Build and navigate DSP (Data Structure Protocol) — graph-based long-term structural memory of codebases for LLM agents. Stores entities (modules, functions), their dependencies (imports), public API (shared/exports), and reasons for every connection. Use when: (1) project has a .dsp/ directory, (2) user asks to set up…
Consult existing Kauri decisions before planning or implementing changes. Use BEFORE making architectural choices, changing conventions, picking libraries, or modifying files that might be covered by a recorded decision.
Draft a Kauri decision for human review before recording it. This skill should be used proactively — when the user makes, confirms, or rejects a non-trivial choice (picking a library, rejecting an approach, choosing an architecture, resolving a trade-off, establishing a convention), invoke this skill to draft a…
Review recent code changes against Kauri decisions. Use after implementing changes, before committing, during PR review, or when asked "does this look right?" to verify consistency with recorded decisions.
Coding interview practice in the user's preferred language. Flows: add a problem to the shared bank, practice an existing problem (tutoring or evaluation), run a timed mock interview, query weak spots, or look up which problems a specific company is reported to ask (from an open-source company-tagged question bank).…
Behavioral interview prep, mock interviews, company research, and round-specific cheat-sheets. Selects from the project STAR files in $PERSONAL/career/star/ and orchestrates them into prep artifacts. For coding interviews, use coding-prep. For creating new STAR project files, use star-stories.
First-run setup for a fresh clone of career-agent. Bootstraps $PERSONAL, checks prerequisites (pandoc, python deps, git config), then runs a guided interview to populate personal-info, goals, impact-doc, and brag-doc. Detects partial setup and resumes. Use when the user says "/onboard", "set me up", "I just cloned the…