com um clique
problem-solving
// Broadly and deeply analyze user intent (avoiding XY problems) and evaluate multiple solution approaches (default 5) with scores from 0 to 100.
// Broadly and deeply analyze user intent (avoiding XY problems) and evaluate multiple solution approaches (default 5) with scores from 0 to 100.
Build the project and automatically fix packaging or build errors (for example Hatch failures) and related breakage. Use when the project fails to build, shows "broken" states, or after making significant changes.
Run CodeQL security/quality analysis and fix findings. Use when the user asks to run CodeQL, security scan, static analysis, or fix CodeQL findings.
Interactive deep research and decision support: frame the real problem (XY-aware), ask exactly 10 multiple-choice questions one at a time, then produce a rigorous comparative evaluation (default 5 approaches, 0–100 scores) and recommendation. Use when the user wants structured discovery before committing to a solution, a scored comparison of approaches, or to avoid jumping straight to an answer—especially for architecture, strategy, or high-stakes trade-offs.
Run linters and fix violations, formatting errors, or style mismatches using Trunk. Use when code quality checks fail, before submitting PRs, or to repair "broken" linting states.
Manage Architecture Decision Records (ADRs). Use this to initialize, create, list, and link ADRs to document architectural evolution. Requires 'adr-tools' to be installed.
At the end of a coding agent session (Cursor, Claude Code, Codex, Gemini CLI, or similar), summarize outcomes, failures, inefficiencies, and root causes, then output a concise postmortem with ranked Must/Should/Consider improvements. Chat-only output; do not edit project files unless the user explicitly asks. Skip nit-picks and one-off mistakes.
| name | problem-solving |
| description | Broadly and deeply analyze user intent (avoiding XY problems) and evaluate multiple solution approaches (default 5) with scores from 0 to 100. |
This skill enables a systematic and thorough evaluation of potential solutions for a given issue. It goes beyond the stated problem to identify the user's true underlying intent, avoiding the "XY Problem" (asking for a solution to an intermediate step rather than the root goal). It ensures that multiple perspectives are considered and that the final recommendation is backed by a structured scoring process.
assets/templates/analysis-report.md template to present your findings.
Input: "We need to migrate our legacy monolith to microservices. Analyze the approaches." Output: A report identifying the intent (e.g., "Improve scalability and deployment speed"). The XY check might note that microservices are a means, not the end. Approaches might include "Modular Monolith" or "Serverless" alongside traditional microservices.
Input: "How do I fix this regex for parsing nested HTML tags in my custom scraper?" Output: A report identifying the Stated Problem (Regex fix) and the Underlying Intent (Extracting data from HTML). The XY check would note that regex is unsuitable for nested HTML. Approaches would include "Use BeautifulSoup/Cheerio", "Use a dedicated HTML parser library", etc., scoring them much higher than the "Fix Regex" approach.