance, GIS, and game work. Each entry is presented as more than a generic prompt: the README says roles have their own personas, professional processes, and expected deliverables. That is useful structure, not proof that every role will make sound decisions.

Localization is the reason to choose this edition. The project reports 213 translated upstream roles and 64 original roles for the Chinese market. Those additions cover Xiaohongshu, Douyin, WeChat, Bilibili, Feishu, DingTalk, cross-border commerce, government work, medical compliance, industrial Qt software, mechanical design, and livestock record checking. English readers can use the linked upstream documentation, but this repository is Chinese-first. Teams serving those markets get vocabulary and workflows that an English-only catalog would require them to recreate.

What happened when we ran it

We cloned commit e00aed9 into an unprivileged Debian container with 3 CPUs, 8 GB of RAM, Node 22, and no secrets. The npm install completed in 4 seconds, installed 0 packages, and occupied 11 MB. That fits the repository's nature: it is primarily a collection of files and instructions, not an application with a dependency tree. The checkout contained 366 files, about 2,645 lines of source, and occupied 6.2 MB before installation.

There was no build script or target, so our run skipped compilation. There was also no test script or tests directory, so we could not execute an automated quality check. npm audit reported 0 known vulnerabilities across all severity levels, though 0 packages were installed. We found 4 CI workflow files. Those are a positive maintenance signal, but they do not substitute for tests that verify role formatting, installation paths, or behavior across the advertised 20 tools.

The breadth is useful when you know the job

The strongest feature is selection. A team can start with a named specialist rather than stretching one general assistant across 20 departments. The China-specific set is particularly concrete: platform operations, regulated sectors, industrial software, and vertical business tasks are not merely translated labels. The repository also claims compatibility with Claude Code, Cursor, Copilot, and 17 other AI coding tools, making the role files more portable than a catalog locked to one interface. The MIT license allows internal adaptation.

The README links a native desktop client for 3 operating systems, macOS, Windows, and Linux, plus an online experts page. It also points to a 35-lesson course focused on using the 277 experts individually and in teams. That supporting material can help newcomers because a catalog this large can become a directory people admire but rarely use. The practical win is finding a few roles that match recurring work and refining them against real examples.

The missing evaluation layer matters more than the missing build

The absence of a build is not a defect by itself because there may be nothing to compile. The absence of automated tests is more consequential. A role can be syntactically valid yet produce vague plans, unsafe actions, weak citations, or inconsistent deliverables. Our box found no test target across 366 files. The claims about independent workflows and useful outputs therefore remain documentation claims, not measured performance. Teams should create scenario checks for every role that reaches production work.

The supplied README excerpt is crowded with at least 7 sponsor blocks, discount codes, API intermediaries, courses, and companion products. Sponsorship is not evidence against the library, but it makes project instructions harder to scan. Security-conscious teams should be careful around third-party model gateways: nothing in our no-secrets run tested those services, their pricing, their uptime, or their handling of prompts and credentials. Treat commercial claims as advertisements, not as project capabilities we verified.

Current activity is stronger evidence than the June release

The repository had 20,550 stars and only 1 open issue at review time. More importantly, its last push was September 10, 2026, the day of our review. The latest tagged release was v1.2.6 on June 16, 2026. That gap does not suggest abandonment because the source is still moving. The low issue count and same-day push together look healthy, although one issue total cannot show how quickly maintainers respond or whether users report problems elsewhere.

The community signal is unusually strong for a project created March 6, 2026: the supplied community item recorded 20,497 stars, while the repository snapshot showed 20,550. Fast adoption can attract contributions and speed translations, but it can also amplify uneven material. With 277 roles and no automated behavioral suite, maintainers need editorial discipline as much as code review. Version tags identify the bundle; they do not certify that a compliance or finance persona is accurate enough for unsupervised use.

It fits beside your assistant, with your controls around it

In a real stack, treat agency-agents-zh as a source layer. Select 1 role, inspect its instructions, adapt its deliverable format, and load it into a supported tool. Keep model access, retrieval, permissions, approvals, logging, and evaluation in your existing platform. For higher-risk work, require human review and restrict tool access. The project can help define who the assistant is supposed to be, but it does not provide the runtime controls that determine what the assistant may do.

Start with 2 or 3 recurring tasks and compare the selected roles with a plain baseline prompt. Record missed requirements, unsupported claims, and intervention rates, then keep only definitions that improve actual work. If your team is English-first, the upstream repository is the cleaner default. If your work depends on Chinese platforms or local business vocabulary, this edition is more practical, provided you regard its 277 roles as editable operating drafts rather than certified experts.

Alternatives

ProjectWhat it isPick it when
Agency Agents upstream gh↗The English upstream collection on which this Chinese edition is based.Pick this instead when your team works mainly in English or wants to stay closest to the original project.
Awesome Claude Code SubagentsA development-focused catalog of specialized Claude Code subagents.Pick this instead when Claude Code is your primary environment and software engineering roles matter more than Chinese-market operations.
Anthropic Skills gh↗Anthropic's examples and reusable Agent Skills for Claude workflows.Pick this instead when you want official skill patterns, scripts, and resources rather than a broad persona catalog.

What people are saying

  1. [velocity-scout] jnMetaCode/agency-agents-zh

Sources

  1. agency-agents-zh GitHub repository
  2. Agency Orchestrator experts homepage
  3. Agency Agents upstream repository

More ai tools reviews

speech-to-speech · alphagenome · awesome-generative-ai-apps · CloddsBot · opencv · flash-attention · the whole board →