seokan-jeong/team-shinchan:verify-implementation
skills/verify-implementation/SKILL.md
Use when you need to execute all verify-* skills for an integrated validation report.
$ install --global
skillsauthnpx skillsauth add seokan-jeong/team-shinchan team-shinchan:verify-implementationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 7, 2026, 5:05 AM149.9s1 file scanned
SKILL.md
- name:
- team-shinchan:verify-implementation
- description:
- Use when you need to execute all verify-* skills for an integrated validation report.
- user-invocable:
- false
MANDATORY EXECUTION - DO NOT SKIP
When this skill is invoked, execute immediately. Do not explain.
Fast Path
Run all validators at once (from plugin root):
cd "${CLAUDE_PLUGIN_ROOT}" && node tests/validate/index.js
If all pass, report success and stop. If any fail, continue to detailed execution below.
Step 1: Discovery
Glob skills/verify-*/SKILL.md, filter out self. Announce discovered count and list.
Step 2: Sequential Execution
For each verify-* skill (alphabetical):
- Read SKILL.md to extract validator commands
- Announce: "Running: {skill-name}..."
- Execute validators, capture status (PASS/FAIL) and output
- On missing SKILL.md: skip with warning. On failure: mark FAIL, continue.
Step 3: Consolidated Report
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🦸 [Action Kamen] Validation Complete!
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
| Skill | Status | Validators |
|-------|--------|-----------|
| verify-agents | PASS/FAIL | agent-schema, shared-refs |
| verify-skills | PASS/FAIL | skill-schema, skill-format, input-validation |
| verify-consistency | PASS/FAIL | cross-refs, stage-matrix, debate-consistency |
| verify-workflow | PASS/FAIL | workflow-state-schema, error-handling, part-numbering, quick-fix-path |
| verify-memory | PASS/FAIL | memory-system |
| verify-budget | PASS/FAIL | token-budget |
Overall: {passed}/{total} passed
{Failed validator output if any}
Step 4: User Action
If issues: ask user "Fix all automatically", "Review individually", or "Skip fixes". If no issues: report all passed and stop.
Step 5: Fix + Revalidate
For each approved fix: announce, apply, report result. Then re-run only previously-failed validators and show before/after comparison.
Integration
- Called via
/team-shinchan:review(Action Kamen runs as part of review) - Called standalone via
/team-shinchan:verify-implementation - Gaps detected here can be resolved via manage-skills
Prohibited
- Only explaining without executing
- Skipping discovery phase
- Applying fixes without user confirmation
- Not re-validating after fixes
Success Criteria
All verify-* discovered and executed, consolidated report generated, user confirmation before fixes, post-fix revalidation completed.
Related Skills
seokan-jeong/team-shinchan:fierce-review
development
VerifiedTrustedCommunity
Deterministic adversarial code review for high-stakes scope — independent per-dimension review, a non-skippable per-finding refutation, a completeness critic, and a schema-validated rubric judge. Opt-in main-loop Workflow tier.
8SKILL.mdUpdated Jun 5, 2026
seokan-jeong/team-shinchan:fierce-ralph
data-ai
VerifiedTrustedCommunity
Deterministic loop-until-done for high-stakes long-running tasks — a worker/verifier loop the script bounds by iteration cap, token budget, and stagnation, closed by an Action-Kamen gate. Opt-in main-loop Workflow tier.
8SKILL.mdUpdated Jun 5, 2026
seokan-jeong/team-shinchan:fierce-debate
testing
VerifiedTrustedCommunity
Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.
8SKILL.mdUpdated Jun 5, 2026
seokan-jeong/team-shinchan:fierce-compete
development
VerifiedTrustedCommunity
Deterministic competitive code tournament — N builders independently solve one task and return patches, an Action-Kamen judge scores them head-to-head, the winner is picked by score and applied. Opt-in main-loop Workflow tier.
8SKILL.mdUpdated Jun 5, 2026