openshift-eng · pmtk · Aug 3, 2026
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
@@ -58,7 +58,7 @@
       "name": "lvms-ci",
       "source": "./plugins/lvms-ci",
       "description": "LVMS CI Automation",
-      "version": "1.3.2"
+      "version": "1.4.0"
     },
     {
       "name": "mcp-atlassian",
@@ -70,7 +70,7 @@
       "name": "microshift-ci",
       "source": "./plugins/microshift-ci",
       "description": "MicroShift CI Automation",
-      "version": "1.5.4"
+      "version": "1.6.0"
     },
     {
       "name": "microshift-dev",

diff --git a/plugins/lvms-ci/.claude-plugin/plugin.json b/plugins/lvms-ci/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
 {
   "name": "lvms-ci",
   "description": "LVMS CI Automation",
-  "version": "1.3.2",
+  "version": "1.4.0",
   "author": {
     "name": "knarra"
   },

diff --git a/plugins/lvms-ci/skills/doctor/SKILL.md b/plugins/lvms-ci/skills/doctor/SKILL.md
@@ -21,6 +21,7 @@ Accepts a comma-separated list of release versions (or `main`), runs analysis fo
 
 ## Arguments
 
+- `--prepared` (optional): Artifacts have already been collected by an external script. When set, skip Step 1. Read the prepare summary from `<WORKDIR>/prepare-summary.json` instead.
 - `<ARGUMENTS>` (required): Comma-separated list of release versions (e.g., `main` or `4.20,4.21,4.22,main`)
 
 ## Work Directory
@@ -37,20 +38,23 @@ Compute once at the start by running `date +%y%m%d` and substituting into the pa
 
 **Goal**: Deterministically collect all failed jobs and download their artifacts before any LLM analysis.
 
-**Actions**:
-
 1. Determine today's `<WORKDIR>` by running `date +%y%m%d` and substituting into `/tmp/lvm-operator-ci-claude-workdir.<YYMMDD>`. Use this value in all subsequent commands.
-2. Run the prepare script:
+
+**If `--prepared` was passed**: the prepare script was already run externally. Read the prepare summary using `Read <WORKDIR>/prepare-summary.json`. Parse the JSON to get the workdir, release info (job counts, file paths), and PR info. Then skip to Step 2.
+
+**Otherwise** run the prepare script:
+
+1. Run:
 
    ```text
    bash plugins/lvms-ci/scripts/doctor.sh prepare --component lvm-operator --workdir <WORKDIR> <ARGUMENTS> --pull-requests
    ```
 
-3. The script deterministically:
+2. The script deterministically:
    - For each release: fetches failed periodic jobs, downloads artifacts, writes `<WORKDIR>/jobs/release-<version>-jobs.json`
    - For PRs: fetches PRs with failures, downloads artifacts, writes `<WORKDIR>/jobs/prs-jobs.json` and `<WORKDIR>/jobs/prs-status.json`
    - Outputs a JSON summary listing all releases, job counts, and file paths
-4. Read the JSON output to know which releases have jobs to analyze and how many
+3. Read the JSON output to know which releases have jobs to analyze and how many
 
 **Job JSON field names** (use these exactly — do NOT guess alternatives like `job_name`):
 

diff --git a/plugins/microshift-ci/.claude-plugin/plugin.json b/plugins/microshift-ci/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
 {
   "name": "microshift-ci",
   "description": "MicroShift CI Automation",
-  "version": "1.5.4",
+  "version": "1.6.0",
   "author": {
     "name": "ggiguash"
   },

diff --git a/plugins/microshift-ci/skills/doctor/SKILL.md b/plugins/microshift-ci/skills/doctor/SKILL.md
@@ -20,6 +20,7 @@ Accepts a comma-separated list of MicroShift release versions, runs analysis for
 
 ## Arguments
 
+- `--prepared` (optional): Artifacts and graphs have already been collected by an external script. When set, skip Steps 1 and 1b. Read the prepare summary from `<WORKDIR>/prepare-summary.json` instead.
 - `<ARGUMENTS>` (required): Comma-separated list of release versions (e.g., `4.19,4.20,4.21,4.22`)
 
 ## Work Directory
@@ -36,20 +37,23 @@ Compute once at the start by running `date +%y%m%d` and substituting into the pa
 
 **Goal**: Deterministically collect all failed jobs and download their artifacts before any LLM analysis.
 
-**Actions**:
-
 1. Determine today's `<WORKDIR>` by running `date +%y%m%d` and substituting into `/tmp/microshift-ci-claude-workdir.<YYMMDD>`. Use this value in all subsequent commands.
-2. Run the prepare script:
+
+**If `--prepared` was passed**: the prepare script was already run externally. Read the prepare summary using `Read <WORKDIR>/prepare-summary.json`. Parse the JSON to get the workdir, release info (job counts, file paths), PR info, and source checkout paths. Then skip to Step 2.
+
+**Otherwise** run the prepare script:
+
+1. Run:
 
    ```text
    bash plugins/microshift-ci/scripts/doctor.sh prepare --component microshift --workdir <WORKDIR> <ARGUMENTS> --pull-requests --repo openshift/microshift
    ```
 
-3. The script deterministically:
+2. The script deterministically:
    - For each release: fetches failed periodic jobs, downloads artifacts, writes `<WORKDIR>/jobs/release-<version>-jobs.json`
    - For rebase PRs: fetches PRs with failures, downloads artifacts, writes `<WORKDIR>/jobs/prs-jobs.json` and `<WORKDIR>/jobs/prs-status.json`
    - Outputs a JSON summary listing all releases, job counts, and file paths
-4. Read the JSON output to know which releases have jobs to analyze and how many
+3. Read the JSON output to know which releases have jobs to analyze and how many
 
 **Job JSON field names** (use these exactly — do NOT guess alternatives like `job_name`):
 
@@ -68,6 +72,10 @@ Compute once at the start by running `date +%y%m%d` and substituting into the pa
 
 ### Step 1b: Generate PCP Performance Graphs
 
+**If `--prepared` was passed**: skip this step entirely (graphs were already generated externally). Proceed to Step 2.
+
+**Otherwise**:
+
 **Goal**: Generate performance graphs from PCP archives for all jobs that have pmlogs.
 
 **Actions**: