smart-think
Advanced multi-mode thinking system with Sequential Thinking MCP and Serena integration for complex problem solving
32
14%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/smart-think/SKILL.mdQuality
Discovery
7%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 is dominated by vague buzzwords and technical jargon without describing concrete actions or providing trigger guidance. It fails to tell Claude what specific tasks this skill performs or when to select it. The only redeeming quality is the mention of specific tool names which provides minimal distinctiveness.
Suggestions
Replace 'complex problem solving' with specific concrete actions this skill performs (e.g., 'Breaks down multi-step problems into sequential reasoning chains, analyzes code architecture, plans refactoring strategies').
Add an explicit 'Use when...' clause with natural trigger terms users would actually say (e.g., 'Use when the user needs step-by-step reasoning, architectural analysis, or multi-faceted problem decomposition').
Remove marketing-style language like 'Advanced multi-mode thinking system' and replace with plain descriptions of what the skill actually does.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, buzzword-heavy language like 'advanced multi-mode thinking system' and 'complex problem solving' without listing any concrete actions. No specific capabilities are described. | 1 / 3 |
Completeness | The description vaguely addresses 'what' (complex problem solving) but provides no 'when' clause or explicit trigger guidance. Both dimensions are very weak. | 1 / 3 |
Trigger Term Quality | The terms used ('multi-mode thinking system', 'Sequential Thinking MCP', 'Serena integration') are technical jargon that users would not naturally say. No natural user-facing keywords are present. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of specific tools ('Sequential Thinking MCP', 'Serena') provides some distinctiveness, but 'complex problem solving' is extremely generic and could overlap with virtually any analytical skill. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a CLI tool's README than actionable instructions for Claude. It defines modes, options, and output format labels but lacks the concrete implementation details—actual tool call sequences, example reasoning chains, or step-by-step workflows—that would make it executable. The arbitrary confidence percentages and thought count ranges add noise without clear utility.
Suggestions
Add a concrete end-to-end workflow showing the exact sequence of MCP tool calls (e.g., mcp__sequential-thinking__sequentialthinking invocations) with example inputs and outputs for at least one thinking mode.
Replace the abstract output format section headers (e.g., 'Problem Analysis', 'Solution Exploration') with a concrete example showing what a complete output looks like for a sample problem.
Add validation/decision checkpoints in the workflow, such as when to escalate from 'think' to 'think-hard' mode, or when a reasoning chain should branch or backtrack.
Remove or justify the specific confidence percentage ranges and thought counts per mode—these appear arbitrary and don't translate into actionable guidance for Claude.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably organized with tables, but includes some unnecessary detail like exact confidence percentage ranges and thought counts that are somewhat arbitrary. The output format sections at the end are vague labels rather than actionable templates. | 2 / 3 |
Actionability | Despite listing MCP tool names, there's no executable code or concrete implementation showing how to actually chain sequential thinking calls, how to structure the reasoning, or what the tool calls look like in practice. The 'Tool Priorities' section describes what to do abstractly but never shows how. | 1 / 3 |
Workflow Clarity | There is no clear multi-step workflow showing how a thinking session proceeds from start to finish. The skill describes modes and tools but never sequences them into a process with validation checkpoints or decision points for when to branch or iterate. | 1 / 3 |
Progressive Disclosure | The content is structured with clear sections and tables, which aids readability. However, everything is in one file with no references to supplementary materials, and some sections (like output formats) are skeletal outlines that either need fleshing out or linking to detailed examples elsewhere. | 2 / 3 |
Total | 6 / 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.
- Repository
- sc30gsw/claude-code-customes
- Commit
7aff694
- 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.