.config/opencode/skills/workflow-validate-plan/SKILL.md
This skill should be used when validating that an implementation plan was correctly executed. It verifies success criteria, runs tests, identifies deviations, and presents structured completion options including MR creation or discard.
npx skillsauth add alexismanuel/dotfiles workflow-validate-planInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Validate that an implementation plan was correctly executed, verifying all success criteria and identifying any deviations or issues. Present structured completion options after verification passes.
Type: RIGID - Follow verification steps exactly. Don't skip test verification or present options before tests pass.
Output: Validation report with structured completion options.
Use this workflow when:
Announce at start: "I'm using the validate-plan workflow to verify the implementation."
From verification-before-completion skill:
When invoked:
Are you in an existing conversation or starting fresh?
git worktree list./plan.md file and use it if present# Check recent commits
git log --oneline -n 20
git diff HEAD~N..HEAD # Where N covers implementation commits
git status
git worktree list # Show all worktrees
Before presenting any completion options, verify tests pass:
# Run project's test suite
npm test / cargo test / pytest / go test ./...
If tests fail:
Tests failing (<N> failures). Must fix before completing:
[Show failures]
Cannot proceed with completion validation until tests pass.
STOP here. Don't proceed to Step 5.
If tests pass: Continue to validation process.
If starting fresh or need more context:
Read the implementation plan completely
Identify what should have changed:
Spawn parallel research tasks to discover implementation:
Task 1 - Verify database changes:
Research if migration [N] was added and schema changes match plan.
Check: migration files, schema version, table structure
Return: What was implemented vs what plan specified
Task 2 - Verify code changes:
Find all modified files related to [feature].
Compare actual changes to plan specifications.
Return: File-by-file comparison of planned vs actual
Task 3 - Verify test coverage:
Check if tests were added/modified as specified.
Run test commands and capture results.
Return: Test status and any missing coverage
For each phase in the plan:
Check completion status:
Run automated verification:
Assess manual criteria:
Think deeply about edge cases:
Create comprehensive validation summary:
## Validation Report: [Plan Name]
### Implementation Status
- Phase 1: [Name] - Fully implemented
- Phase 2: [Name] - Fully implemented
- Phase 3: [Name] - Partially implemented (see issues)
### Automated Verification Results
- Build passes: `make build`
- Tests pass: `make test`
- Linting issues: `make lint` (3 warnings)
### Code Review Findings
#### Matches Plan:
- Database migration correctly adds [table]
- API endpoints implement specified methods
- Error handling follows plan
#### Deviations from Plan:
- Used different variable names in [file:line]
- Added extra validation in [file:line] (improvement)
#### Potential Issues:
- Missing index on foreign key could impact performance
- No rollback handling in migration
### Manual Testing Required:
1. UI functionality:
- [ ] Verify [feature] appears correctly
- [ ] Test error states with invalid input
2. Integration:
- [ ] Confirm works with existing [component]
- [ ] Check performance with large datasets
### Recommendations:
- Address linting warnings before merge
- Consider adding integration test for [scenario]
- Document new API endpoints
Only present these options AFTER all verification passes.
Present exactly these 3 options:
Implementation complete and verified. What would you like to do?
1. Push and create a Merge Request
2. Keep the branch as-is (I'll handle it later)
3. Discard this work
Which option?
Don't add explanation - keep options concise.
Based on user's selection (1-3), execute the appropriate workflow:
Note: When working with worktrees, ensure you're in the correct directory context before executing git commands.
Use mr-generator skill to generate intelligent MR descriptions from commits:
# Push worktree's branch
git push -u origin <feature-branch>
# Generate MR description with mr-generator
python3 <skill-path>/mr-generator/scripts/mr_generator.py --create --jira <ticket-id>
# Or manually create MR with description:
glab mr create --title "<title>" --description "$(cat <<'EOF'
## Summary
<2-3 bullets of what changed>
## Test Plan
- [ ] <verification steps from validation report>
EOF
)"
After MR creation, use mr-tracker skill to monitor review activity:
./scripts/mr_tracker.sh watch <mr-iid> 30 # Check every 30 seconds
Report: "Keeping worktree <name>. All changes remain for later handling."
Don't make any git changes.
Confirm first:
This will permanently delete:
- Worktree <name>
- Branch <name>
- All commits: <commit-list>
Type 'discard' to confirm.
Wait for exact confirmation.
If confirmed:
# Navigate to main repository (not the worktree)
cd $(git rev-parse --show-toplevel)/..
# Remove the worktree and its branch
git worktree remove <worktree-path> --force
git branch -D <feature-branch>
If you were part of the implementation:
git worktree list to identify the current worktreeIf you catch yourself:
STOP and run the verification commands first.
| Mistake | Impact | Fix |
|---------|--------|-----|
| Skipping test verification | Ship broken code | Run tests BEFORE presenting options |
| Presenting open-ended next step | User doesn't know options | Present exactly 3 structured choices |
| Auto-deleting work | Lost progress | Require typed "discard" confirmation |
| Merging without verifying | Breaks base branch | Run tests on merged result |
| Wrong CLI tool (gh vs glab) | MR creation fails | Use glab for GitLab |
Always verify:
mr-generator skill for descriptionmr-tracker skill to monitor review activityThese skills complement this workflow:
Generates intelligent GitLab merge request descriptions from git commits. Use when creating MRs (Option 1) to automatically generate professional descriptions with proper commit categorization and Jira integration.
Core discipline underlying this workflow. Enforces evidence-before-claims by requiring fresh verification output before any success assertions.
Monitors GitLab merge request activity after MR creation. Use for watching MR comments, checking approval status, and tracking review feedback.
Use when work items need Jira ticket creation for traceability.
Fetches Jira ticket content by ID or text search. Useful for referencing related tickets in MR descriptions.
development
Generate GitLab merge request descriptions from git commits with automatic categorization and Jira integration.
development
This skill should be used when reviewing code changes in a branch against main/master/develop. It analyzes commits, integrates JIRA ticket and MR context when available, and produces a structured code review using Conventional Comments format.
development
This skill should be used when conducting comprehensive codebase research to answer questions, understand architecture, or prepare context for implementation planning. It spawns parallel sub-agents and synthesizes findings into a structured research document.
testing
This skill should be used when executing an approved implementation plan with batch checkpoints. It implements tasks in batches of 3, stops for review after each batch, and handles mismatches or blockers by asking for guidance rather than guessing.