Web Application Testing
anthropics/skills
Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.
Saves a user journey driven through the app as a deterministic regression check that replays with no model and no test code, using Reticle.
Install Reticle Flow Replay
$ npx skills add reticlehq/reticle --skill replay-user-flows -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install reticlehq/reticle replay-user-flows --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/reticlehq/reticle.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/replay-user-flows .claude/skills/replay-user-flows && rm -rf skills-srcUse ~/.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/
Install the "replay-user-flows" agent skill from https://github.com/reticlehq/reticle/tree/main/skills/replay-user-flows into .claude/skills/replay-user-flows/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "replay-user-flows", 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 install https://github.com/reticlehq/reticle/tree/main/skills/replay-user-flowsType 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.
$ npx skills add reticlehq/reticle --skill replay-user-flows -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install reticlehq/reticle replay-user-flows --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/reticlehq/reticle.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/replay-user-flows .agents/skills/replay-user-flows && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "replay-user-flows" agent skill from https://github.com/reticlehq/reticle/tree/main/skills/replay-user-flows into .agents/skills/replay-user-flows/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "replay-user-flows", 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.
$ npx skills add reticlehq/reticle --skill replay-user-flows -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install reticlehq/reticle replay-user-flows --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/reticlehq/reticle.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/replay-user-flows .cursor/skills/replay-user-flows && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "replay-user-flows" agent skill from https://github.com/reticlehq/reticle/tree/main/skills/replay-user-flows into .cursor/skills/replay-user-flows/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "replay-user-flows", 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 https://github.com/reticlehq/reticle.git --path skills/replay-user-flows--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add reticlehq/reticle --skill replay-user-flows -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install reticlehq/reticle replay-user-flows --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/reticlehq/reticle.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/replay-user-flows .gemini/skills/replay-user-flows && rm -rf skills-srcUse ~/.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/
Install the "replay-user-flows" agent skill from https://github.com/reticlehq/reticle/tree/main/skills/replay-user-flows into .gemini/skills/replay-user-flows/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "replay-user-flows", 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.
$ gh skill install reticlehq/reticle replay-user-flowsInstalls 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).
$ npx skills add reticlehq/reticle --skill replay-user-flows -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/reticlehq/reticle.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/replay-user-flows .github/skills/replay-user-flows && rm -rf skills-srcUse ~/.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/
Install the "replay-user-flows" agent skill from https://github.com/reticlehq/reticle/tree/main/skills/replay-user-flows into .github/skills/replay-user-flows/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "replay-user-flows", 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.
$ npx skills add reticlehq/reticle --skill replay-user-flows -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install reticlehq/reticle replay-user-flows --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/reticlehq/reticle.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/replay-user-flows .opencode/skills/replay-user-flows && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "replay-user-flows" agent skill from https://github.com/reticlehq/reticle/tree/main/skills/replay-user-flows into .opencode/skills/replay-user-flows/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "replay-user-flows", 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
replay-user-flows- GitHub stars
- 1.2k
- Token cost
- ~1.5k tokens
- SKILL.md length
- 661 words
- Files
- 1
- Skills in repo
- 19
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Saves a user journey driven through the app as a deterministic regression check that replays with no model and no test code, using Reticle.
- Driving the same flow by hand twice and wanting it saved as a check
- SKILL.md covers Record, Replay, Re-verify the whole suite… and When NOT to record, plus 1 more section
- Calls curl and npx; reaches docs.reticle.sh
- Proving a refactor against every existing user journey
What it does
Exploring an app to find a journey is the costly part, so Reticle saves it once and replays it afterwards. A drive is saved automatically as a flow under `.reticle/flows/` when the session ends, and you commit it so any agent on the repo can replay it. A step only keeps a consequence if you declared one, which means driving the golden path with `reticle_act_and_wait` and a named signal; a bare `reticle_act` records a click with nothing to prove.
You can annotate the business outcome with intent and success-state notes, and no `data-testid` is needed first, because steps without one are anchored on component and source location. `reticle_verify` with the changed files replays the flows that cover them, and `reticle_flow_replay` runs one named flow through `reticle_run`. Reticle must be wired into the project first, with `npx @reticlehq/server@latest init` and the `install-and-verify` skill.
When your agent uses it
- Driving the same flow by hand twice and wanting it saved as a check
- Proving a refactor against every existing user journey
- Getting regression coverage without writing a test suite by hand
Example prompts
- “Record the create-task flow with a success signal so we can replay it after refactors.”
- “Replay the flows covering src/tasks/TaskList.tsx and tell me if anything regressed.”
- “Save this checkout journey as a regression check without writing test code.”
Requirements
- Reticle wired into the project, installed with `npx @reticlehq/server@latest init`
What it can do on your machine
Read from SKILL.md and the folder at commit 178e5c0. 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:
curlnpx
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
docs.reticle.sh
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
Reticle Flow Replay loads about 1.5k tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 661 words of instructions outside code blocks.
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 reticlehq/reticle at commit 178e5c0, republished under its Apache-2.0 licence (© reticlehq). 661 words, ~1,462 tokens.
Download SKILL.mdSave it as
.claude/skills/replay-user-flows/SKILL.md (or your agent's skills folder).- name
- replay-user-flows
- description
- Turn a user journey you just clicked through into a saved regression check that re-runs deterministically, with no model in the loop and no test code to write. Use when you have driven the same flow twice, when the user wants regression coverage without a Playwright suite, when a refactor needs proving against every existing journey, or when re-verifying by hand is costing a full drive every time.
- license
- Apache-2.0
- metadata.version
- 3.7.0
- metadata.homepage
- https://www.reticle.sh
- metadata.repository
- https://github.com/reticlehq/reticle
Record a journey once, re-verify it forever
Exploring an app to find a journey is the expensive part, and re-driving it with a model pays that cost again on every change. Reticle flows pay it once: the journey is saved with semantic anchors and replayed deterministically afterwards.
Needs Reticle wired in the project. Not there? RETICLE_INSTALL_SOURCE=npx_skill npx @reticlehq/server@latest init, then the install-and-verify skill.
Record
You do not have to ask. A drive is saved as a flow automatically when the session ends, written to .reticle/flows/. Commit it: any agent on the repo can then replay it.
What decides whether it is worth committing is how you drove it. A step keeps a consequence only when you declared one, so drive the golden path like this:
reticle_act_and_wait({ sessionId, ref, action: "click", until: { kind: "signal", name: "task:created" } })That step replays as a test. A bare reticle_act saves a click with nothing to prove, and replays green through any regression.
To name a flow deliberately rather than take the automatic one, reticle_record and reticle_flow_save do it through reticle_run { tool, args }. Neither is advertised, and neither needs to be: reticle_run is on the default surface and dispatches to any registered tool by name. RETICLE_ADVERTISE_ALL_TOOLS=1 advertises them outright instead, which suits a suite that calls by name rather than a running agent.
Annotate the business outcome, not just the clicks, so a replay proves the journey achieved something. Extended surface, like the two above:
reticle_run({ tool: "reticle_annotate", sessionId, args: { flow: "create-task", kind: "intent", text: "create a task and see it in the list" } })
reticle_run({ tool: "reticle_annotate", sessionId, args: { flow: "create-task", kind: "success-state", signal: "task:created" } })You do not need to add data-testid first. A step whose element has no testid is anchored on its component and source location automatically, and a testid-preserving refactor still replays green.
Replay
reticle_verify({ sessionId, action: "change", files: ["src/tasks/TaskList.tsx"] })That replays the flows covering those files. To replay one named flow directly, reticle_flow_replay is reached through reticle_run.
Three statuses, and the failures are legible rather than blind:
| status | means | next |
|---|---|---|
ok | every anchor resolved, every expectation held | done |
drift | an anchor missed: a renamed testid, a signal that never fired | read decision.nextAction; it names the file:line and the closest surviving anchor |
error | the flow file is missing or invalid, or a step failed at runtime | fix from the error envelope's failed step |
On drift, reticle_verify { action: "heal" } proposes the nearest-match rebind so flows do not rot. Apply it when the rename was intentional; treat it as a finding when it was not.
Show full SKILL.md (287 more words)Show less
Re-verify the whole suite after any change
reticle_verify({ sessionId, action: "flows" })
// → { status, total, passed, failed, failures: [{ flow, verdict, whatChanged, whereInSource, nextAction }] }One call, every saved flow, no model per flow. Only failures carry detail, so a green suite is cheap to check. Build → flow_verify → fix from each nextAction → repeat is the regression loop, and it is the point of recording in the first place.
Only the flows your change could have broken
On a large suite, replaying everything after a one-file edit is waste. Hand it the diff instead:
reticle_verify({ sessionId, action: "change", since: "HEAD~1" })It works out which saved flows cover the files you edited and replays only those. Give it a git ref or the file list. Use this in the inner loop and flow_verify before you ship: the narrow one is fast, the whole one is the guarantee.
Which of your flows actually prove anything
reticle_run({ tool: "reticle_domain", sessionId }) // not advertised, one hop away
// → { flowCount, coverage: { asserted, presenceOnly, assertionFree }, gaps: { declaredUntestedSignals, … } }A recorded flow that asserts nothing replays green through any regression: it proves the clicks still resolve, not that the app still works. Check this after a recording session: anything landing in assertionFree needs an annotate pass with a success-state, or it is decoration.
When NOT to record
A journey you will run once is cheaper to drive with reticle_act_and_wait and forget. Record the flows that define the product (the ones a regression in would be a bad day) and leave exploratory drives unsaved. A suite of forty half-meant flows costs more attention than it returns.
Honesty
A replay reports what happened. drift is not a pass, and healing a flow to make it green when the app genuinely broke is the one thing that makes the whole suite worthless. If the rename was not intentional, the drift is the finding: report it with the whereInSource pointer.
Full flow reference, one page: curl https://docs.reticle.sh/flows.md. Index of everything: curl https://docs.reticle.sh/llms.txt.
© reticlehq, Apache-2.0. 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 skills/replay-user-flows of reticlehq/reticle.
Open the folder on GitHubat commit 178e5c0
Compare with similar skills
Reticle Flow 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Reticle Flow Replay this skillreticlehq/reticle | 1.2k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Web Application Testinganthropics/skills | 180k | 51 repos | ~966 | Automated safety check: Pass | Apache-2.0 | |
| Write and Verify Playwright Testsappsmithorg/appsmith | 41k | — | ~2.9k | Automated safety check: Notes | Apache-2.0 | |
| playwright-cli Browser Automationgithub/gh-aw | 5.4k | 23 repos | ~2.8k | Automated safety check: Pass | MIT | |
| Cucumber and Playwright E2E Testslanggenius/dify | 158k | — | ~682 | Automated safety check: Pass | Custom licence | |
| E2E Testinglangflow-ai/langflow | 155k | — | ~3.3k | Automated safety check: Pass | MIT |
Similar skills
- Official
Write and Verify Playwright Tests
appsmithorg/appsmith
Writes a Playwright end-to-end test from a prompt, runs it against a live Appsmith deployment and retries with fixes up to three times until it passes.
- Official
playwright-cli Browser Automation
github/gh-aw
Drives a real browser from the command line with playwright-cli to open pages, interact, mock requests, save state and work with Playwright tests.
Cucumber and Playwright E2E Tests
langgenius/dify
Guides changes and reviews of the Cucumber and Playwright end-to-end suite under `e2e/`: feature files, step definitions, support code, tags, locators and assertions.
E2E Testing
langflow-ai/langflow
Write and review Playwright E2E tests for Langflow. An agent skill from langflow-ai/langflow.
Handsontable Playwright E2E Tests
handsontable/handsontable
Guides writing and changing Playwright end-to-end tests for Handsontable using page objects, data-testid hooks and deterministic waits.
More from reticlehq/reticle
All 19 skills in this repoAgentic TDD
reticlehq/reticle
Applies red-green TDD to behavior unit tests cannot reach, by stating the expected outcome against the running app with Reticle before writing the feature.
Whole-App Health Sweep
reticlehq/reticle
Sweeps a running web app by clicking every reachable control, then reports dead buttons, console errors, failed requests and mismatches between API data and the screen.
Broken UI Debugger
reticlehq/reticle
Finds why a running web app misbehaves when the console is empty and the code looks fine, by reading the click, request, store and console together.
Desktop App Driving with Reticle
reticlehq/reticle
Drives and verifies Electron or Tauri desktop apps through Reticle, which sees the renderer and the IPC calls that a browser-based testing tool cannot observe.
False Green Test Detection
reticlehq/reticle
Finds out why a passing test suite sits on top of a broken app by comparing what the running app does with what the tests claim, using Reticle.
Fix What I Pointed At
reticlehq/reticle
Picks up bugs a person flagged by pointing at elements in the running app, each mark carrying the element, their note and the source file and line, then fixes and verifies them.
Related
Categories
Questions about Reticle Flow Replay
What does Reticle Flow Replay do?
Saves a user journey driven through the app as a deterministic regression check that replays with no model and no test code, using Reticle. Exploring an app to find a journey is the costly part, so Reticle saves it once and replays it afterwards.reticle/flows/` when the session ends, and you commit it so any agent on the repo can replay it.
When should I use Reticle Flow Replay?
Reticle Flow Replay fits situations like: driving the same flow by hand twice and wanting it saved as a check; proving a refactor against every existing user journey; getting regression coverage without writing a test suite by hand.
How do I install Reticle Flow Replay in Claude Code?
Run `npx skills add reticlehq/reticle --skill replay-user-flows -a claude-code`. Or copy the skill folder (skills/replay-user-flows in reticlehq/reticle) into .claude/skills/replay-user-flows in your project. Claude Code loads it when a task matches its description.
How do I install Reticle Flow Replay in Codex?
Run `npx skills add reticlehq/reticle --skill replay-user-flows -a codex`. Or copy the skill folder (skills/replay-user-flows in reticlehq/reticle) into .agents/skills/replay-user-flows in your project. Codex loads it when a task matches its description.
Can I use Reticle Flow 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 reticlehq/reticle --skill replay-user-flows -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/replay-user-flows, .gemini/skills/replay-user-flows, .github/skills/replay-user-flows and .opencode/skills/replay-user-flows in your project.
What does Reticle Flow Replay need to run?
Going by SKILL.md and its folder, Reticle Flow Replay needs the command-line tools its instructions call (curl and npx). Our summary lists: Reticle wired into the project, installed with `npx @reticlehq/server@latest init`.
Does Reticle Flow Replay access the network?
SKILL.md names 1 domain. In commands or code: docs.reticle.sh; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Reticle Flow Replay 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 Reticle Flow Replay use?
Reticle Flow Replay is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Reticle Flow Replay use?
About 1.5k tokens (SKILL.md is roughly 5.8k 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 Reticle Flow Replay?
Skills that share tags, products or a category with Reticle Flow Replay: Web Application Testing (anthropics/skills, 180k stars), Write and Verify Playwright Tests (appsmithorg/appsmith, 41k stars), playwright-cli Browser Automation (github/gh-aw, 5.4k stars) and Cucumber and Playwright E2E Tests (langgenius/dify, 158k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Reticle Flow Replay?
reticlehq (a GitHub organization) maintains it in reticlehq/reticle, which has 1,199 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 9, 2026.
Source: reticlehq/reticle on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.