@slamb2k/mad-skills 2.0.30 → 2.0.31

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "mad-skills",
   "description": "AI-assisted planning, development and governance tools",
-  "version": "2.0.30",
+  "version": "2.0.31",
   "author": {
     "name": "slamb2k",
     "url": "https://github.com/slamb2k"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@slamb2k/mad-skills",
-  "version": "2.0.30",
+  "version": "2.0.31",
   "description": "Claude Code skills collection — full lifecycle development tools",
   "type": "module",
   "repository": {

package/skills/manifest.json

@@ -1,5 +1,5 @@
 {
-  "generated": "2026-03-12T17:16:55.117Z",
+  "generated": "2026-03-13T00:14:06.892Z",
   "count": 10,
   "skills": [
     {
@@ -76,7 +76,7 @@
       "name": "ship",
       "directory": "ship",
       "description": "\"Ship changes through the full PR lifecycle. Use after completing feature work to commit, push, create PR, wait for checks, and merge. Handles the entire workflow: syncs with main, creates feature branch if needed, groups commits logically with semantic messages, creates detailed PR, monitors CI, fixes issues, squash merges, and cleans up. Invoke when work is ready to ship.\"",
-      "lines": 356,
+      "lines": 374,
       "hasScripts": false,
       "hasReferences": true,
       "hasAssets": false,

package/skills/ship/SKILL.md

@@ -259,15 +259,21 @@ suggest the manual PR creation command. Do NOT revert the push.
 
 ---
 
-## Stage 3: Wait for CI
+## Stage 3 + 4: CI Watch & Fix Loop
 
-Launch **Bash subagent** in the **background** (haiku — just polling):
+Run CI monitoring in the **foreground** so failures are caught and fixed
+immediately. This stage loops: watch → detect failure → fix → push → watch again.
+
+**Maximum 2 fix attempts.** If CI still fails after 2 rounds, report to user and stop.
+
+### Watch
+
+Launch **Bash subagent** (haiku — polling):
 
 ```
 Task(
   subagent_type: "Bash",
   model: "haiku",
-  run_in_background: true,
   description: "Monitor CI checks",
   prompt: <read from references/stage-prompts.md#stage-3>
 )
@@ -276,18 +282,14 @@ Task(
 Substitute `{PR_NUMBER}`, `{BRANCH}`, `{PLATFORM}`, `{AZDO_MODE}`,
 `{AZDO_ORG}`, `{AZDO_ORG_URL}`, `{AZDO_PROJECT}`, `{PAT}` into the prompt.
 
-While CI runs in the background, briefly inform the user:
-```
-CI running for PR #{pr_number}... waiting for checks.
-```
+Briefly inform the user: `⏳ Watching CI for PR #{pr_number}...`
 
-When the background task completes, read the output file and parse CHECKS_REPORT.
+Parse CHECKS_REPORT when the subagent returns.
 
----
+### Fix (if needed)
 
-## Stage 4: Fix Failing Checks (if needed)
-
-If CHECKS_REPORT shows failures, launch **general-purpose subagent**:
+If CHECKS_REPORT shows `some_failed`, **immediately** launch a fix subagent —
+do not wait, do not ask the user:
 
 ```
 Task(
@@ -300,8 +302,24 @@ Task(
 Substitute `{PR_NUMBER}`, `{BRANCH}`, `{FAILING_CHECKS}`, `{PLATFORM}`,
 `{AZDO_MODE}`, `{AZDO_ORG}`, `{AZDO_ORG_URL}`, `{AZDO_PROJECT}`, `{PAT}` into the prompt.
 
-If fixed, return to Stage 3 (run CI watch again).
-If unable to fix after 2 attempts, report to user and stop.
+The fix subagent MUST commit and push before returning. Once it returns,
+**immediately loop back to Watch** to re-check CI.
+
+### Loop summary
+
+```
+attempt = 0
+while attempt < 2:
+  CHECKS = run_watch()
+  if CHECKS.status == "all_passed" or CHECKS.status == "no_checks":
+    break  → proceed to Stage 5
+  attempt += 1
+  run_fix(CHECKS.failing_checks)
+  → loop back to watch
+
+if attempt == 2 and still failing:
+  report failures to user, stop
+```
 
 ---
 

package/skills/ship/references/stage-prompts.md

@@ -147,7 +147,8 @@ SHIP_REPORT:
 **Agent:** Bash (haiku, background)
 
 ```
-Monitor PR/pipeline status checks until complete.
+Monitor PR/pipeline status checks until complete. Fail fast — stop polling the
+moment any check fails so fixes can start immediately.
 
 Limit CHECKS_REPORT to 10 lines maximum.
 
@@ -159,8 +160,8 @@ BRANCH: {BRANCH}
 
 **If PLATFORM == github:**
 
-1. **Wait for checks to complete**
-   gh pr checks {PR_NUMBER} --watch
+1. **Wait for checks — fail fast on first failure**
+   gh pr checks {PR_NUMBER} --watch --fail-fast
 
 2. **Report final status**
    gh pr checks {PR_NUMBER}
@@ -190,9 +191,9 @@ BRANCH: {BRANCH}
    ```
    If no policies exist either, report `no_checks`.
 
-2. **Wait for runs to complete — with fail-fast** (max 30 minutes, check every 30s)
+2. **Wait for runs to complete — with fail-fast** (max 30 minutes, check every 15s)
    ```
-   for i in $(seq 1 60); do
+   for i in $(seq 1 120); do
      # Check for failures FIRST — stop immediately if any run has failed
      FAILED=$(az pipelines runs list --branch "$BRANCH" --top 5 \
        --org "{AZDO_ORG_URL}" --project "{AZDO_PROJECT}" \
@@ -207,7 +208,7 @@ BRANCH: {BRANCH}
        --org "{AZDO_ORG_URL}" --project "{AZDO_PROJECT}" \
        --query "[?status=='inProgress'] | length(@)" -o tsv 2>/dev/null)
      if [ "$IN_PROGRESS" = "0" ] || [ -z "$IN_PROGRESS" ]; then break; fi
-     sleep 30
+     sleep 15
    done
    ```
 
@@ -259,9 +260,9 @@ BRANCH: {BRANCH}
    ```
    If no evaluations exist either, report `no_checks`.
 
-2. **Wait for runs to complete — with fail-fast** (max 30 minutes, check every 30s)
+2. **Wait for runs to complete — with fail-fast** (max 30 minutes, check every 15s)
    ```
-   for i in $(seq 1 60); do
+   for i in $(seq 1 120); do
      BUILDS_JSON=$(curl -s -H "$AUTH" "$BUILDS_URL")
 
      # Check for failures FIRST
@@ -274,7 +275,7 @@ BRANCH: {BRANCH}
      # Check if anything still running
      IN_PROGRESS=$(echo "$BUILDS_JSON" | jq '[.value[] | select(.status=="inProgress")] | length')
      if [ "$IN_PROGRESS" = "0" ]; then break; fi
-     sleep 30
+     sleep 15
    done
    ```