smart-think
Advanced multi-mode thinking system with Sequential Thinking MCP and Serena integration for complex problem solving
Install with Tessl CLI
npx tessl i github:sc30gsw/claude-code-customes --skill smart-think45
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description fails on all dimensions by using buzzwords and technical jargon without explaining what the skill actually does or when to use it. 'Advanced multi-mode thinking system' and 'complex problem solving' are vague marketing language that provide no actionable guidance for skill selection. The technical terms (Sequential Thinking MCP, Serena) are implementation details that users would never mention.
Suggestions
Replace abstract language with specific concrete actions (e.g., 'Breaks down complex problems into steps, analyzes dependencies, generates structured solutions')
Add a 'Use when...' clause with natural trigger terms users would actually say (e.g., 'Use when tackling multi-step problems, planning projects, or debugging complex issues')
Remove or explain technical jargon - describe what Sequential Thinking MCP and Serena actually enable in user-facing terms
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Uses vague, abstract language like 'advanced multi-mode thinking system' and 'complex problem solving' without describing any concrete actions. No specific capabilities are listed. | 1 / 3 |
Completeness | Missing both clear 'what' (no concrete actions described) and 'when' (no explicit trigger guidance or 'Use when...' clause). Only vague domain reference to 'complex problem solving'. | 1 / 3 |
Trigger Term Quality | Contains technical jargon ('Sequential Thinking MCP', 'Serena integration') that users would not naturally say. No natural keywords that match how users would request help. | 1 / 3 |
Distinctiveness Conflict Risk | 'Complex problem solving' is extremely generic and could conflict with virtually any skill. The technical terms don't help distinguish when to use this vs other analytical skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
52%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill presents a well-organized reference for a multi-mode thinking system with good token efficiency and clear option tables. However, it lacks the critical workflow guidance showing how to actually orchestrate the MCP tools together, and the actionability suffers from missing concrete examples of tool invocations and expected outputs.
Suggestions
Add a step-by-step workflow showing the actual sequence of MCP tool calls for a complete thinking session (e.g., 1. Call sequential-thinking with X, 2. If confidence < threshold, call Y)
Include concrete examples of mcp__sequential-thinking__sequentialthinking invocations with sample inputs and expected response structures
Add validation checkpoints: how to assess if thinking depth is sufficient, when to escalate modes, and how to handle low-confidence results
Show a complete worked example demonstrating the full flow from problem input through tool orchestration to final output
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-organized with tables for quick reference. No unnecessary explanations of concepts Claude already knows - it jumps straight to usage patterns and options. | 3 / 3 |
Actionability | Provides concrete command examples and tool names, but lacks executable code showing how to actually implement the thinking process. The MCP tool calls are named but not demonstrated with actual invocation patterns or expected outputs. | 2 / 3 |
Workflow Clarity | No clear workflow sequence for how to actually execute a thinking session. Missing: how to chain the MCP tools together, what order to call them, validation steps, or how to handle when confidence thresholds aren't met. The mode selection guidelines are vague criteria rather than actionable steps. | 1 / 3 |
Progressive Disclosure | Content is well-structured with clear sections and tables, but everything is in one file. For a skill this complex with multiple modes and integrations, detailed examples and MCP integration specifics could be split into referenced files. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.