@kennethsolomon/shipkit 3.10.0 → 3.10.2

package/skills/sk:start/SKILL.md

@@ -30,10 +30,10 @@ Read the task description from arguments. Scan for signal keywords to determine
 
 | Signal Keywords | Detected Flow |
 |----------------|---------------|
-| bug, fix, broken, error, regression, failing, crash, wrong | `debug` (11 steps) |
-| urgent, prod down, hotfix, emergency, critical, production, incident | `hotfix` (11 steps) |
-| config, bump, typo, copy, rename, dependency, upgrade, version, docs | `fast-track` (10 steps) |
-| *(default — no special signals)* | `feature` (21 steps) |
+| bug, fix, broken, error, regression, failing, crash, wrong | `debug` (7 steps) |
+| urgent, prod down, hotfix, emergency, critical, production, incident | `hotfix` (6 steps) |
+| config, bump, typo, copy, rename, dependency, upgrade, version, docs | `fast-track` (5 steps) |
+| *(default — no special signals)* | `feature` (8 steps) |
 
 **Scope detection:**
 
@@ -60,7 +60,7 @@ Present the classification and recommendation:
 ```
 Detected: [Full-stack feature / Backend bug fix / Frontend hotfix / Small config change / etc.]
 Recommended:
-  Flow:   [feature (21 steps) / debug (11 steps) / hotfix (11 steps) / fast-track (10 steps)]
+  Flow:   [feature (8 steps) / debug (7 steps) / hotfix (6 steps) / fast-track (5 steps)]
   Mode:   [autopilot / manual]
   Agents: [team (backend + frontend + QA) / solo]
 
@@ -84,12 +84,10 @@ Wait for user response:
 
 ### Step 3 — Route (enters the chosen flow)
 
-1. Reset `tasks/workflow-status.md`:
-   - Set all steps to `not yet`
-   - Add metadata to the tracker header:
-     ```
-     > Mode: [autopilot/manual] | Agents: [team/solo] | Flow: [feature/debug/hotfix/fast-track]
-     ```
+1. Log the routing decision to terminal:
+   ```
+   Mode: [autopilot/manual] | Agents: [team/solo] | Flow: [feature/debug/hotfix/fast-track]
+   ```
 
 2. Dispatch to the chosen flow:
 

package/skills/sk:test/SKILL.md

@@ -126,12 +126,12 @@ Sub-agent 3: [FE command]
 - Read the failure output carefully — identify the root cause
 - Fix the failing **implementation code** or test setup, not the test assertions (tests define expected behavior)
 - Do NOT skip, mark incomplete, or delete failing tests
-- Auto-commit with message `fix(test): resolve failing tests` — do NOT ask the user
 - Re-run the failing suite
 - Loop until all pass
-- Fix the implementation and auto-commit. If the fix is a logic change (new behavior, changed contract), update the relevant tests to reflect the new behavior before committing.
+- If the fix is a logic change (new behavior, changed contract), update the relevant tests to reflect the new behavior.
+- Once all tests pass, make ONE squash commit: `fix(test): resolve failing tests` — do NOT ask the user
 
-> Gates own their commits — the fix-commit-rerun loop is fully internal. No manual commit step needed after this gate.
+> Squash gate commits — collect all fixes for the pass, then one commit. Do not commit after each individual fix.
 
 ### 5. Verify Coverage
 
@@ -184,8 +184,8 @@ Read `.shipkit/config.json` from the project root if it exists.
 
 | Profile | Model |
 |---------|-------|
-| `full-sail` | sonnet |
-| `quality` | sonnet |
+| `full-sail` | opus (inherit) |
+| `quality` | opus (inherit) |
 | `balanced` | haiku |
 | `budget` | haiku |
 

package/skills/sk:setup-claude/templates/tasks/workflow-status.md.template

@@ -1,28 +0,0 @@
-# Workflow Status
-
-> Tracks progress through the development workflow. Reset this file when starting a new feature, bug fix, or task.
-> Updated automatically after every slash command. Do not edit manually.
-
-| # | Step | Status | Notes |
-|---|------|--------|-------|
-| 1 | Read Todo | >> next << | |
-| 2 | Read Lessons | not yet | |
-| 3 | Explore (`/sk:brainstorm`) | not yet | |
-| 4 | Design (`/sk:frontend-design` or `/sk:api-design`) | not yet | optional |
-| 5 | Accessibility (`/sk:accessibility`) | not yet | optional |
-| 6 | Plan (`/sk:write-plan`) | not yet | |
-| 7 | Branch (`/sk:branch`) | not yet | |
-| 8 | Migrate (`/sk:schema-migrate`) | not yet | optional |
-| 9 | Write Tests (`/sk:write-tests`) | not yet | |
-| 10 | Implement (`/sk:execute-plan`) | not yet | |
-| 11 | Commit (`/sk:smart-commit`) | not yet | |
-| 12 | **Lint + Dep Audit** (`/sk:lint`) | not yet | HARD GATE — loop until clean, gates own their commits |
-| 13 | **Verify Tests** (`/sk:test`) | not yet | HARD GATE — 100% coverage, gates own their commits |
-| 14 | **Security** (`/sk:security-check`) | not yet | HARD GATE — 0 issues, gates own their commits |
-| 15 | Performance (`/sk:perf`) | not yet | optional gate, gates own their commits |
-| 16 | **Review + Simplify** (`/sk:review`) | not yet | HARD GATE — 0 issues, gates own their commits |
-| 17 | **E2E** (`/sk:e2e`) | not yet | HARD GATE — all E2E scenarios must pass, gates own their commits |
-| 18 | Update (`/sk:update-task`) | not yet | |
-| 19 | Finalize (`/sk:finish-feature`) | not yet | |
-| 20 | Sync Features (`/sk:features`) | not yet | required — sync feature specs after ship |
-| 21 | Release (`/sk:release`) | not yet | optional |