step-through
SolidWalks the user through a long enumerated response (numbered findings, audit list, refactor plan, bug list, PR review, recommendations, action items) one item at a time. For each item, lets the user dive deeper, take action, defer, or skip — instead of staring at the whole wall of text. Learns the user's per-severity defaults from feedback. Use when an assistant has just produced a long list and the user says "let's go through these one by one", "step me through", "walk me through", "let's triage", "next item", or otherwise wants interactive per-item review of a previous response. Works on any enumerated content — not just PR reviews.
Install
Quality Score: 83/100
Skill Content
Details
- Author
- mostafa-drz
- Repository
- mostafa-drz/claude-skills
- Created
- 7 months ago
- Last Updated
- yesterday
- Language
- HTML
- License
- MIT
Similar Skills
Semantically similar based on skill content — not just same category
code-walkthrough
Walks a person through code changes one step at a time in conversation, starting at the entry point and following the flow that changes, showing a small chunk per step and explaining it in plain language. Defaults to the current branch's changes, and walks the code from the perspective of any context provided instead — a file, directory, symbol, pull request, plan, or ticket. Use when someone wants to be walked through, taught, paced through, or shown around code or a branch step by step, or to learn how a change works before reviewing or extending it. Stops after every step and waits, so the learner sets the pace. Paces through code that already exists and builds nothing — to build new work while being paced through it, use pairing. Does not produce a written overview to read alone — use code-overview. Does not review code quality — use code-review. Does not diagnose bugs — use investigate.
walkthrough
Answer a codebase question as an ordered sequence of anchored steps walked in IntelliJ, not as terminal prose. Claude generates the steps, the IDE plugin walks the user through them, and the user can ask a question on any step which Claude answers in place. Triggered by /walkthrough <question>. Watcher events are WEBCOMPANION_EVENT / WEBCOMPANION_FINISHED / WEBCOMPANION_CANCELLED.
deep-think
Structured sequential thinking engine for complex reasoning, multi-variable decisions, and strategy under uncertainty. Breaks problems into numbered thought steps with revision and branching support. Replaces the Sequential Thinking MCP server with visible, challengeable reasoning tailored to CEO decision-making. Engage this skill PROACTIVELY -- without waiting for the user to ask -- whenever a problem involves multi-variable decisions, contradictory signals, high-stakes reasoning, strategy under uncertainty, or when you catch yourself making unexamined assumptions. Use when the user says "think through this", "break this down", "reason through", "what are we missing", "think step by step", "structured thinking", "analyze this carefully", "help me think about", "deep think", or any request requiring deliberate multi-step reasoning before action. This is the thinking engine that precedes and sharpens every other skill.