@kennethsolomon/shipkit 3.0.7 → 3.2.0

package/skills/sk:setup-claude/templates/commands/finish-feature.md.template

@@ -2,11 +2,11 @@
 
 # Finish Feature Command
 
-**Workflow:** Read → Explore → Design → Accessibility → Plan → Branch → Migrate → Write Tests → Implement → Lint → Verify Tests → Security → Performance → Review → **Finalize** → Release
+**Workflow:** Read → Explore → Design → Accessibility → Plan → Branch → Migrate → Write Tests → Implement → Lint → Verify Tests → Security → Performance → Review → E2E Tests → **Finish** → Sync Features
 
 Finalize a feature/bug-fix branch: changelog, arch log, security gate, verification, and PR creation.
 
-This is the **last step before `/release`**. It auto-commits documentation changes (changelog, arch log) so you don't need to loop back to `/commit` for docs-only work.
+This is the **last step before `/sk:release`**. It auto-commits documentation changes (changelog, arch log) so you don't need to loop back to `/sk:smart-commit` for docs-only work.
 
 ## Before You Start
 
@@ -16,7 +16,7 @@ before marking the feature done. This is the last gate before merge — catch re
 mistakes here rather than in review.
 
 If `tasks/security-findings.md` exists, read it. Check that any Critical or High
-severity findings from the most recent `/security-check` audit have been addressed.
+severity findings from the most recent `/sk:security-check` audit have been addressed.
 If unresolved Critical/High findings remain, warn the user before proceeding.
 
 ## Steps
@@ -69,7 +69,7 @@ If unresolved Critical/High findings remain, warn the user before proceeding.
         - Migration/Compatibility: Any breaking changes?
       - Verify the auto-filled sections (Summary, Type, What Changed, Impact)
 
-   c) **Auto-commit the arch log** (no need to go back to `/commit`):
+   c) **Auto-commit the arch log** (no need to go back to `/sk:smart-commit`):
       ```bash
       git add .claude/docs/architectural_change_log/
       git commit -m "docs: add architectural changelog entry"
@@ -79,7 +79,7 @@ If unresolved Critical/High findings remain, warn the user before proceeding.
 
 5. **Verification** (with Test Checklist for Reviewers)
 
-   Tests should have been created during `/execute-plan`. Verify:
+   Tests should have been created during `/sk:execute-plan`. Verify:
 
    a) **Automated Tests**
       - Execute: `[TEST_COMMAND]`
@@ -108,7 +108,7 @@ If unresolved Critical/High findings remain, warn the user before proceeding.
       - Follows [LANGUAGE] conventions and style guide (see `CLAUDE.md`)
 
 6. **Security Gate**
-   - Read `tasks/security-findings.md`. If it doesn't exist or has no audit for this branch, recommend: "Run `/security-check` before creating a PR."
+   - Read `tasks/security-findings.md`. If it doesn't exist or has no audit for this branch, recommend: "Run `/sk:security-check` before creating a PR."
    - If the most recent audit has unresolved Critical or High findings, list them and ask the user to confirm they've been addressed before proceeding.
 
 7. **Create Pull Request**
@@ -126,7 +126,7 @@ If unresolved Critical/High findings remain, warn the user before proceeding.
 
    c) **Generate PR title and body:**
       - Title: Short, imperative, under 70 characters
-      - Body: Summary of changes, review findings (if any from `/review`), test status
+      - Body: Summary of changes, review findings (if any from `/sk:review`), test status
 
    d) **Create PR:**
    ```bash
@@ -152,4 +152,4 @@ EOF
 
 ## When Done
 
-> "Feature finalized and PR created! Run `/release` when ready to tag and publish."
+> "Feature finalized and PR created! Run `/sk:release` when ready to tag and publish."

package/skills/sk:setup-claude/templates/commands/security-check.md.template

@@ -6,7 +6,7 @@ description: "Audit changed code for security best practices, production-grade q
 
 # /security-check
 
-**Workflow:** Read → Explore → Design → Accessibility → Plan → Branch → Migrate → Write Tests → Implement → Lint → Verify Tests → **Security** → Performance → Review → Finalize → Release
+**Workflow:** Read → Explore → Design → Accessibility → Plan → Branch → Migrate → Write Tests → Implement → Lint → Verify Tests → **Security** → Performance → Review → E2E Tests → Finish → Sync Features
 
 Audit code for security vulnerabilities, production-grade quality, and industry gold-standard compliance.
 
@@ -164,9 +164,9 @@ Tell the user:
 > "Security audit complete. Findings saved to `tasks/security-findings.md`.
 > - **Critical:** N | **High:** N | **Medium:** N | **Low:** N
 >
-> Review the findings, then run `/finish-feature` when ready to finalize."
+> Review the findings, then run `/sk:finish-feature` when ready to finalize."
 
 If there are Critical or High findings:
-> "There are critical/high findings that should be addressed before merging. Fix them, then re-run `/security-check` to verify."
+> "There are critical/high findings that should be addressed before merging. Fix them, then re-run `/sk:security-check` to verify."
 
 **Do not auto-fix.** The user decides what to address.

package/skills/sk:setup-claude/templates/commands/write-plan.md.template

@@ -6,7 +6,7 @@ description: "Write a decision-complete plan into tasks/todo.md (no code yet)."
 
 # /write-plan
 
-**Workflow:** Read → Explore → Design → Accessibility → **Plan** → Branch → Migrate → Write Tests → Implement → Lint → Verify Tests → Security → Performance → Review → Finalize → Release
+**Workflow:** Read → Explore → Design → Accessibility → **Plan** → Branch → Migrate → Write Tests → Implement → Lint → Verify Tests → Security → Performance → Review → E2E Tests → Finish → Sync Features
 
 Create a decision-complete plan **before** writing code.
 

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

@@ -7,25 +7,28 @@
 |---|------|--------|-------|
 | 1 | Read Todo | >> next << | |
 | 2 | Read Lessons | not yet | |
-| 3 | Explore (`/brainstorm`) | not yet | |
-| 4 | Design (`/frontend-design` or `/api-design`) | not yet | optional |
-| 5 | Accessibility (`/accessibility`) | not yet | optional |
-| 6 | Plan (`/write-plan`) | not yet | |
-| 7 | Branch (`/branch`) | not yet | |
-| 8 | Migrate (`/schema-migrate`) | not yet | optional |
-| 9 | Write Tests (`/write-tests`) | not yet | |
-| 10 | Implement (`/execute-plan`) | not yet | |
-| 11 | Commit (`/smart-commit`) | not yet | |
-| 12 | **Lint** (`/lint`) | not yet | HARD GATE — loop until clean |
-| 13 | Commit (`/smart-commit`) | not yet | conditional |
-| 14 | **Verify Tests** (`/test`) | not yet | HARD GATE — 100% coverage |
-| 15 | Commit (`/smart-commit`) | not yet | conditional |
-| 16 | **Security** (`/security-check`) | not yet | HARD GATE — 0 issues |
-| 17 | Commit (`/smart-commit`) | not yet | conditional |
-| 18 | Performance (`/perf`) | not yet | optional gate |
-| 19 | Commit (`/smart-commit`) | not yet | conditional |
-| 20 | **Review** (`/review`) | not yet | HARD GATE — 0 issues |
-| 21 | Commit (`/smart-commit`) | not yet | conditional |
-| 22 | Update (`/update-task`) | not yet | |
-| 23 | Finalize (`/finish-feature`) | not yet | |
-| 24 | Release (`/release`) | not yet | optional |
+| 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 |
+| 13 | Commit (`/sk:smart-commit`) | not yet | conditional |
+| 14 | **Verify Tests** (`/sk:test`) | not yet | HARD GATE — 100% coverage |
+| 15 | Commit (`/sk:smart-commit`) | not yet | conditional |
+| 16 | **Security** (`/sk:security-check`) | not yet | HARD GATE — 0 issues |
+| 17 | Commit (`/sk:smart-commit`) | not yet | conditional |
+| 18 | Performance (`/sk:perf`) | not yet | optional gate |
+| 19 | Commit (`/sk:smart-commit`) | not yet | conditional |
+| 20 | **Review + Simplify** (`/sk:review`) | not yet | HARD GATE — 0 issues |
+| 21 | Commit (`/sk:smart-commit`) | not yet | conditional |
+| 22 | **E2E** (`/sk:e2e`) | not yet | HARD GATE — all E2E scenarios must pass |
+| 23 | Commit (`/sk:smart-commit`) | not yet | conditional — skip if E2E was clean |
+| 24 | Update (`/sk:update-task`) | not yet | |
+| 25 | Finalize (`/sk:finish-feature`) | not yet | |
+| 26 | Sync Features (`/sk:features`) | not yet | required — sync feature specs after ship |
+| 27 | Release (`/sk:release`) | not yet | optional |

package/skills/sk:setup-optimizer/SKILL.md

@@ -43,7 +43,7 @@ Before making any changes, runs a diagnostic pass on the existing CLAUDE.md:
 - **Stale content** — detects outdated info (stale model/route counts, removed dependencies, old command names like `/laravel-lint` instead of `/sk:lint`)
 - **Inconsistencies** — compares documented vs actual project state (directories, scripts, workflows)
 - **Section completeness** — flags sections that exist but are empty or have only placeholder text
-- **Outdated workflow** — checks if the workflow matches the current 24-step TDD flow with hard gates
+- **Outdated workflow** — checks if the workflow matches the current 27-step TDD flow with hard gates
 
 Reports findings before proceeding. If issues are found, they inform subsequent steps.
 
@@ -51,15 +51,15 @@ Reports findings before proceeding. If issues are found, they inform subsequent
 
 If the workflow section is outdated or missing, replace it with the latest version:
 
-**Current workflow (24 steps, TDD with hard gates):**
+**Current workflow (27 steps, TDD with hard gates):**
 ```
-Read → Explore → Design → Accessibility → Plan → Branch → Migrate → Write Tests → Implement → Lint → Verify Tests → Security → Performance → Review → Finish
+Read → Explore → Design → Accessibility → Plan → Branch → Migrate → Write Tests → Implement → Lint → Verify Tests → Security → Performance → Review → E2E Tests → Finish → Sync Features
 ```
 
 **What gets updated:**
-- Workflow table (24 steps with correct commands: `/sk:write-tests`, `/sk:lint`, `/sk:test`, `/sk:accessibility`, `/sk:perf`)
+- Workflow table (27 steps with correct commands: `/sk:write-tests`, `/sk:lint`, `/sk:test`, `/sk:accessibility`, `/sk:perf`, `/sk:e2e`)
 - Step details (TDD red/green/verify descriptions)
-- Tracker rules (hard gates at 12, 14, 16, 20; optional steps 4, 5, 7, 18, 24)
+- Tracker rules (hard gates at 12, 14, 16, 20, 22; optional steps 4, 5, 8, 18, 27)
 - Step completion summary rule (NON-NEGOTIABLE)
 - Bug fix flow section
 - Sub-Agent Patterns section (if missing)
@@ -67,6 +67,8 @@ Read → Explore → Design → Accessibility → Plan → Branch → Migrate
 - Lessons Capture section (if missing)
 - Testing TDD section (if missing)
 - 3-Strike Protocol (if missing)
+- Fix & Retest Protocol section (if missing)
+- Requirement Change Flow section (if missing)
 
 **What gets preserved:**
 - Everything marked with `<!-- LOCK -->` is never touched

package/skills/sk:test/SKILL.md

@@ -154,6 +154,23 @@ All detected suites pass with 100% coverage on new code. Both lines of the repor
 
 ---
 
+## Fix & Retest Protocol
+
+When a test failure requires an implementation fix, classify the fix before committing:
+
+**a. Bug fix — same behavior contract** (the code was wrong, the test expectation was right) → fix the implementation, re-run `/sk:test`. No test update needed.
+
+**b. Logic change** (new behavior, changed data contract, modified function signature, new code path) → trigger protocol:
+1. Update or add failing unit tests to reflect the new behavior (RED first)
+2. Fix the implementation to make the updated tests pass (GREEN)
+3. Re-run `/sk:test` — must pass at 100% coverage
+4. Commit (tests + fix together in one commit)
+5. Re-run the gate that triggered this fix (Security, Performance, Review, or E2E)
+
+**Why this matters:** quality gates (Security, Performance, Review, E2E) run after tests pass. If those gates require logic fixes, tests can become stale. This protocol ensures tests always reflect the actual implementation.
+
+---
+
 ## Model Routing
 
 Read `.shipkit/config.json` from the project root if it exists.