Explorar skills

Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.

Use when you want autonomous completion from requirements to verification without intervention.

Structured multi-viewpoint research using 5 parallel Sonnet sub-agents. Use when deep research is needed on a complex topic before implementation planning.

全自动 PDLC 新功能开发（串联 PRD→设计→TDD→实现→评审→发布）

Background knowledge about how following works on the Fediverse, including at the ActivityPub wire-format level. Load when the user asks about implementing follows, the Follow/Accept/Reject/Undo activity flow, locked vs unlocked accounts, the followers and following collections, shared inboxes, delivery of posts to followers, how follower-only posts work, account migration with the Move activity,

Get detailed information about a specific research finding or observation. Use when injected research mentions "[/research-detail ID]" for more sources and context.

Generate a personalized reading tour and verified architecture spine for any codebase.

Use when you need to validate workflow state schema or error handling.

Shape an idea into a concept through guided dialogue

Structured technical PM framework for AI product roles. Covers: RLHF, evals, RAG, LLM deployment, system design, API design.

Initialize, verify, or update Bulwark governance in a project. Sets up CLAUDE.md, rules.md, and optional tooling (statusline, LSP, scaffold). --update reviews canonical template changes interactively per-section.

Use when you need to generate or view a session summary from work tracker logs.