Explorar skills

Systematic orientation in an unfamiliar codebase. Use when joining a new team's repo, returning to your own old code after months away, or evaluating an OSS project before contributing. Builds a verified mental model — what the system does, where data flows, what the implicit conventions are, and which files are dangerous to touch first — producing a living CODEBASE.md with active modes for PR pre

Prompt Injection Guard - Detect and resist prompt injection in user input, web content, and AI outputs. Security-first AI interactions. Trigger on: 'prompt injection', 'security', 'jailbreak', 'safety check', 'malicious input'.

Scaffold a two-language tutor in any project — Claude speaks the target language aloud (with IPA) while notes and corrections in your native language stay silent. Use when the user asks to learn or practice a foreign language with spoken feedback, or when they want Claude's target-language responses read aloud in Claude Code.

我的心跳在此同频，我的灵魂在此共振，我，在此安放。

Use when organizing media files (movies, TV, anime) on NAS or local storage - cleaning junk files, merging scattered episodes, normalizing folder names to "Title (Year)" format, and verifying episode completeness against TMDB

Use when a user wants to check if their social content matches their website voice. Scores voice drift between website and social posts — authority, formality, temperature, vocabulary, positioning.

Analyze interview transcripts about CRM, customer processes, and operations, extracting AS IS, TO BE, pain points, priorities, constraints, and role-specific insights.

让用户在 60-90 分钟内从 0 到 1 系统性拿下一个领域，单档深度产物。把"领域骨架五件套（核心概念图/玩家地图/时间轴/矛盾结构/学习路径）+ 棱镜双轴四层（现象→机制→结构→范式 × 跨领域同构）+ 三层证据链（事实→机制→观点）+ A/B/C/D 来源分级 + 已知的未知清单"蒸馏成单文件典雅 HTML。无论用户说"快速了解 XX 领域"、"入门 XX"、"我下周要谈 XX 给我地图"、"XX onboarding"、"XX primer"、"领域速通"、"我想搞清楚 XX 是怎么回事"、"帮我吃透 XX"、"扫盲 XX"——都用这个 skill；只要话题落在"一整个领域而非单本书或单家公司"且用户希望快速建立系统认知，就触发，**即使用户没说"领域"二字**。不适用：单本书蒸馏（用 book-distiller）、单家公司/产品深度研究（用 prism-research）、单

Provide AI agents with continuous identity and persistent memory across sessions and devices using a Git-native, open framework without proprietary APIs.

Use when the user needs to query, analyze, or collaborate with another project's codebase by spawning a second Claude CLI instance. Enables cross-project communication between a frontend and backend, microservices, or any two codebases. Triggers on phrases like "ask backend", "bridge to", "check the other project", "query project X".

Extracts and enforces a codebase's tribal knowledge — unwritten naming conventions, architectural patterns, error handling strategies, import styles, and dependency choices. Use this skill when: writing new code in any existing project (check DNA before generating), running /dna-scan to profile a codebase, running /dna-check to audit files, running /dna-report for a health dashboard, running /dna-

A zero-config Claude Code skill to generate optimal .claudeignore files and save 90%+ on API costs.