Loading...
Loading...
Found 36 Skills
Use when the user wants an agent to explore an unfamiliar repository, synthesize candidate work, ask structured direction questions, generate a bounded Claude Code /goal or equivalent implementation goal, or safely prepare a doctrine-gated autonomous request.
This skill should be used when the user asks to "generate an AGENTS.md", "create a CLAUDE.md", "write agent instructions", "set up AGENTS.md", "make an AGENTS.md for this repo", "configure agent behavior", or mentions generating, writing, or improving an AGENTS.md or CLAUDE.md file for a project.
Before searching a codebase, forces you to zero in on the target: what exactly are you looking for, what would it look like, where would it live, what else might it be called. Activates on "find", "where is", "search for", or when exploration begins. Prevents grep-and-pray.
Guided project onboarding for new codebases. Helps agents understand project structure, build systems, test commands, and development workflows by creating persistent knowledge memories.
Interview user to clarify any topic - exploring codebase, investigating issues, planning features, understanding requirements, or drilling into plans. Socratic questioning to uncover details.
Navigate unfamiliar code using GitNexus knowledge graph
Load context for a task: read the spec/ticket, explore the codebase surface, and present the task context to the user. The user controls implementation.
Your pathfinder for navigating unknown codebases. Investigates with precision, implements surgically, and never assumes — if it doesn't know, it says so. Maintains a .notebook/ knowledge base that grows across sessions, turning every discovery into lasting intelligence. Summons available skills, MCPs, and docs when the mission demands. Use when fixing bugs, implementing features, refactoring, investigating flows, or any development task in unfamiliar territory. Triggers on "fix this", "implement this", "how does this work", "investigate this flow", "help me with this code". Do NOT use for greenfield scaffolding, CI/CD, or infrastructure provisioning.
Continuously interview users around a plan or design until a shared understanding is reached, and address each branch of the decision tree one by one. Use this when the user wants to stress-test a plan, have their design grilled, or mentions "grill me".
Create a plan for the specified task.
Continuously question users about their plan or design. Suitable for scenarios where users want to stress-test their plan before building, or when using any "grill" trigger phrases.
Create a plan collaboratively with the user, then convert the approved plan into a GitHub issue.