Menu
Regenerate the CI Doctor HTML report from existing data
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | microshift-ci:doctor-refresh |
| argument-hint | <release1,release2,...> |
| description | Regenerate the CI Doctor HTML report from existing data |
| user-invocable | true |
| allowed-tools | Bash, Read, Glob |
/microshift-ci:doctor-refresh <release1,release2,...>
Regenerates the CI Doctor HTML report from existing data. Use this after /microshift-ci:create-bugs --create to update the report with newly created bugs.
This is a lightweight operation: it does not re-analyze jobs, re-aggregate summaries, or re-query JIRA. It reads the existing bug mapping files (which include newly created bugs via the create-bugs Step 4c update) and regenerates the HTML.
<ARGUMENTS> (required): Comma-separated list of release versions (e.g., 4.19,4.20,4.21,4.22)Compute once at the start by running date +%y%m%d and substituting into the path below. In all commands, replace <WORKDIR> with the computed path.
/tmp/microshift-ci-claude-workdir.<YYMMDD>
Compute today's <WORKDIR> by running date +%y%m%d and substituting into /tmp/microshift-ci-claude-workdir.<YYMMDD>.
Verify the directory exists. If it does not:
Error: no workdir found at <WORKDIR>
Run the full doctor workflow first: /microshift-ci:doctor <releases>
Parse <ARGUMENTS> into a list of release versions.
Check for rebase PR sources in the workdir by looking for bugs/bug-candidates-rebase-release-*.json files. Extract the source identifiers (e.g., rebase-release-4.22).
Verify that <WORKDIR>/bugs/bug-matches-<source>.json exists for each release version and each rebase PR source.
If any mapping files are missing, report which ones are missing and show an error:
Error: bug mapping files missing for: <sources>
Run the full create-bugs workflow first: /microshift-ci:create-bugs <sources> --create
Continue to Step 3 anyway — the HTML report will be generated with whatever data is available.
Do NOT delete bug mapping files. Do NOT launch create-bugs agents. The mapping files are produced by the preceding /microshift-ci:create-bugs session and include newly created bugs (via Step 4c of the create-bugs skill).
Read <WORKDIR>/close-stale-bugs/closed-bugs.json. If the file does not exist, skip this step — do not pass --ignore in Step 4. If the file exists but fails to parse as valid JSON, or the parsed object does not contain an array field named closed, log a warning and proceed as if the file were absent (do not set IGNORE_KEYS, do not pass --ignore in Step 4). If the closed array is present and non-empty, join the keys with commas to form an IGNORE_KEYS string (e.g., USHIFT-1234,USHIFT-5678).
Run the refresh script:
bash plugins/microshift-ci/scripts/doctor.sh refresh --component microshift --workdir <WORKDIR> [--ignore <IGNORE_KEYS>] <ARGUMENTS>
Include --ignore <IGNORE_KEYS> only if Step 3 produced a non-empty key list.
Display the path to the regenerated HTML report.
/microshift-ci:doctor-refresh 4.19,4.20,4.21,4.22
/microshift-ci:doctor-refresh 4.22
/microshift-ci:doctor run/microshift-ci:create-bugs run/microshift-ci:create-bugs runSurface your daily task list — QA-ready tickets, sprint backlog, carry-over items, open PRs, RHEL verification queue, and quarterly reminders. Use at the start of your day to see what needs attention.
Show detailed info about a specific TODO task — its tracked links, notes, and live Jira/PR status. Use when the user asks about a task, wants context to resume work on it, or asks what's needed to finish a ticket. Not for listing all tasks (read the TODO file directly or use edge-ic:sprint-status for sprint-wide views)
End-of-week automation - review active work and prepare next week's TODO
Run the full Prow CI release testing workflow — create PR, trigger jobs, check status, merge PR, download and upload artifacts
Generate interactive PCP performance dashboard from a Prow job URL
Download Prow job artifacts, identify root cause of failure, and produce a structured error report