Arg Action Chain Designer | Agent Skills Atlas

About this skill

Use when the user wants to create, refine, review, or convert an agent task or existing skill into an ARG Action Chain / ARG 行动链路. This skill is especially relevant for recurring automations, multi-step agent jobs, data pipelines, report generation, MCP workflows, or tasks where agent drift, hallucinated fields, self-verification, premature planning, or uncontrolled long-context execution are risks. Trigger when the user mentions ARG, Step Contract, clue card, validation gate, progressive disclosure, reducing agent drift/self-deception, converting a normal skill into arg-xxx, or making a task chain more bounded and verifiable.

Quick start

Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.

Installation guide →

Review, license & listing details

Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1

Content SHA-256: 1afb2bdfbcfe5ef072bb773cd5715572f75bdc9813cd354c196846fff2202641

About scan coverage and limitations

Original listing metadata

Original name

arg-action-chain-designer

Original description

Use this skill when the user wants to create, refine, review, or convert an agent task or existing skill into an ARG Action Chain / ARG 行动链路. This skill is especially relevant for recurring automations, multi-step agent jobs, data pipelines, report generation, MCP workflows, or tasks where agent drift, hallucinated fields, self-verification, premature planning, or uncontrolled long-context execution are risks. Trigger when the user mentions ARG, Step Contract, clue card, validation gate, progressive disclosure, reducing agent drift/self-deception, converting a normal skill into arg-xxx, or making a task chain more bounded and verifiable.

About this listing

Category: Developer tools
Reported license: MIT
Listing language (estimated): English
Review status: Not individually reviewed
Agent compatibility: Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.