Skip to content
cccskills
FreePublished on GitHubEnglish overview

browser-replay

Replay recorded browser actions on the original or an alternative URL to check UI changes or reproduce bugs. When a page element cannot be found, the skill searches for a similar target and records how many steps succeeded.

OriginalShow the original description

Replay a recorded session trajectory against the same URL or a mutated variant; uses browser-selectors embedding similarity to recover from DOM drift

ruvnet/ruflo
AI rating70/ 100See how to install

Good for

  • Checking UI flows after a deployment
  • Reproducing a bug from a recorded session
  • Preparing repeated runs for screenshot comparison
  • Replaying a parent session before modifying a fork

Overview

What it does

browser-replay loads recorded browser actions and repeats clicks, text entry, and other steps in order. It can run on the original URL or another URL you specify. If a page structure change prevents it from finding a target, it searches browser-selectors for a similar candidate and retries once. It records a new action history and writes the proportion of successful steps and the resulting verdict to findings.md.

When it helps

Use it to check whether the same UI flow still works after a deployment, or to reproduce a bug from a previous session. It also helps repeat the same actions for screenshot comparisons or check the parent session before making changes to a fork.

Example requests

  • “Replay this session and summarize the success rate.”
  • “Try the recorded actions on a different URL.”
  • “Run a regression test with the tolerance set to 0.9.”

Notes

The skill requires a recorded session, Ruflo browser MCP tools, ruvector, and @claude-flow/cli. The default verdict threshold is 0.85. Network timing and changing content can cause false failures. Major changes to page structure may require recording the session again.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Objective evaluation

AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.

Clear instructionsIs it clear when to use it and what it does?
AGoodIt specifies replaying recorded actions for regression testing and bug reproduction.
Concrete stepsAre steps, inputs, outputs, and examples spelled out?
AGoodSeven steps specify the input format, retry count, success-rate calculation, and findings destination.
SafetyAre sending data, deleting files, and running commands disclosed?
CCheck firstIt replays recorded clicks, input, and browser_eval without individual confirmation.
Easy setupDoes it need few tools or API keys, and are they documented?
BPartly lackingIt specifies a ruvector version and CLI examples, but lacks setup steps for browser MCP tools and the recording environment.

The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 21, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Tell us which point is wrong and why. No login needed. We will check it against the SKILL.md, redo the evaluation, and show the result here.

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

Files included (1)

  • SKILL.md3.3 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Browser Replay

Re-drive a recorded session trajectory. Used for regression testing, deterministic re-runs, and as the verification path that browser-record plus browser-selectors actually produces something replayable.

This skill is the load-bearing assumption of the v0.2.0 architecture. ADR-0001 Verification §4 requires ≥80% replay success across 10 distinct sites of varying drift profiles before the proposal moves from Proposed → Accepted. If you find replay unreliable, capture the failure modes in findings.md and report them up the ADR.

When to use

  • Regression-testing a UI flow after a deploy.
  • Reproducing a bug captured in a prior session.
  • Comparing two runs of the same flow for browser-screenshot-diff.
  • Forking a session (/ruflo-browser fork) and replaying the parent before mutating.

Steps

  1. Locate the source session: 
    npx -y ruvector@0.2.27 rvf status <session-id>.rvf
  2. Load the trajectory: 
    Read .../trajectory.ndjson
    Each line is {ts, action, args, selector, result}.
  3. Open a fresh browser via mcp__plugin_ruflo-core_ruflo__browser_open (target URL = original or --url override).
  4. For each trajectory step, dispatch the matching MCP tool (browser_click, browser_fill, browser_eval, etc.) with the recorded args.
  5. On selector miss, do not fail immediately — query the browser-selectors namespace for an embedding-similar selector for the same <host>:<intent> and retry once: 
    npx -y @claude-flow/cli@latest memory search --namespace browser-selectors \
  --query "<host> <intent>" --limit 5
  6. Record a new trajectory for the replay run (allocate a fresh RVF container, lineage-tracked via rvf derive).
  7. Verdict: tally matched-step / total-step ratio. Default tolerance threshold is 0.85 (configurable via --tolerance). Verdict goes into findings.md.

Caveats

  • Browserbase explicitly does not offer replay (rrweb session replay was deprecated). We're betting on selector-embedding recovery; expect noise on heavily drifted sites.
  • Network nondeterminism (timing, content variation) can produce false-fail verdicts. Use --mutate to inject expected variation or pin to a fixture.
  • For visual diff, chain into browser-screenshot-diff against the parent session id.
  • If selector recovery requires more than one retry per step, log it. That's the signal that the site needs a re-record, not a replay.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

add-model-descriptions

FreeSummaryAI rating 80

Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.

  • Adding newly available router models to chat-ui
  • Writing concise descriptions of model capabilities
  • Updating production and development model entries together
ruvnet/ruflo77.9KUpdated Oct 20, 2026

adr-create

FreeSummaryAI rating 80

Create an Architecture Decision Record, a document for recording important design choices, with the next sequential number. It generates a Markdown template, registers the record in AgentDB, and links related decisions found through search.

  • Record the reasoning behind adopting a technology
  • Start an ADR for an API or data model change
  • Document an infrastructure decision
ruvnet/ruflo77.9KUpdated Oct 20, 2026

adr-index

FreeSummary

Build a searchable index and relationship graph from ADRs, records of architectural decisions. Import two supported document formats, refresh existing metadata without duplicate relationships, and review summaries of statuses, missing references, and inconsistencies.

  • Index ADRs imported from another project
  • Refresh a graph that differs from files on disk
  • Set up ADR tracking in an existing codebase
ruvnet/ruflo77.9KUpdated Oct 20, 2026

adr-reindex

FreeSummaryAI rating 70

Rebuild the index of ADRs, records of architectural decisions, after files or relationship lines are deleted. It clears stored records and relationships, indexes the files still present, and checks that the final record count matches.

  • Rebuild the index after deleting an ADR file
  • Remove stale relationships after editing an ADR
  • Reconcile the ADR index on a schedule
ruvnet/ruflo77.9KUpdated Oct 20, 2026

adr-review

FreeSummaryAI rating 80

Review code changes against accepted Architecture Decision Records, documents that capture agreed design choices. Report violations, outdated references, compliant changes, and areas without ADR coverage, then suggest code fixes or a new decision record where appropriate.

  • Check a pull request before merging
  • Review major code changes against agreed design decisions
  • Find references to superseded ADRs
ruvnet/ruflo77.9KUpdated Oct 20, 2026

adr-verify

FreeSummaryAI rating 90

Check saved architecture decision records (ADRs) for broken references, circular replacement relationships, and inconsistent statuses. Use the results to verify imported records or stop a CI check when selected integrity rules fail.

  • Checking ADR integrity after import
  • Blocking CI when ADR issues are found
  • Reviewing ADR data before a release
ruvnet/ruflo77.9KUpdated Oct 20, 2026

See all skills by ruvnet

Report a problem with this skill