Validate that "$3" is an existing directory; fail if it is not. Do NOT create the directory.
Extract {BUILD_NUMBER} from "$1" by matching a 10–20 digit sequence; fail if none is found.
Use the extracted number as {BUILD_NUMBER}.
Use curl to download the file build-log.txt under "$1". Only allow HTTPS URLs (reject HTTP).
When fetching, use: curl -fsSL --max-time 20 --retry 3 --retry-connrefused --proto '=https' --max-filesize 100M "${1}/build-log.txt".
The build-log.txt file contains e2e failures, store the artifacts related to failure "$2" under directory specified by "$3" to determine a possible root cause for the failure.
Use the "gcloud storage" command to fetch given artifacts under "$3" and make sure to use {BUILD_NUMBER} in URLs.
Provide evidence for the failure.
Try to find additional evidence. For example, in logs and events.
Do not delete downloaded artifacts during the cleanup phase.
1---2name: e2e-analyze3description: Analyze test errors4---56# General instructions78- Validate that "$3" is an existing directory; fail if it is not. Do NOT create the directory.9- Extract {BUILD_NUMBER} from "$1" by matching a 10–20 digit sequence; fail if none is found.10- Use the extracted number as {BUILD_NUMBER}.11- Use curl to download the file build-log.txt under "$1". Only allow HTTPS URLs (reject HTTP).12- When fetching, use: `curl -fsSL --max-time 20 --retry 3 --retry-connrefused --proto '=https' --max-filesize 100M "${1}/build-log.txt"`.13- The build-log.txt file contains e2e failures, store the artifacts related to failure "$2" under directory specified by "$3" to determine a possible root cause for the failure.14- Use the "gcloud storage" command to fetch given artifacts under "$3" and make sure to use {BUILD_NUMBER} in URLs.15- Provide evidence for the failure.16- Try to find additional evidence. For example, in logs and events.17- Do not delete downloaded artifacts during the cleanup phase.1819# Output format2021- The output should be formatted as:22 ```text23 Error: {Error message here}24 Summary: {Failure analysis here}25 Evidence: {Evidence here}26 Additional evidence: {Additional evidence here}27 ```
Run npx get-skill add openshift/e2e-analyze in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Analyze test errors It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
openshift (@openshift) published this skill. Their other Agent Skills are listed on their SkillMD profile.