Browse reusable Agent Skills, each with a clear purpose and practical guidance.
用于升级 AI 系统、agent workflow、Codex skill、prompt、memory、RAG、tool routing、schema、eval set 或 feedback loop；也用于把 AI 工作单从指令单升级为意图单，并对研究、检索、测试和 AI 对话做 VOI 决策门审计。需要 Intent Work Order、WOOP 任务准入、决策对象、VOI/EVPI/EVSI、OODA、eval、Human Gate、versioning 与 rollback 的受控演化时使用。Use when controlled AI system evolution or a decision-oriented information audit is needed.
Agent Farm CLI — the tool for spawning builders, managing Tower, workspaces, and cron tasks. ALWAYS consult this skill BEFORE running any `afx` command to get the exact syntax. This prevents wasting time guessing flags that don't exist. Use this whenever you need to spawn a builder, check status, send messages, clean up worktrees, manage Tower, or run cron tasks. If you're about to type `afx` followed by anything, check here first.
Deploy and manage Kagenti operator, agents, and tools on Kubernetes. Handles installer, CRDs, pipelines, and demo deployments.
Extracts learnings from execution trajectories at the end of a Mantis loop. Use to parse agent conversations, extract successes, failures, and false assumptions, and append them to learnings.jsonl. Don't use for analyzing source code or writing patches.
Review and clean up Claude auto-memory for the current project. Opens the memory list in Emacs for annotation, then applies deletions, updates, and relocations based on edits. Triggers: /memory-review, "review my memories", "clean up memories", "prune memories", "update my memories"
Clone target repo into .repos/ and verify skill discovery works
Review the current conversation to find agent mistakes, inefficiencies, and corrections, then propose new guidelines to add to CLAUDE.md to prevent recurrence. Triggers: /retrospect, "what went wrong", "capture lessons", "update CLAUDE.md", "add this to instructions", "remember not to do this", "update the guidelines", "add to agents.md", "end of session review", or when the user asks to capture anything from the current session into instructions. Always use this skill when the user invokes it at the end of a session — even if the session seemed smooth, there may still be patterns worth capturing.
Update the repo-local review-pr-local and review-spec-local companion skills using human feedback left on pull request conversations. Use when aggregating replies to agent-authored PR review comments, incorporating broader human review comments, extracting repeated reviewer feedback, and refining .agents/skills/review-pr-local/SKILL.md and .agents/skills/review-spec-local/SKILL.md with evidence-backed adjustments.
나노바나나 프롬프트의 정확성을 한글 번역본과 비교하여 검증하고, WebSearch로 팩트체크한 후 이슈별로 사용자 확인을 거쳐 수정합니다. 사용: /improve-prompt week1/deep-dive-llms/tokenization