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

Agent Integration Replay

by Comfy-Org in Comfy-Org/ComfyUI_frontend

Replay recorded agent conversations as Playwright tests against the real chat panel and canvas.

GPL-3.0Auto-check: notesTesting & QA

Install Agent Integration Replay

skills CLI
$ npx skills add Comfy-Org/ComfyUI_frontend --skill agent-integration-replay -a claude-code

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

GitHub CLI
$ gh skill install Comfy-Org/ComfyUI_frontend agent-integration-replay --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/Comfy-Org/ComfyUI_frontend.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/agent-integration-replay .claude/skills/agent-integration-replay && 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
agent-integration-replay
GitHub stars
2.1k
Token cost
~805 tokens
SKILL.md length
379 words
Files
1
Skills in repo
22
Repo updated
First seen
Licence
GPL-3.0

At a glance

Replay recorded agent conversations as Playwright tests against the real chat panel and canvas.

  • Asked to replay agent recordings
  • SKILL.md covers Replay the recorded… and Conventions
  • Calls pnpm
  • Run the agent replay suite

What it does

Agent Integration Replay is an agent skill from Comfy-Org/ComfyUI_frontend. Replay recorded agent conversations as Playwright tests against the real chat panel and canvas. Use when asked to replay agent recordings, run the agent replay suite, or debug an agent panel or graph-edit regression against a recording. Triggers on: replay agent conversation, agent replay suite, agent integration test.

Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Integration testing and Browser testing. It works with Playwright, ComfyUI and pnpm. The repository describes itself as: Official front-end implementation of ComfyUI. The licence is GPL-3.0.

When your agent uses it

  • Asked to replay agent recordings
  • Run the agent replay suite
  • Debug an agent panel
  • Graph-edit regression against a recording

Example prompts

  • “/agent-integration-replay”

What it can do on your machine

Read from SKILL.md and the folder at commit f9be289. 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

    Shell commands in SKILL.md call:

    • pnpm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    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

Agent Integration Replay loads about 805 tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 379 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~805

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:45
    `.env`) so the suite backs up and restores its user data.

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 Comfy-Org/ComfyUI_frontend at commit f9be289, republished under its GPL-3.0 licence (© Comfy-Org). 379 words, ~805 tokens.

Download SKILL.mdSave it as .claude/skills/agent-integration-replay/SKILL.md (or your agent's skills folder).
name
agent-integration-replay
description
Replay recorded agent conversations as Playwright tests against the real chat panel and canvas. Use when asked to replay agent recordings, run the agent replay suite, or debug an agent panel or graph-edit regression against a recording. Triggers on: replay agent conversation, agent replay suite, agent integration test.

Agent integration replay

One job: replay the recorded conversations as tests. Replay needs only a ComfyUI backend on port 8188 and the dev server below. Recording a new conversation is the recorder's job, documented in browser_tests/fixtures/data/agent/README.md; the local stack launcher for the real agent is proposed in #16781 and is not in this tree.

Replay the recorded conversations as tests

Every JSON under browser_tests/fixtures/data/agent/conversations/ is one recorded conversation. The replay sends each recorded prompt through the real chat panel, plays the agent's side back from the recording, applies the recorded graph operations through the real multi-player library, and checks the canvas and the panel after every turn.

bash
DISTRIBUTION=cloud DEV_SERVER_COMFYUI_URL=http://127.0.0.1:8188 pnpm dev
bash
pnpm comfy-test agent-replay
  • On a terminal with no flags it asks which recording to replay and whether to watch it. Any flag, or a non-interactive stdin, runs without prompts.
  • One case: pnpm comfy-test agent-replay --case <case id> --headed (the case id is the JSON file name without .json); --video records it under test-results/; --url <origin> points at a dev server other than http://localhost:5173; --help prints usage and runs nothing.
  • Another spec: pnpm comfy-test agent-replay --spec <path> --case <case id> replays the same recordings through a spec that asserts something else about them, so a new agent spec does not need a hand-written Playwright invocation. --case reaches it when the spec titles its cases recorded <case id>, as browser_tests/tests/agent/agentConversationReplay.spec.ts does; without that title the whole spec runs. A --spec path that is not on disk is refused rather than passed to Playwright, which would match nothing.
  • Set TEST_COMFYUI_DIR to the ComfyUI install behind 8188 (or put it in .env) so the suite backs up and restores its user data.
  • The command is a thin front for the raw invocation, which still works when the CLI is not available:
Show full SKILL.md (88 more words)Show less
bash
PLAYWRIGHT_TEST_URL=http://localhost:5173 DISTRIBUTION=cloud pnpm exec playwright test agentConversation --project=cloud

Add --headed to watch it and RECORD_VIDEO=true for video. For one recording use pnpm comfy-test agent-replay --case <case id>.

  • A failing replay names the turn and the assertion. Compare that turn's response entries with what the panel rendered; never edit a fixture to make a test pass.

Conventions

  • A fix that changes what the agent's ops do to the graph or the panel ships with a recording made before the fix, so it went red.
  • Fixtures validate against zAgentConversation in browser_tests/fixtures/data/agent/agentConversation.ts; a schema change is versioned, never silent.

© Comfy-Org, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/agent-integration-replay of Comfy-Org/ComfyUI_frontend.

Open the folder on GitHubat commit f9be289

Compare with similar skills

Agent Integration Replay 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.

Agent Integration Replay compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Integration Replay this skillComfy-Org/ComfyUI_frontend2.1k—~805Automated safety check: NotesGPL-3.0
Kouchou AI Testingdigitaldemocracy2030/kouchou-ai171—~355Automated safety check: PassAGPL-3.0
JS Package TestingOpentrons/opentrons523—~1.2kAutomated safety check: NotesApache-2.0
E2E Testinglangflow-ai/langflow155k—~3.3kAutomated safety check: PassMIT
Ckeditor5 TestingTriliumNext/Trilium38k—~3.3kAutomated safety check: PassAGPL-3.0
UI Previewtingly-dev/tingly-box351—~2kAutomated safety check: NotesMPL-2.0

Similar skills

  • Kouchou AI Testing

    digitaldemocracy2030/kouchou-ai

    Testing commands and strategy for the kouchou-ai repo, including unit/integration tests and Playwright E2E rules.

    171 GitHub stars~355 tokensUpdated today
    Testing & QAAuto-check passed

  • JS Package Testing

    Opentrons/opentrons

    Vite demo and Playwright + Applitools tests for packed @opentrons JS packages in js-package-testing/.

    523 GitHub stars~1.2k tokensUpdated today
    Testing & QAAuto-check: notes

  • E2E Testing

    langflow-ai/langflow

    Write and review Playwright E2E tests for Langflow. An agent skill from langflow-ai/langflow.

    155k GitHub stars~3.3k tokensUpdated today
    Testing & QAAuto-check passed

  • Ckeditor5 Testing

    TriliumNext/Trilium

    Testing CKEditor 5 plugins in the Trilium monorepo. An agent skill from TriliumNext/Trilium.

    38k GitHub stars~3.3k tokensUpdated today
    Testing & QAAuto-check passed

  • UI Preview

    tingly-dev/tingly-box

    Capture headless-Chrome screenshots of the tingly-box frontend (running locally in mock mode) so frontend changes can be visually verified in environments without a real browser.

    351 GitHub stars~2k tokensUpdated today
    Testing & QAAuto-check: notes

  • Tuistory

    remorses/tuistory

    tmux for AI agents. An agent skill from remorses/tuistory.

    367 GitHub stars~2.4k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed

More from Comfy-Org/ComfyUI_frontend

All 22 skills in this repo

  • Adding Deprecation Warnings

    Comfy-Org/ComfyUI_frontend

    Adds deprecation warnings for renamed or removed properties/APIs.

    2.1k GitHub stars~775 tokensUpdated today
    Auto-check passed

  • Codegen Transform

    Comfy-Org/ComfyUI_frontend

    Transforms raw Playwright codegen output into ComfyUI convention-compliant tests.

    2.1k GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Comment Sicko

    Comfy-Org/ComfyUI_frontend

    Dispatches the comment-sicko subagent to hunt gratuitous comments in a PR/diff, triages its raw findings, and posts a polite, professional writeup.

    2.1k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Hardening Flaky E2E Tests

    Comfy-Org/ComfyUI_frontend

    Diagnoses and fixes flaky Playwright e2e tests by replacing race-prone patterns with retry-safe alternatives.

    2.1k GitHub stars~2.8k tokensUpdated today
    Auto-check passed

  • Perf Fix With Proof

    Comfy-Org/ComfyUI_frontend

    Ships performance fixes with CI-proven improvement using stacked PRs.

    2.1k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Publishing A New Package

    Comfy-Org/ComfyUI_frontend

    Publishes a new package from this monorepo to npm under @comfyorg and proves it is consumable from another repo.

    2.1k GitHub stars~1.8k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Agent Integration Replay

What does Agent Integration Replay do?

Replay recorded agent conversations as Playwright tests against the real chat panel and canvas. Agent Integration Replay is an agent skill from Comfy-Org/ComfyUI_frontend. Replay recorded agent conversations as Playwright tests against the real chat panel and canvas.

When should I use Agent Integration Replay?

Agent Integration Replay fits situations like: asked to replay agent recordings; run the agent replay suite; debug an agent panel; graph-edit regression against a recording.

How do I install Agent Integration Replay in Claude Code?

Run `npx skills add Comfy-Org/ComfyUI_frontend --skill agent-integration-replay -a claude-code`. Or copy the skill folder (.claude/skills/agent-integration-replay in Comfy-Org/ComfyUI_frontend) into .claude/skills/agent-integration-replay in your project. Claude Code loads it when a task matches its description.

How do I install Agent Integration Replay in Codex?

Run `npx skills add Comfy-Org/ComfyUI_frontend --skill agent-integration-replay -a codex`. Or copy the skill folder (.claude/skills/agent-integration-replay in Comfy-Org/ComfyUI_frontend) into .agents/skills/agent-integration-replay in your project. Codex loads it when a task matches its description.

Can I use Agent Integration Replay 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 Comfy-Org/ComfyUI_frontend --skill agent-integration-replay -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-integration-replay, .gemini/skills/agent-integration-replay, .github/skills/agent-integration-replay and .opencode/skills/agent-integration-replay in your project.

What does Agent Integration Replay need to run?

Going by SKILL.md and its folder, Agent Integration Replay needs the command-line tools its instructions call (pnpm).

Does Agent Integration Replay 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 Agent Integration Replay safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Agent Integration Replay use?

Agent Integration Replay is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Integration Replay use?

About 805 tokens (SKILL.md is roughly 3.2k 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 Agent Integration Replay?

Skills that share tags, products or a category with Agent Integration Replay: Kouchou AI Testing (digitaldemocracy2030/kouchou-ai, 171 stars), JS Package Testing (Opentrons/opentrons, 523 stars), E2E Testing (langflow-ai/langflow, 155k stars) and Ckeditor5 Testing (TriliumNext/Trilium, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Integration Replay?

Comfy-Org (a GitHub organization) maintains it in Comfy-Org/ComfyUI_frontend, which has 2,056 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 9, 2026.

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