tunneleven/c4flow:test
skills/test/SKILL.md
Run unit and integration tests with coverage checking. Auto-detect framework, classify failures, enforce coverage threshold before advancing to review. Use when the user wants to run tests, check coverage, or validate implementation quality. Triggers on "run tests", "check coverage", "test suite", or when the code phase completes.
development
Updated Apr 23, 2026
$ install --global
skillsauthnpx skillsauth add tunneleven/C4Flow c4flow:testInstall 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: Apr 23, 2026, 11:34 PM56.5s6 files scanned
SKILL.md
- name:
- c4flow:test
- description:
- Run unit and integration tests with coverage checking. Auto-detect framework, classify failures, enforce coverage threshold before advancing to review. Use when the user wants to run tests, check coverage, or validate implementation quality. Triggers on "run tests", "check coverage", "test suite", or when the code phase completes.
/c4flow:test — Unit + Integration Tests
Phase: 4: Testing Agent type: Sub-agent (dispatched by orchestrator) Status: Implemented
Overview
Run the full test suite after implementation is complete. Detect the test framework, execute tests, classify failures (code bugs vs environment issues), and check coverage against threshold. Does NOT write test files.
Based on: run-tests skill with coverage checking added for c4flow workflow.
Input
- Feature name (kebab-cased) from
.state.json docs/specs/<feature>/tech-stack.md— framework & testing stack infodocs/specs/<feature>/spec.md— expected behaviors (Given/When/Then scenarios)- Coverage threshold (from
tech-stack.mdor default 80%)
Output
- Test results: pass/fail count, duration, coverage percentage
- Failure analysis: root cause suggestions with confidence levels
- Gate decision: pass (advance to REVIEW) or fail (report issues)
Gate Condition
TEST → REVIEW: Tests pass, coverage >= threshold
Capabilities
| Capability | Source | Details | |---|---|---| | Framework detection | run-tests | 16 frameworks: Jest, Vitest, Mocha, Ava, pytest, Go, Cargo, .NET, Mix, Gradle, Maven, PHPUnit, RSpec, Minitest, Dart, Swift, Make | | JS runner differentiation | run-tests | Detects Jest vs Vitest vs Mocha vs Ava from config + devDependencies | | Monorepo awareness | run-tests | nx, turbo, lerna, pnpm-workspace detection | | Failure classification | run-tests | Tier 1 (code bugs: deep analysis) / Tier 2 (env issues: quick fix) | | Deep analysis | run-tests | Up to 5 unique-file slots, ±10 lines context, HIGH/MEDIUM/LOW confidence | | Coverage checking | NEW | Parse coverage output, check against threshold |
Helper Scripts
Located in skills/test/scripts/:
| Script | Used by sub-agent? | Purpose |
|--------|:------------------:|---------|
| detect-framework.sh | ✅ Yes | Auto-detect test framework from project files (16 frameworks) |
| classify-failure.sh | ✅ Yes | Classify test output as Tier 1 (code) or Tier 2 (env) |
| format-output.sh | ✅ Yes | Format results in concise/detailed/JSON mode |
| parse-args.sh | ❌ No | Inherited from run-tests for standalone usage. Sub-agent receives params from orchestrator, not CLI args |
Execution
Follow prompt.md step by step.
How Other Phases Use This Output
| Test Output | Used By | |---|---| | Pass/fail status | Gate condition for REVIEW phase | | Coverage % | Gate condition for REVIEW phase | | Uncovered file list | REVIEW phase uses as context for code review | | Failure analysis | If BLOCKED, orchestrator presents to user for guidance |
Related Skills
tunneleven/c4flow:verify
development
VerifiedTrustedCommunity
Quality gate aggregation — runs bd preflight, combines with Codex review results, declares Ready for PR status. Use when the user wants to check if code is ready for PR, verify quality gates, or run preflight checks. Also triggers when mentioning "verify", "preflight", "quality gate", or "ready for PR".
SKILL.mdUpdated Apr 23, 2026
tunneleven/c4flow:tdd
development
VerifiedTrustedCommunity
Test-driven development — RED-GREEN-REFACTOR cycles for all C4Flow implementation work. Merged into c4flow:code as a sub-agent phase with a mandatory RED gate pause. Use c4flow:code to run the full task loop.
SKILL.mdUpdated Apr 23, 2026
tunneleven/c4flow:sync
testing
VerifiedTrustedCommunity
Sync local project with remote sources — pulls DoltHub beads and GitHub repo to local. Handles the "no common ancestor" Dolt error that occurs when bd init creates a fresh local DB that conflicts with an existing DoltHub history. Use when local beads are out of sync, after a fresh init on a project that already has DoltHub data, or to pull the latest GitHub changes.
SKILL.mdUpdated Apr 23, 2026
tunneleven/c4flow:spec
content-media
VerifiedTrustedCommunity
Generate structured spec artifacts (proposal, tech-stack, spec, design) through interactive collaboration, using research.md as structured input.
SKILL.mdUpdated Apr 23, 2026