tunneleven/c4flow:research
skills/research/SKILL.md
Perform merged market analysis and technical research on a feature idea. Combines market-research (business domain, competitive landscape, feature comparison, gap analysis) with C4Flow technical research (approaches, contrarian view, risks).
data-ai
Updated Apr 23, 2026
$ install --global
skillsauthnpx skillsauth add tunneleven/C4Flow c4flow:researchInstall 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, 11:31 PM61.3s3 files scanned
SKILL.md
- name:
- c4flow:research
- description:
- Perform merged market analysis and technical research on a feature idea. Combines market-research (business domain, competitive landscape, feature comparison, gap analysis) with C4Flow technical research (approaches, contrarian view, risks).
/c4flow:research — Merged Market & Technical Research
Phase: 1: Research & Spec Agent type: Sub-agent (dispatched by orchestrator) Status: Implemented
Overview
Analyze a feature idea across both market and technical dimensions. Produces a single structured artifact (research.md) with 16 sections that feeds directly into the spec phase.
Sources merged:
- market-research — business domain, competitive landscape, feature comparison, gap analysis
- C4Flow research — technical approaches, contrarian view, risks, recommendations
Input
- Feature name (kebab-cased)
- Feature description from user
- Mode:
research(default) |fast
Output
docs/specs/<feature>/research.md(16 sections)
Execution Modes
| Mode | Web Search | Duration | Use When |
|------|-----------|----------|----------|
| research (default) | Yes (web search + URL fetching) | ~3-5 minutes | Pre-proposal, serious builds, funding prep |
| fast | No | ~30 seconds | Quick exploration, early ideation |
Analysis Layers
| Layer | Sections | Purpose | |-------|----------|---------| | Layer 1: Market | Problem Statement → Initial MVP Scope (10 sections) | "Nên build không, và build gì?" | | Layer 2: Technical | Technical Approaches → Recommendations (4 sections) | "Build như thế nào?" | | Quality Gate | 8 core + 1 conditional check | Verify output completeness | | Executive Summary | 2-3 sentence verdict | Build / buy / skip decision |
Research Standards
Every research output MUST follow these 5 standards:
- Source every claim — numbers, stats, and key claims must link to a source or be explicitly labeled
[estimate] - Favor recent data — prefer sources from the last 12 months; flag anything older than 2 years as
[stale: YYYY] - Include contrarian evidence — actively search for downside cases, criticisms, and reasons the feature might fail
- Translate to a decision — findings must lead to a clear recommendation, not just a dump of information
- Distinguish fact / inference / recommendation — label each clearly so the reader knows what is proven vs. interpreted vs. suggested
Execution
Follow prompt.md step by step.
Output Sections (16 total)
Executive Summary → Problem Statement → Target Users → Core Workflows →
Domain Entities → Business Rules → Competitive Landscape → Feature Comparison →
Gap Analysis → Differentiation Strategy → Initial MVP Scope →
Technical Approaches → Contrarian View → Risks → Recommendations → Sources
See references/research-template.md for full artifact structure.
How Spec Phase Uses This Output
| Research Section | Feeds Into |
|-----------------|------------|
| Executive Summary | proposal.md → Why (motivation) |
| Target Users + Core Workflows | proposal.md → What Changes; spec.md → User stories |
| Domain Entities + Business Rules | spec.md → Requirements; design.md → Data Model |
| Competitive Landscape + Feature Comparison | proposal.md → Impact + Differentiation |
| Gap Analysis + Differentiation Strategy | proposal.md → Capabilities (New) |
| Initial MVP Scope | proposal.md → Scope (In/Out) |
| Technical Approaches | tech-stack.md → Technology Choices |
| Contrarian View + Risks | design.md → Risks/Trade-offs |
| Recommendations | proposal.md → Success Criteria |
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:test
development
VerifiedTrustedCommunity
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.
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