Loading...
Loading...
Found 56 Skills
Deep contextual grep for codebases. Expert at finding patterns, architectures, implementations, and answering "Where is X?", "Which file has Y?", and "Find code that does Z" questions. Use when exploring unfamiliar codebases, finding specific implementations, understanding code organization, discovering patterns across multiple files, or locating functionality in a project. Supports three thoroughness levels quick, medium, very thorough.
Systematic approach to exploring the TensorRT-LLM codebase before implementing new features or optimizations. Teaches how to discover existing infrastructure, trace code paths, and avoid reimplementing what already exists. Derived from real mistakes where ~250 lines of code were written and deleted because existing forward methods weren't discovered upfront. Use when starting any new feature, optimization, or code modification in TRT-LLM.
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".
Teaches learners to extract transferable design lessons from real-world codebases through critical evaluation and systematic exploration. Use when a learner wants to study existing code to learn patterns, architecture, or design decisions—not just understand what it does. Guides through navigation, pattern recognition, critical evaluation (deliberate choice vs. compromise), and lesson extraction. Triggers on phrases like "learn from this codebase", "study how X is implemented", "understand design patterns in Y", or when a learner wants to improve by reading real code.
Ensures alignment between user and Claude during feature/spec planning through a structured interview process. Use this skill when the user invokes /plan-interview before implementing a new feature, refactoring, or any non-trivial implementation task. The skill runs an upfront interview to gather requirements across technical constraints, scope boundaries, risk tolerance, and success criteria before any codebase exploration. Do NOT use this skill for: pure research/exploration tasks, simple bug fixes, or when the user just wants standard planning without the interview process.
This skill should be used when a developer is ready to implement a GitHub Task issue and needs to read the full spec hierarchy (Task + Feature + Epic), explore the codebase, produce a concrete Technical Approach with real file paths, and drive TDD implementation against Gherkin scenarios. Triggers on phrases like "implement task
Query DeepWiki for repository documentation and structure. Use to understand open source projects, find API docs, and explore codebases.
Token optimization best practices for cost-effective Claude Code usage. Automatically applies efficient file reading, command execution, and output handling strategies. Includes model selection guidance (Opus for learning, Sonnet for development/debugging). Prefers bash commands over reading files.
Use this at session start to discover what CodeCompass can do. Read .ai/capabilities.json for module map (5 domains, 21+ modules) instead of manual Grep/Glob. Apply when: (1) planning tasks, (2) user asks 'What can CodeCompass do?', (3) before implementing features
Project setup. Explore the codebase, ask about strategy and aims, write persistent context to AGENTS.md. Run when starting or when aims shift.