steelmorgan/vanessa-diagnostics
framework_eng/skills/tool-usage/vanessa/vanessa-diagnostics/SKILL.md
MUST use WHEN a feature scenario has failed, artifacts were not created, or you need to classify a failure after execution. Provides an algorithm for analyzing run artifacts and classifying the error type.
$ install --global
skillsauthnpx skillsauth add steelmorgan/1c-agent-based-dev-framework vanessa-diagnosticsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 13, 2026, 5:59 AM24.4s1 file scanned
SKILL.md
- name:
- vanessa-diagnostics
- description:
- MUST use WHEN a feature scenario has failed, artifacts were not created, or you need to classify a failure after execution. Provides an algorithm for analyzing run artifacts and classifying the error type.
Vanessa Automation Diagnostics
Vanessa is run through v8-runner test va (see the v8-runner skill → references/testing.md). This skill is about how to analyze a failed run.
Run Artifacts
There are two layers - do not confuse them:
| Layer | What writes it | Where it is located |
|------|-----------|-----------|
| Vanessa artifacts | the VA player itself (va-status.json, vanessa-execution.log, reports junit/junit.xml, cucumber/CucumberJson.json) | at the paths from the active tests.va / va-params profile, usually project-local (<project_root>/vanessa-tests/reports/…, .../logs/…) |
| v8-runner run artifacts | v8-runner itself (internal run logs, 1cv8c stdout/stderr, run-id metadata) | workPath/temp/<runner-id>/runs/<run-id>/ (workPath is taken from v8project.yaml) |
When a run fails, do not clean up both locations before diagnostics are complete. Read the exact Vanessa report paths from the active profile.
Monitoring Progress During a Run
For long v8-runner test va operations (usually several minutes), use the Monitor tool instead of blindly polling files:
- Start
v8-runnerin the background:Bash run_in_background: true, redirect stdout to a log file (for examplev8-runner test va 2>&1 | tee /tmp/va-stdout.log). - Subscribe to this file through the Monitor tool with the filter:
ERROR:|\\[artifact\\]|passed|Failed:- each matched line will arrive as a notification. - Stop waiting when any of the following conditions is met:
va-status.logappears in the run directory (it is created on success AND on error - unlikeva-status.json);- the
1cv8c.*vanessa-automationprocess finishes; - a line
ERROR:appears in stdout (for exampleERROR: runtime error: test run reported failures).
- Do not use
va-status.jsonas the sole exit condition. It is created only upon normal scenario completion; in the case of an early failure (step error, client crash), the file is absent and waiting for it will hang forever.
After the run completes, proceed to the diagnostic sequence below.
When to Apply
| Trigger | Action |
|---------|----------|
| va-status.json not created | Treat the run as catastrophic, go to diagnostics |
| va-status.json != 0 | Read artifacts and classify the failure |
| vanessa-execution.log contains an error | Determine the error class |
| Suspected GUI lockup | Visual diagnostics |
| The run is "green", but 0 steps executed / steps undefined/skipped | False success - classify as step_resolution_error/scenario_error |
Mandatory Diagnostic Order
- Check
va-status.json. - Check
vanessa-execution.log. - Check
event-log: first the lastError; if empty - without the level filter. - If there is a signal of a modal window / security warning -
gui-control/screenshot. - Only if that is insufficient -
tech-log-analysis.
Special-case: Security Warning
If event-log contains an entry about Security Warning for bddRunner.epf or plugins:
- Treat it as a trigger for visual inspection.
- Open the real screen via noVNC or take a screenshot (do not rely on X11 window titles).
- Only after visual confirmation, interpret a rerun.
Error Classes
| Class | When to set |
|-------|---------------|
| scenario_error | The scenario is formulated incorrectly or uses the wrong flow |
| step_resolution_error | The required step was not found or could not be resolved |
| assertion_error | The steps ran, but the result check did not match |
| test_data_error | Depends on missing / unsuitable data |
| environment_error | Problem in X11, environment, runner, or client startup |
| product_ui_error | Error in visible form behavior or UI flow |
| product_logic_error | Business logic returns the wrong result for a correct scenario |
Quick Heuristic
| Signal | Class |
|--------|-------|
| No va-status.json, GTK/X11 error | environment_error |
| Step not found | step_resolution_error |
| The form opened, expectation mismatch | assertion_error / product_ui_error |
| Error from the business module in the registration log | product_logic_error |
| Document/object not found | test_data_error |
Diagnostic Result
The agent must report: error class, main signal source, next action loop.
failure_type = test_data_error
main_signal = document not found in event log / form flow
next_action = choose another fixture or prepare stable test data
depends_on:
- framework/rules/vanessa-diagnostics-policy.mdc
- framework/rules/vanessa-security-warning.mdc
- framework/skills/tool-usage/v8-runner/SKILL.md
- framework/skills/tool-usage/diagnostics/event-log-analysis/SKILL.md
- framework/skills/tool-usage/diagnostics/tech-log-analysis/SKILL.md
- framework/skills/tool-usage/browser-ui/gui-control/SKILL.md
- framework/skills/tool-usage/browser-ui/screenshot/SKILL.md
Related Skills
steelmorgan/source-of-truth
testing
VerifiedTrustedCommunity
MUST use BEFORE making a judgment about the cause of a conflict, a test failure, or an artifact dispute. Defines the end-to-end verification method L1→L6 and the classification of the first broken link.
69SKILL.mdUpdated Jun 13, 2026
steelmorgan/skill-learning
development
VerifiedTrustedCommunity
MUST use AFTER a work cycle with ≥2 iterations (wrote → error → fixed → success). Provides the retrospective procedure and the format for recording practice/anti-patterns in references/learned-patterns.md or {project}/.context/learned-patterns.md.
69SKILL.mdUpdated Jun 13, 2026
steelmorgan/rlm-workflow
tools
VerifiedTrustedCommunity
MUST use WHEN you are writing reusable knowledge into RLM (pattern / architectural decision / stable domain fact) OR reading it before a non-trivial task/solution in the domain. Provides the breakdown of native-push vs RLM-pull, tools for writing and reading RLM, H-MEM levels, and hygiene.
69SKILL.mdUpdated Jun 13, 2026
steelmorgan/quick-fix
testing
VerifiedTrustedCommunity
MUST use WHEN the task is classified as simple (< 20 lines, 1 file, no new metadata objects, no architectural decisions). Provides a short cycle of 3 steps with a guard on the self path and mandatory verify.
69SKILL.mdUpdated Jun 13, 2026