Gerstep/research
.claude/skills/Research/SKILL.md
Company due diligence, technology deep-dives, market analysis, and topic exploration for cyber•Fund investment decisions, content creation, and personal projects. Supports 3 intensity levels (quick/standard/deep) for speed-quality tradeoffs.
$ install --global
skillsauthnpx skillsauth add Gerstep/cybos 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 16, 2026, 1:43 AM34.9s19 files scanned
SKILL.md
- name:
- research
- description:
- Company due diligence, technology deep-dives, market analysis, and topic exploration for cyber•Fund investment decisions, content creation, and personal projects. Supports 3 intensity levels (quick/standard/deep) for speed-quality tradeoffs.
Research Skill
Company due diligence, technology deep-dives, market analysis, and topic exploration for cyber•Fund investment decisions, content creation, and personal projects.
Capabilities
- Company Research: Comprehensive DD on target companies
- Technology Research: Deep technical analysis of technologies
- Market Research: Market sizing, dynamics, and opportunity assessment
- Topic Research (Content): Ideas, narratives, people for essays/tweets
- Topic Research (Investment): Market dynamics and opportunities for investment thesis
Research Intensity Levels
- 🔍 Quick (10-30s): 1 agent
- 🔬 Standard (2-5m): 2-3 agents [DEFAULT]
- 🔎 Deep (5-15m): 3-5 agents + quality-reviewer
See shared/intensity-tiers.md for full specification.
Workflow
All research types use one universal workflow:
workflows/orchestrator.md
The orchestrator dynamically selects agents based on research type and intensity.
Agent Selection
See shared/agent-selection-matrix.md for full matrix.
| Research Type | Quick | Standard | Deep | |---------------|-------|----------|------| | Company DD | company | company + market + financial | +team +quality-reviewer | | Technology | tech | tech + market | +company +quality-reviewer | | Market | market | market + financial | +company +quality-reviewer | | Topic-Content | content | content | +quality-reviewer | | Topic-Investment | investment | investment + market | +financial +quality-reviewer |
Agents
Research agents (autonomous MCP access):
company-researcher: Business model, product, tractionmarket-researcher: TAM, dynamics, trendsfinancial-researcher: Funding, metrics, comparablesteam-researcher: Founder backgrounds, team assessmenttech-researcher: Technology deep-divescontent-researcher: Academic papers, social media, first-principles (for content)investment-researcher: Market dynamics, opportunities, timing (for investment)
Quality & Synthesis:
quality-reviewer: Gap analysis, contradiction detection (deep only, max 1 iteration)synthesizer: Consolidate parallel research outputs
Common References
shared/agent-selection-matrix.md- Dynamic agent selectionshared/investment-lens.md- cyber•Fund investment philosophyshared/mcp-strategy.md- MCP tool selectionshared/output-standards.md- Formats and emoji conventionsshared/intensity-tiers.md- 3-tier intensity spec
Output Locations
All research creates timestamped workspace:
~/CybosVault/private/deals/<company>~/CybosVault/private/research/MMDD-<slug>-YY/ # Company
~/CybosVault/private/research/<topic>/MMDD-<slug>-YY/ # Tech/Market/Topic
├── raw/ # Agent outputs
└── report.md # Final synthesis
Key Principles
- Agents do ALL data gathering - Main session orchestrates, agents make MCP calls
- No redundancy - Each agent makes its own calls autonomously
- Dynamic selection - Agents chosen based on research type + intensity
- Quality loop - Deep mode includes quality-reviewer (max 1 iteration)
Investment Context
All research applies cyber•Fund's investment philosophy:
- Path to $1B+ revenue (not niche $50M ARR outcomes)
- Defensible moat (data, network effects, hard tech)
- Clear business model (revenue > token speculation)
- Strong founders (high energy, sales DNA, deep expertise)
- Market timing ("why now?")
Related Skills
Gerstep/remotion-best-practices
development
VerifiedTrustedCommunity
Best practices for Remotion - Video creation in React
92SKILL.mdUpdated Apr 16, 2026
Gerstep/excalidraw-diagram
content-media
VerifiedTrustedCommunity
Generate Excalidraw diagrams from text content. Supports three output modes - Obsidian (.md), Standard (.excalidraw), and Animated (.excalidraw with animation order). Triggers on "Excalidraw", "画图", "流程图", "思维导图", "可视化", "diagram", "标准Excalidraw", "standard excalidraw", "Excalidraw动画", "动画图", "animate".
92SKILL.mdUpdated Apr 16, 2026
Gerstep/design-taste-frontend
development
VerifiedTrustedCommunity
Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.
92SKILL.mdUpdated Apr 16, 2026
Gerstep/Writing
documentation
VerifiedTrustedCommunity
Iterative critique and improvement of long-form content (guidebooks, playbooks, essays). Launches parallel judge subagents for multi-dimensional critique, synthesizes findings, presents proposals for user approval. Never edits without consent.
92SKILL.mdUpdated Apr 16, 2026