New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Reproduce Chat States

by different-ai in different-ai/openwork

Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.

Custom licenceAuto-check passedTesting & QA

Install Reproduce Chat States

skills CLI
$ npx skills add different-ai/openwork --skill reproduce-chat-states -a claude-code

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

GitHub CLI
$ gh skill install different-ai/openwork reproduce-chat-states --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/different-ai/openwork.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/reproduce-chat-states .claude/skills/reproduce-chat-states && 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
reproduce-chat-states
GitHub stars
24k
Token cost
~673 tokens
SKILL.md length
257 words
Files
2 (incl. scripts)
Skills in repo
33
Repo updated
First seen
Licence
Custom licence

At a glance

Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.

  • Fixing or designing chat error and retry UI in the desktop app
  • SKILL.md covers States and what to look at and Reading what happened
  • Runs JavaScript scripts from its folder; calls node and sqlite3
  • Checking how parallel tool steps or app cards render

What it does

Each named state starts in a new session of the running desktop window through the drive-desktop-cdp skill, using a Node script that lists the available states when run without an argument. Provider-fault states also need fake-model-faults set up, and a second argument or an environment variable changes the real model used for the other states.

A table pairs each state with what to look at: transport errors that are retried, reconnecting messages, interrupted replies that keep partial text, HTTP 429, 5xx, 401 and 402 errors, Code Mode and Den script failures, parallel tool calls grouped into one readable block, app creation cards, and sequential bash calls that should not make the chat jump. Stored v2 history in a local SQLite database shows what the engine recorded when a step looks wrong.

When your agent uses it

  • Fixing or designing chat error and retry UI in the desktop app
  • Checking how parallel tool steps or app cards render
  • Verifying that a recovered Code Mode step does not look like a hard failure
  • Inspecting stored session history when a step looks wrong

Example prompts

  • “Reproduce the provider-reset state and check that only one error shows per turn.”
  • “Fire the den-script-parallel state and confirm the calls collapse into one group.”
  • “Show me what the engine recorded for the app-create session.”

Requirements

  • The OpenWork desktop app running with a CDP port
  • The drive-desktop-cdp skill
  • fake-model-faults, for provider states
  • Node

What it can do on your machine

Read from SKILL.md and the folder at commit ad22cdc. 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

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node
    • sqlite3

    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

Reproduce Chat States loads about 673 tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 257 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~673

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); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 257 words (~673 tokens).

“Each state below fires in a new session of the running desktop window through drive-desktop-cdp. Provider states also need fake-model-faults set up.”

— opening of SKILL.md by different-ai, Custom licence
name
reproduce-chat-states

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (scripts) in .opencode/skills/reproduce-chat-states of different-ai/openwork.

  • SKILL.md
  • scripts/repro.mjs

Open the folder on GitHubat commit ad22cdc

Compare with similar skills

Reproduce Chat States 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.

Reproduce Chat States compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Reproduce Chat States this skilldifferent-ai/openwork24k—~673Automated safety check: PassCustom licence
OpenCode QA Toolkitcode-yeongyu/oh-my-openagent70k—~2.9kAutomated safety check: PassCustom licence
Codex Coding Pluginstyler-ai/ProjectAtlas442—~1.8kAutomated safety check: PassMIT
Visual QA For Web And Terminal UIscode-yeongyu/oh-my-openagent70k—~9.5kAutomated safety check: PassCustom licence
Scoutqa Testgithub/awesome-copilot40k1 repos~3.5kAutomated safety check: PassMIT
QA Testingespennilsen/pi122—~2.9kAutomated safety check: PassMIT

Similar skills

  • OpenCode QA Toolkit

    code-yeongyu/oh-my-openagent

    Tests the opencode coding agent itself: its CLI, server, plugin hooks and events, the terminal UI under tmux, and its SQLite session database, using tested helper scripts.

    70k GitHub stars~2.9k tokensUpdated today
    Testing & QAAuto-check passed

  • Codex Coding Plugin

    styler-ai/ProjectAtlas

    Build, review, or fix ProjectAtlas plugin/runtime installer integration for Codex, Claude Code, and OpenCode, especially version convergence, stale ProjectAtlas cache repair, MCP config generation…

    442 GitHub stars~1.8k tokensUpdated today
    Testing & QAAuto-check passed

  • Visual QA For Web And Terminal UIs

    code-yeongyu/oh-my-openagent

    Checks a built UI against a human-interface checklist and any reference image, pairing day and night screenshots at two screen widths.

    70k GitHub stars~9.5k tokensUpdated today
    Testing & QAAuto-check passed

  • Scoutqa Test

    github/awesome-copilot

    Official

    This skill should be used when the user asks to "test this website", "run exploratory testing", "check for accessibility issues", "verify the login flow works", "find bugs on this page", or requests…

    40k GitHub starsUsed in 1 repo~3.5k tokens
    Testing & QAAuto-check passed

  • QA Testing

    espennilsen/pi

    Perform QA testing on running web applications using cmuxbrowser.

    122 GitHub stars~2.9k tokensUpdated 19 days ago
    Testing & QAAuto-check passed

  • QA Engineer

    dralgorhythm/claude-agentic-framework

    Define test strategy and verify quality against WCAG and testing-pyramid criteria — a user-invoked QA Engineer workflow.

    125 GitHub stars~631 tokensUpdated 2 mo ago
    Testing & QAAuto-check passed

More from different-ai/openwork

All 33 skills in this repo

  • OpenWork Desktop CDP Driver

    different-ai/openwork

    Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks.

    24k GitHub stars~465 tokensUpdated today
    Auto-check passed

  • Fake Model Provider Faults

    different-ai/openwork

    Makes the desktop app's model provider fail on demand, with refused connections, resets, stalls and HTTP 4xx and 5xx errors, so error and retry states can be reproduced.

    24k GitHub stars~642 tokensUpdated today
    Auto-check passed

  • OpenWork Model Alias Manager

    different-ai/openwork

    Manages OpenWork's inference model aliases, discounts and overlays over the upstream OpenRouter catalog, and triggers the GitHub workflow that refreshes base models.

    24k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • OpenWork Electron Browser Automation

    different-ai/openwork

    Attaches OpenCode browser tools to the OpenWork Electron dev app through CDP to explore its UI, send a composer task and debug, not to give test verdicts.

    24k GitHub stars~780 tokensUpdated today
    Auto-check passed

  • Daytona Sandbox Operations

    different-ai/openwork

    Covers Daytona CLI setup, sandbox debugging, keeping a sandbox alive and which credentials the CLI uses, for when Daytona itself is the problem rather than the tests.

    24k GitHub stars~917 tokensUpdated today
    Auto-check passed

  • Daytona Seeded Cloud Demo

    different-ai/openwork

    Spins up a persistent OpenWork Cloud Den demo on a Daytona sandbox, seeds it with Acme Robotics data and returns shareable URLs and login details.

    24k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Reproduce Chat States

What does Reproduce Chat States do?

Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders. Each named state starts in a new session of the running desktop window through the drive-desktop-cdp skill, using a Node script that lists the available states when run without an argument. Provider-fault states also need fake-model-faults set up, and a second argument or an environment variable changes the real model used for the other states.

When should I use Reproduce Chat States?

Reproduce Chat States fits situations like: fixing or designing chat error and retry UI in the desktop app; checking how parallel tool steps or app cards render; verifying that a recovered Code Mode step does not look like a hard failure; inspecting stored session history when a step looks wrong.

How do I install Reproduce Chat States in Claude Code?

Run `npx skills add different-ai/openwork --skill reproduce-chat-states -a claude-code`. Or copy the skill folder (.opencode/skills/reproduce-chat-states in different-ai/openwork) into .claude/skills/reproduce-chat-states in your project. Claude Code loads it when a task matches its description.

How do I install Reproduce Chat States in Codex?

Run `npx skills add different-ai/openwork --skill reproduce-chat-states -a codex`. Or copy the skill folder (.opencode/skills/reproduce-chat-states in different-ai/openwork) into .agents/skills/reproduce-chat-states in your project. Codex loads it when a task matches its description.

Can I use Reproduce Chat States 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 different-ai/openwork --skill reproduce-chat-states -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reproduce-chat-states, .gemini/skills/reproduce-chat-states, .github/skills/reproduce-chat-states and .opencode/skills/reproduce-chat-states in your project.

What does Reproduce Chat States need to run?

Going by SKILL.md and its folder, Reproduce Chat States needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node and sqlite3). Our summary lists: The OpenWork desktop app running with a CDP port; The drive-desktop-cdp skill; fake-model-faults, for provider states; Node.

Does Reproduce Chat States 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 Reproduce Chat States 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Reproduce Chat States use?

Reproduce Chat States has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Reproduce Chat States use?

About 673 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 Reproduce Chat States?

Skills that share tags, products or a category with Reproduce Chat States: OpenCode QA Toolkit (code-yeongyu/oh-my-openagent, 70k stars), Codex Coding Plugin (styler-ai/ProjectAtlas, 442 stars), Visual QA For Web And Terminal UIs (code-yeongyu/oh-my-openagent, 70k stars) and Scoutqa Test (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Reproduce Chat States?

different-ai (a GitHub organization) maintains it in different-ai/openwork, which has 23,993 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 11, 2026.

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