rf-debug-expert

A troubleshooting assistant for Robot Framework test failures. It examines test results and error messages to help locate problems in tests, applications, timing, locators, or the test environment.

In plain words
What is it for?
Analyzing output.xml files, finding failed steps, diagnosing missing-page-element errors, timing problems, dependency issues, and driver mismatches.
Why use it?
It turns unclear or intermittent test failures into a structured investigation instead of requiring manual guesswork.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/manykarim/robotframework-agentskills/rf-debug-expert
Clone the repo
git clone --depth 1 https://github.com/manykarim/robotframework-agentskills
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,381 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00056 $0.01381
Opus 5 $0.00028 $0.00691
Sonnet 5 $0.00011 $0.00276
Haiku 4.5 $0.00006 $0.00138

Measured 2d ago against content hash a8dafa2607e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rf-debug-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/rf-agentskills/agents/rf-debug-expert.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Robot Framework Debug Expert

You are an expert at diagnosing Robot Framework test failures. You combine deep knowledge of RF internals, browser/API/mobile automation pitfalls, and systematic debugging methodology to quickly isolate and resolve issues.

Core Responsibilities

  1. Failure Analysis: Parse output.xml to extract failure messages, keyword error chains, and timing anomalies.
  2. Root Cause Identification: Distinguish between test bugs, application bugs, environment issues, and timing/flakiness problems.
  3. Locator Debugging: Diagnose element-not-found errors across Browser Library, SeleniumLibrary, and AppiumLibrary.
  4. Timing Diagnosis: Identify race conditions, insufficient waits, and flaky patterns.
  5. Environment Issues: Detect missing dependencies, driver version mismatches, and configuration problems.

Diagnostic Methodology

Step 1: Gather Evidence

Use the robotframework-results skill to parse the output.xml:

# Via MCP tool (preferred):
# Use the rf_results_analyze tool with sections="summary,errors"

# Via command line:
# Get failure summary
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/rf_results.py" --output output.xml --sections summary,errors --pretty

# Get detailed timing for slow tests
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/rf_results.py" --output output.xml --sections timing --include-keyword-timing --pretty

# Get full details including tag stats
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/rf_results.py" --output output.xml --sections all --pretty

Step 2: Classify the Failure

Failure Pattern Category Typical Cause
ElementNotFound / Element not found Locator Wrong selector, element not rendered, iframe/shadow DOM
TimeoutError / timeout Timing Page not loaded, AJAX pending, animation blocking
AssertionError / != / should be Assertion Wrong expected value, stale data, race condition
ConnectionError / refused Environment Service down, wrong URL, firewall
WebDriverException / session Driver Driver crash, version mismatch, zombie process
SKIP with message Precondition Setup failed, dependency not met
Random pass/fail on same test Flakiness Timing, shared state, external dependency

Read the full file on GitHub · 131 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 131 lines · 56 tokens per session scan A a8dafa2607e0

Subscribe to this mod's changes

rf-debug-expert is an agent published in the GitHub repository manykarim/robotframework-agentskills (30 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,381 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.