validate-workflow
Validate AI Developer Workflow step outputs and contracts. Use when verifying workflow step completeness before proceeding.
What this skill does
# Validate Workflow
Validate AI Developer Workflow step outputs and ensure contract compliance.
## Arguments
- `$ARGUMENTS`: `<step-type> [spec-path]`
- `step-type`: One of `plan`, `build`, `review`, `fix`
- `spec-path`: Optional path to spec file (auto-detected if not provided)
## Step Contracts
| Step | Output Type | Key Requirements |
| --- | --- | --- |
| `plan` | Spec file | Summary, requirements, criteria, approach |
| `build` | Code changes | Commits with prefix, tests pass |
| `review` | Report | PASS/FAIL status, severity-rated issues |
| `fix` | Resolutions | Issues addressed, no new issues |
## Instructions
### Step 1: Identify Step Type
Parse the step type from arguments:
```text
Valid types: plan, build, review, fix
```
### Step 2: Load Step Contract
**Plan Contract:**
- [ ] Spec file exists at `specs/*.md`
- [ ] Contains Summary section
- [ ] Contains Requirements list
- [ ] Contains Acceptance Criteria
- [ ] Contains Technical Approach
- [ ] Scope is bounded and achievable
**Build Contract:**
- [ ] Files modified or created
- [ ] Commits exist with `build:` prefix
- [ ] No build/lint errors
- [ ] Tests pass (if exist)
- [ ] All spec requirements addressed
**Review Contract:**
- [ ] Report generated with structured format
- [ ] STATUS is clearly PASS or FAIL
- [ ] Issues have severity levels (CRITICAL/HIGH/MEDIUM/LOW)
- [ ] Issue descriptions are actionable
- [ ] All code reviewed against spec
**Fix Contract:**
- [ ] All flagged issues addressed
- [ ] Commits exist with `fix:` prefix
- [ ] No new issues introduced
- [ ] Verification confirms resolution
### Step 3: Validate Outputs
**For Plan Step:**
```bash
# Find latest spec file
ls -t specs/*.md | head -1
# Check required sections
grep -c "## Summary\|## Requirements\|## Acceptance\|## Technical" specs/latest.md
```
**For Build Step:**
```bash
# Check for build commits
git log --oneline -5 | grep "^[a-f0-9]* build:"
# Check build status
npm run build 2>&1 | tail -5
# or: dotnet build 2>&1 | tail -5
# Check tests
npm test 2>&1 | tail -10
# or: dotnet test 2>&1 | tail -10
```
**For Review Step:**
```bash
# Check for review report
ls -t .claude/temp/*review*.md 2>/dev/null | head -1
# Verify PASS/FAIL status
grep -E "STATUS:|Result:" review_report.md
```
**For Fix Step:**
```bash
# Check for fix commits
git log --oneline -5 | grep "^[a-f0-9]* fix:"
# Verify no new issues
# (re-run review step)
```
### Step 4: Check Success Criteria
For each criterion in the contract:
1. Execute verification command/check
2. Record pass/fail status
3. Capture evidence (file path, command output, etc.)
### Step 5: Report Results
Generate validation report.
## Output
```markdown
## Workflow Validation Report
### Step Validated
**Step:** {plan|build|review|fix}
**Spec Path:** {path if applicable}
**Timestamp:** {ISO-8601}
### Contract Check
| Requirement | Status | Evidence |
| --- | --- | --- |
| {requirement} | ✅/❌ | {details} |
| {requirement} | ✅/❌ | {details} |
| {requirement} | ✅/❌ | {details} |
### Output Validation
#### {Output Name}
- **Path:** {path}
- **Exists:** ✅/❌
- **Format Valid:** ✅/❌
- **Issues:** {if any}
### Success Criteria
| Criterion | Met | Evidence |
| --- | --- | --- |
| {criterion} | ✅/❌ | {evidence} |
| {criterion} | ✅/❌ | {evidence} |
### Overall Status
**Result:** VALID | INVALID
**Summary:** {brief summary of validation result}
### Issues Found
1. **{Severity}:** {description}
- **Location:** {where}
- **Expected:** {what should be}
- **Actual:** {what was found}
- **Recommendation:** {how to fix}
### Next Steps
- {Recommended action if invalid}
- {Continue to next step if valid}
```
## Validation Quick Reference
### Plan Validation Commands
```bash
# Check spec exists
test -f specs/*.md && echo "Spec exists"
# Check sections
for section in "Summary" "Requirements" "Acceptance" "Technical"; do
grep -q "## $section" specs/*.md && echo "$section: OK"
done
```
### Build Validation Commands
```bash
# Check commits
git log --oneline -10 | grep "build:"
# Check tests
npm test --if-present || echo "No npm tests"
dotnet test 2>/dev/null || echo "No dotnet tests"
```
### Review Validation Commands
```bash
# Check report format
grep -E "^STATUS:|^Result:" review_output.md
# Check severity levels
grep -cE "CRITICAL|HIGH|MEDIUM|LOW" review_output.md
```
## Anti-Patterns
| Avoid | Why | Instead |
| --- | --- | --- |
| Skipping validation | Proceeding with incomplete work | Always validate before next step |
| Partial checks | Missing critical issues | Complete all contract checks |
| Auto-fixing during validation | Scope creep | Validate only, fix separately |
| Ignoring warnings | Technical debt | Address all severity levels |
## Cross-References
- @composable-steps.md - Step contracts
- @adw-framework.md - ADW architecture
- `workflow-validator` agent - Automated validation
- `composable-step-design` skill - Step design patterns
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.