sc30gsw/spec-tech-research
skills/spec-tech-research/SKILL.md
Advanced technical research command with extended thinking modes and MCP integration for comprehensive analysis
$ install --global
skillsauthnpx skillsauth add sc30gsw/claude-code-customes spec-tech-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: May 19, 2026, 6:36 AM153.3s1 file scanned
SKILL.md
- name:
- spec-tech-research
- description:
- Advanced technical research command with extended thinking modes and MCP integration for comprehensive analysis
Spec Tech Research
Advanced technical research with extended thinking modes and MCP integration for comprehensive analysis.
Usage
/spec:tech-research "<topic>" [options]
Thinking Modes
| Mode | Token Budget | Depth | Use Case |
|------|--------------|-------|----------|
| think | 10,000 | Standard | Quick research, overviews |
| think-hard | 20,000 | Enhanced | Detailed comparisons |
| think-harder | 30,000 | Structured | Complex topics, decisions |
| ultrathink | 50,000 | Maximum | Critical analysis, academic |
Core Options
| Option | Short | Description | Example |
|--------|-------|-------------|---------|
| --mode | -m | Thinking mode | -m ultrathink |
| --budget | -b | Token budget | -b 25000 |
| --output | -o | Output file | -o analysis.md |
| --format | -f | Output format | -f json |
| --mcp | | MCP tools to use | --mcp "context7,sequential" |
Research Options
| Option | Short | Description | Example |
|--------|-------|-------------|---------|
| --depth | -d | Search depth (quick/standard/deep/exhaustive) | -d deep |
| --template | -t | Report template | -t academic |
| --confidence | -c | Confidence threshold (0-1) | -c 0.9 |
| --sources | | Include citations | --sources |
| --diagrams | | Generate diagrams | --diagrams |
| --language | -l | Output language | -l ja |
Tool Priorities
ALWAYS prioritize mcp__serena__ for codebase analysis:
Codebase Intelligence (Serena MCP First)
mcp__serena__search_for_pattern- Find implementation patternsmcp__serena__find_symbol- Understand architecturemcp__serena__get_symbols_overview- Architecture-aware recommendationsmcp__serena__read_memory/write_memory- Research continuity
Research Enhancement (Other MCPs)
mcp__context7__resolve-library-id- Library documentationmcp__sequential-thinking__sequentialthinking- Complex analysis
Templates
| Template | Description |
|----------|-------------|
| overview | Quick summary with key points |
| comprehensive | Full analysis with all aspects |
| academic | Research paper format with citations |
| technical | Implementation-focused with code |
Examples
# Quick overview
/spec:tech-research "Redis vs Memcached" -d quick -t overview
# Deep framework analysis
/spec:tech-research "React architecture patterns" -m think-harder -t comprehensive --diagrams
# Security research with high confidence
/spec:tech-research "Zero-trust security model" -m ultrathink -c 0.95 --sources
# Implementation research
/spec:tech-research "Implementing OAuth 2.0 with PKCE" -t technical -m think-hard
# Codebase-aware research
/spec:tech-research "State management options" --mcp "serena,context7" --codebase-context
# Japanese technical documentation
/spec:tech-research "Docker コンテナ化" -l ja -t technical
Output Structure
# Technical Research Report: [Topic]
## Executive Summary
- Key findings and recommendations
## Table of Contents
1. Introduction
2. Core Concepts
3. Technical Analysis
4. Implementation Considerations
5. Best Practices
6. Comparisons
7. Recommendations
8. Conclusion
9. References
## Confidence Scores
- Finding 1: 95% confidence
- Finding 2: 88% confidence
Integration
Research results can be used with:
/serenafor implementation/debug-errorfor context/smart-thinkfor decisions/spec:requirementsfor requirements
Related Skills
sc30gsw/skill-creator
tools
VerifiedTrustedCommunity
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
10SKILL.mdUpdated May 30, 2026
sc30gsw/skills/sdd-workflow
testing
VerifiedTrustedCommunity
# sdd-workflow — Workflow Status Dashboard ## Slash Command ``` /sdd-workflow [slug] ``` ## Purpose Read-only meta skill. Displays the current state of the SDD workflow — which phases are complete, which is next, and any blockers. Does NOT modify any files. --- ## This Skill is Read-Only `sdd-workflow` never writes to or modifies any file. It only reads spec files and git history to report status. There is no approval gate for this skill. --- ## Usage: Specific Feature ``` /sdd-workflo
10SKILL.mdUpdated May 30, 2026
sc30gsw/skills/sdd-tasks
content-media
VerifiedTrustedCommunity
# sdd-tasks **Slash command**: `/sdd-tasks <slug>` **Purpose**: Generate `tasks.md` (TASK-001..N) and `progress.md` from `requirements.md` and `design.md`. --- ## Prerequisites - `.claude/specs/<slug>/requirements.md` must exist - `.claude/specs/<slug>/design.md` must exist (run `/sdd-design` first) --- ## Steps ### 1. Read spec inputs ``` .claude/specs/<slug>/requirements.md .claude/specs/<slug>/design.md ``` Extract: - Every REQ-XXX ID with its acceptance criteria - Every design sect
10SKILL.mdUpdated May 30, 2026
sc30gsw/skills/sdd-review
development
VerifiedTrustedCommunity
# sdd-review — Post-Implementation Code Review ## Slash Command ``` /sdd-review <slug> ``` ## Purpose Run code review and security review on all changes introduced by the feature branch. Append structured findings to `review.md`. Does NOT auto-apply fixes — only proposes them. --- ## Prerequisites - `sdd-impl` has completed: all tasks in `progress.md` are `done` (or at least one is `done`; partial reviews are allowed). - The feature branch must have at least one commit ahead of `main`. -
10SKILL.mdUpdated May 30, 2026