Agent skill

Awsl

Run Claude Code JavaScript Workflows through the awsl compatibility runtime.

Apache-2.0Auto-check passedAgent Workflows

Install Awsl

skills CLI

$ npx skills add XhinLiang/awsl --skill awsl -a claude-code

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

GitHub CLI

$ gh skill install XhinLiang/awsl awsl --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/XhinLiang/awsl.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/awsl .claude/skills/awsl && 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/

Paste into Claude Code

Install the "awsl" agent skill from https://github.com/XhinLiang/awsl/tree/main/skills/awsl into .claude/skills/awsl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "awsl", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/XhinLiang/awsl/tree/main/skills/awsl

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add XhinLiang/awsl --skill awsl -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install XhinLiang/awsl awsl --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/XhinLiang/awsl.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/awsl .agents/skills/awsl && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "awsl" agent skill from https://github.com/XhinLiang/awsl/tree/main/skills/awsl into .agents/skills/awsl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "awsl", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add XhinLiang/awsl --skill awsl -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install XhinLiang/awsl awsl --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/XhinLiang/awsl.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/awsl .cursor/skills/awsl && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "awsl" agent skill from https://github.com/XhinLiang/awsl/tree/main/skills/awsl into .cursor/skills/awsl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "awsl", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/XhinLiang/awsl.git --path skills/awsl

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add XhinLiang/awsl --skill awsl -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install XhinLiang/awsl awsl --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/XhinLiang/awsl.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/awsl .gemini/skills/awsl && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "awsl" agent skill from https://github.com/XhinLiang/awsl/tree/main/skills/awsl into .gemini/skills/awsl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "awsl", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install XhinLiang/awsl awsl

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add XhinLiang/awsl --skill awsl -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/XhinLiang/awsl.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/awsl .github/skills/awsl && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "awsl" agent skill from https://github.com/XhinLiang/awsl/tree/main/skills/awsl into .github/skills/awsl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "awsl", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add XhinLiang/awsl --skill awsl -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install XhinLiang/awsl awsl --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/XhinLiang/awsl.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/awsl .opencode/skills/awsl && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "awsl" agent skill from https://github.com/XhinLiang/awsl/tree/main/skills/awsl into .opencode/skills/awsl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "awsl", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: awsl
GitHub stars: 104
Token cost: ~687 tokens
SKILL.md length: 331 words
Files: 2
Skills in repo: 1
Repo updated: Sep 29, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Run Claude Code JavaScript Workflows through the awsl compatibility runtime.

Works in 4 steps: Preserve the calling instructions'… → Use the explicit Workflow implementation… → Read the Workflow's literal meta and… → …
An agents current task
SKILL.md covers Adapt the dispatch, Run the workflow and Continue or diagnose
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Awsl is an agent skill from XhinLiang/awsl. Run Claude Code JavaScript Workflows through the awsl compatibility runtime. Use when an agent's current task or loaded Skill requires dispatching a Claude Code Workflow but the host cannot execute that Workflow natively, or when awsl workflow inspection, durable run state, resume, or provider diagnostics are needed.

Its SKILL.md is about 690 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Agent Workflows. It works with JavaScript and TypeScript. The repository describes itself as: Codex-verified, Claude-compatible durable local runtime for Claude Code Workflow JS, with resume, checkpoints, budgets, and Git worktrees. The licence is Apache-2.0.

When your agent uses it

An agents current task
Loaded Skill requires dispatching a Claude Code Workflow but the host cannot execute that Workflow natively
Awsl workflow inspection
Durable run state

Example prompts

“/awsl”

Workflow steps

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

Preserve the calling instructions' prerequisite checks, argument defaults,
Use the explicit Workflow implementation path from the calling
Read the Workflow's literal meta and confirm meta.name matches the
Do not copy, migrate, symlink, or edit the calling Skill or Workflow to make

What it can do on your machine

Read from SKILL.md and the folder at commit b405764. 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 json and bash).
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

Awsl loads about 687 tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 331 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~81
When it runs · the whole SKILL.md, loaded when a task matches: ~687

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 XhinLiang/awsl at commit b405764, republished under its Apache-2.0 licence (© XhinLiang). 331 words, ~687 tokens.

Download SKILL.mdSave it as .claude/skills/awsl/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: awsl
description: Run Claude Code JavaScript Workflows through the awsl compatibility runtime. Use when an agent's current task or loaded Skill requires dispatching a Claude Code Workflow but the host cannot execute that Workflow natively, or when awsl workflow inspection, durable run state, resume, or provider diagnostics are needed.

Claude Code Workflow compatibility

Use the installed awsl executable as the workflow runtime. Run awsl help or awsl help <command> when repository instructions do not provide the complete invocation contract.

Do not search for or select repository Skills on awsl's behalf. The calling agent remains responsible for its current task and loaded Skill. Use this Skill only after those instructions require a Claude Code Workflow and native Workflow dispatch is unavailable or incompatible.

Adapt the dispatch

When current instructions dispatch a request shaped like:

json

{ "name": "<workflow>", "args": {} }

Preserve the calling instructions' prerequisite checks, argument defaults, modes, and reporting contract.
Use the explicit Workflow implementation path from the calling instructions. If only a name is provided, resolve it to .claude/workflows/<workflow>.js below the repository root.
Read the Workflow's literal meta and confirm meta.name matches the dispatch name.
Do not copy, migrate, symlink, or edit the calling Skill or Workflow to make it compatible.

Run the workflow

Validate locally with awsl workflow inspect <workflow> when the path or Workflow ABI is uncertain.
Translate the existing dispatch to the CLI:

bash

awsl run <workflow> --provider codex --cwd <repo-root> --args '<strict-json>'

Pass only the dispatch object's args value to --args; name selects the Workflow and is not part of its arguments. Do not invent missing values, reinterpret the calling instructions, or reimplement the Workflow as ad hoc model calls. Prefer --args-file when JSON is large or shell quoting would be fragile.

Continue or diagnose

Run awsl doctor when the executable or Codex provider is unavailable.
awsl automatically retries only safe transient failures that occur before provider output or tool activity; do not wrap awsl run in another blind retry loop.
Run awsl runs list and awsl runs show <run-id> before deciding whether a failed or interrupted operation should resume.
Use awsl resume <run-id> only when the repository workflow's own run ID and awsl's durable run ID have been identified correctly; they may be different.
Report the workflow's terminal result. On failure, preserve repository checkpoints and include the awsl run ID needed for continuation.

Files

SKILL.md and 1 other file in skills/awsl of XhinLiang/awsl.

SKILL.md
agents/openai.yaml

Open the folder on GitHubat commit b405764

Compare with similar skills

Awsl 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.

Awsl compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Awsl this skillXhinLiang/awsl	104	—	~687	Automated safety check: Pass	Apache-2.0	11 days ago
Remove Dead Codeqdhenry/Claude-Command-Suite	1.3k	—	~986	Automated safety check: Pass	None	7 mo ago
Developing Genkit JSgoogle/skills	21k	1 repos	~3.1k	Automated safety check: Pass	Apache-2.0	yesterday
Build Audit Logsactivepieces/activepieces	25k	1 repos	~5.9k	Automated safety check: Pass	Custom licence	today
Build With SimplepdfSimplePDF/simplepdf-embed	407	—	~7k	Automated safety check: Pass	MIT	yesterday
Browser Testing With Devtoolsshashankswe2020-ux/whoop-mcp	165	—	~3k	Automated safety check: Warn	MIT	yesterday

Similar skills

Remove Dead Code
qdhenry/Claude-Command-Suite
Safely identifies and removes dead code in TypeScript/JavaScript projects using multi-agent analysis with automatic backup branches.
1.3k GitHub stars~986 tokensUpdated 7 mo ago
Agent WorkflowsAuto-check passed
Developing Genkit JS
google/skills
Official
Develop AI-powered applications using Genkit in Node.js/TypeScript.
21k GitHub starsUsed in 1 repo~3.1k tokens
Agent WorkflowsAuto-check passed
Build Audit Logs
activepieces/activepieces
Build or review audit trails in TypeScript/JavaScript apps using evlog (pipelines, typed actions, denials, retention, compliance-style reviews).
25k GitHub starsUsed in 1 repo~5.9k tokens
Productivity & AutomationAuto-check passed
Build With Simplepdf
SimplePDF/simplepdf-embed
Integrate SimplePDF into a web application for PDF viewing, editing, filling, signing, programmatic control, AI-agent interaction, human-in-the-loop form prefilling, submissions, webhooks, or…
407 GitHub stars~7k tokensUpdated yesterday
Documents & OfficeAuto-check passed
Browser Testing With Devtools
shashankswe2020-ux/whoop-mcp
Tests in real browsers. An agent skill from shashankswe2020-ux/whoop-mcp.
165 GitHub stars~3k tokensUpdated yesterday
Testing & QAAuto-check: warnings
AWS Lambda Durable Functions
awslabs/agent-plugins
Official
Build resilient, long-running, multi-step applications with AWS Lambda durable functions with automatic state persistence, retry logic, and orchestration for long-running executions.
916 GitHub stars~2.3k tokensUpdated today
Backend & APIsAuto-check passed

Works with

Questions about Awsl

What does Awsl do?

Run Claude Code JavaScript Workflows through the awsl compatibility runtime. Awsl is an agent skill from XhinLiang/awsl. Run Claude Code JavaScript Workflows through the awsl compatibility runtime.

When should I use Awsl?

Awsl fits situations like: an agents current task; loaded Skill requires dispatching a Claude Code Workflow but the host cannot execute that Workflow natively; awsl workflow inspection; durable run state.

How do I install Awsl in Claude Code?

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

How do I install Awsl in Codex?

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

Can I use Awsl 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 XhinLiang/awsl --skill awsl -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/awsl, .gemini/skills/awsl, .github/skills/awsl and .opencode/skills/awsl in your project.

What does Awsl need to run?

SKILL.md names no scripts, command-line tools or credentials: Awsl is instructions for the agent only.

Does Awsl 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 Awsl 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 Awsl use?

Awsl 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 Awsl use?

About 687 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Awsl?

Skills that share tags, products or a category with Awsl: Remove Dead Code (qdhenry/Claude-Command-Suite, 1.3k stars), Developing Genkit JS (google/skills, 21k stars), Build Audit Logs (activepieces/activepieces, 25k stars) and Build With Simplepdf (SimplePDF/simplepdf-embed, 407 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Awsl?

XhinLiang (a GitHub user) maintains it in XhinLiang/awsl, which has 104 GitHub stars. The repository was last updated on September 29, 2026.

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

Install Awsl

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Claude Code Workflow compatibility

Adapt the dispatch

Run the workflow

Continue or diagnose

Files

Compare with similar skills

Similar skills

Remove Dead Code

Developing Genkit JS

Build Audit Logs

Build With Simplepdf

Browser Testing With Devtools

AWS Lambda Durable Functions

Related

Questions about Awsl