← Back to Skills Marketplace
bytesagain-lab

Coze Studio

by bytesagain-lab · GitHub ↗ · v2.0.0 · MIT-0
cross-platform ✓ Security Clean
378
Downloads
0
Stars
1
Active Installs
9
Versions
Install in OpenClaw
/install coze-studio
Description
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging coze studio, typescript, agent, agent-platform.
README (SKILL.md)

Coze Studio

An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation. ## Commands

  • help - Help
  • run - Run
  • info - Info
  • status - Status

Features

  • Core functionality from coze-dev/coze-studio

Usage

Run any command: coze-studio \x3Ccommand> [args]

💬 Feedback & Feature Requests: https://bytesagain.com/feedback Powered by BytesAgain | bytesagain.com

Examples

# Show help
coze-studio help

# Run
coze-studio run

  • Run coze-studio help for all commands

  • Run coze-studio help for all commands

Configuration

Set COZE_STUDIO_DIR to change data directory. Default: ~/.local/share/coze-studio/

Usage Guidance
This skill appears to be a small, local CLI utility that stores data under COZE_STUDIO_DIR (default ~/.local/share/coze-studio). Before installing or running: (1) review the scripts yourself to confirm behavior (they only write logs and a simple DB file), (2) avoid pointing COZE_STUDIO_DIR at sensitive system paths, and (3) run in a sandbox or non-critical account if you want to be cautious. Note that the SKILL.md advertises a larger platform but the shipped scripts are basic placeholders — functionality is limited rather than risky.
Capability Analysis
Type: OpenClaw Skill Name: coze-studio Version: 2.0.0 The skill bundle contains basic bash scripts (coze_studio.sh and script.sh) that implement simple logging and data management functions within a local directory (~/.local/share/coze-studio/). While the description in SKILL.md claims to be a complex AI development platform, the provided code is merely a placeholder or template with no network activity, data exfiltration, or malicious execution patterns.
Capability Assessment
✓ Purpose & Capability
The name/description claim an AI-agent dev platform; the included scripts implement a small local CLI with commands like run, status, add, list and reference COZE_STUDIO_DIR. The requested artifacts (no credentials, no unusual binaries) match a lightweight CLI helper. The only minor mismatch is that the SKILL.md advertises broader functionality but the scripts are simple placeholders/utility functions rather than a full platform — this is a functionality gap, not a security inconsistency.
✓ Instruction Scope
SKILL.md instructs to run 'coze-studio <command>'; it documents COZE_STUDIO_DIR. The bundled scripts only create a data directory, append to logs/data files, and echo output. They do not read unrelated system files, call external endpoints, or access secrets. They do read standard env vars (XDG_DATA_HOME, HOME) which is expected.
✓ Install Mechanism
No install spec is provided (instruction-only). The included shell scripts are small and plain text; there are no downloads, package installs, or archive extraction steps. Low-risk from an install perspective.
✓ Credentials
The skill requires no credentials or special environment variables. It optionally respects COZE_STUDIO_DIR (and standard XDG_DATA_HOME/HOME) to set its data directory, which is reasonable for a local CLI. No secrets or unrelated service tokens are requested.
✓ Persistence & Privilege
The skill is not 'always: true', does not request system-wide config changes, and does not modify other skills. It creates and writes files only under the user-specified (or default) data directory.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install coze-studio
  3. After installation, invoke the skill by name or use /coze-studio
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.0
v2.5 standard: Use-when desc, homepage, source, security fix
v1.0.7
yaml-fix+quality
v1.0.6
yaml-fix+quality
v1.0.5
Quality upgrade
v1.0.4
Quality upgrade: custom functionality
v1.0.3
Standards compliance: unique content, no template text
v1.0.2
Quality fix: cleaner docs, removed flags
v1.0.1
Quality update: docs, examples, standards compliance
v1.0.0
Initial release
Metadata
Slug coze-studio
Version 2.0.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 9
Frequently Asked Questions

What is Coze Studio?

An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging coze studio, typescript, agent, agent-platform. It is an AI Agent Skill for Claude Code / OpenClaw, with 378 downloads so far.

How do I install Coze Studio?

Run "/install coze-studio" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Coze Studio free?

Yes, Coze Studio is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Coze Studio support?

Coze Studio is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Coze Studio?

It is built and maintained by bytesagain-lab (@bytesagain-lab); the current version is v2.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments