Loading...
Loading...
Found 64 Skills
Harness Engineering Phase 1 Step 2: Conduct in-depth analysis of project code and fill in the substantive content of each file in the docs/ knowledge base. Use this skill after the directory skeleton is created by harness-step1-create-agents-md. Immediately trigger this skill when the user says "fill document content", "improve docs/ files", "add substantive content to documents", "analyze project and write architecture document", "write ARCHITECTURE.md", or "write technical decision document". Prerequisite: The project already has AGENTS.md and the docs/ directory skeleton (created by harness-step1).
Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.
This skill MUST be used for semantic Rust navigation and analysis: resolving definitions across crate boundaries, finding all references to a symbol, inspecting inferred types or trait implementations, searching symbols by name, and renaming symbols safely. SHOULD be preferred over grep or file reads whenever the task requires Rust-aware understanding.
Analyzing .NET code for modernization. Outdated TFMs, deprecated packages, superseded patterns.
Review a pull request or contribution deeply, explain it tutorial-style for a maintainer, and produce a polished report artifact such as HTML or Markdown. Use when asked to analyze a PR, explain a contributor's design decisions, compare it with similar systems, or prepare a merge recommendation.
Apply and validate SOLID principles in object-oriented design
Color contrast analyzer for WCAG compliance. Use when analyzing color contrast in code files, when user mentions WCAG compliance, color accessibility, contrast ratios, or when discussing colors in UI components. Calculates contrast ratios, identifies violations, and suggests accessible color alternatives that preserve design themes.
Recursive Language Models (RLM) CLI - enables LLMs to recursively process large contexts by decomposing inputs and calling themselves over parts. Use for code analysis, diff reviews, codebase exploration. Triggers on "rlm ask", "rlm complete", "rlm search", "rlm index".
Maps questions to the optimal tldr command. Use this to pick the right layer
Cognitive science-based deep source code understanding assistant (Chinese improved version). Supports three analysis modes: Quick (overview), Standard (comprehension), Deep (mastery, automatically uses parallel processing for large projects). Integrates elaborative interrogation, self-explanation testing, and retrieval practice to help truly understand and master code.
Microscopic deconstruction and exhaustive analysis of code, systems, documents, or concepts. Breaks subjects into atomic components, examines every facet, and produces encyclopedic reports. Use when deep understanding is needed before making changes, analyzing unfamiliar codebases, or producing thorough technical documentation. Triggers on "심층 분석", "deep dive", "분석해줘", "해부", "deconstruct", "뜯어봐", "thoroughly analyze", "코드 분석".
Generate feature specifications by analyzing existing source code.