sc30gsw/smart-think
skills/smart-think/SKILL.md
Advanced multi-mode thinking system with Sequential Thinking MCP and Serena integration for complex problem solving
$ install --global
skillsauthnpx skillsauth add sc30gsw/claude-code-customes smart-thinkInstall 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, 6:35 AM127.1s1 file scanned
SKILL.md
- name:
- smart-think
- description:
- Advanced multi-mode thinking system with Sequential Thinking MCP and Serena integration for complex problem solving
Smart Think: Advanced Multi-Mode Problem Solving
Intelligent problem-solving with multiple thinking modes, budget control, and MCP integration for complex analysis and decision-making.
Usage
/smart-think "<problem_description>" [options]
Options
| Option | Short | Description | Default |
|--------|-------|-------------|---------|
| --mode | -m | Thinking mode | think |
| --budget | -b | Token budget | Auto |
| --interactive | -i | Interactive refinement | false |
| --output | -o | Save to file | none |
| --serena | -s | Use Serena integration | false |
| --research | -r | Include research phase | false |
| --citations | -c | Include citations | false |
| --structured | | Structured output | false |
| --confidence | | Show confidence levels | false |
| --focus | -f | Focus area | none |
Thinking Modes
| Mode | Budget Range | Thoughts | Confidence | Best For |
|------|--------------|----------|------------|----------|
| think | 2,000-8,000 | 3-6 | 70-85% | Quick decisions |
| think-hard | 8,000-15,000 | 6-10 | 75-90% | Complex analysis |
| think-harder | 15,000-25,000 | 10-15 | 80-95% | Architecture decisions |
| ultrathink | 25,000-50,000 | 15-25 | 85-98% | Research, complex systems |
Tool Priorities
ALWAYS prioritize mcp__sequential-thinking__ as primary engine, with mcp__serena__ for codebase context:
Primary Thinking Engine (Sequential Thinking MCP)
- Use
mcp__sequential-thinking__sequentialthinkingas primary thinking tool - Generate and test multiple solution hypotheses
- Build reasoning chains with confidence tracking
Codebase Intelligence (Serena MCP - When --serena flag)
- Use
mcp__serena__get_symbols_overviewfor technical understanding - Use
mcp__serena__search_for_patternfor implementation insights - Use
mcp__serena__read_memory/mcp__serena__write_memoryfor decision continuity
Example Usage
# Default thinking mode
/smart-think "Should we use Redux or Zustand?"
# Deep analysis with codebase context
/smart-think "Database migration strategy" -m think-harder --serena
# Research-focused with citations
/smart-think "Technology selection" -m ultrathink --research --citations
# Quick decision with budget control
/smart-think "CSS framework choice" -b 5000 --focus=frontend
Mode Selection Guidelines
- Think: Quick decisions, simple problems, time constraints
- Think-Hard: Important decisions, moderate complexity
- Think-Harder: Critical decisions, high complexity
- UltraThink: Mission-critical, research-level analysis
Output Formats
Default Format
- Problem Analysis
- Solution Exploration
- Recommendation
- Next Steps
Research Format (with --research)
- Executive Summary
- Literature Review
- Technical Analysis
- Recommendations
- References
Technical Format (with --serena)
- Technical Context
- Code Analysis
- Architecture Implications
- Implementation Strategy
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