Coding & Dev Tools

moltis-org Skill

Songwriting craft, AI music generation prompts (Suno focus), parody/adaptation techniques, phonetic tricks, and lessons learned. These are tools and ideas, not rules. Break any of them when the art calls for it.

moltis-org Bundle

PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.

xu-xiang Skill

逐步优化上下文检索以解决子智能体（subagent）上下文问题的模式。

xu-xiang Bundle

为 X、LinkedIn、TikTok、YouTube、时事通讯 (Newsletters) 以及多平台复用活动创建平台原生内容系统。当用户需要社交帖子、推文串 (Threads)、脚本、内容日历或将单一源素材清晰地适配到多个平台时使用。

xu-xiang Bundle

Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

xu-xiang Bundle

建议在逻辑间隔进行手动上下文压缩（Context Compaction），以便在任务阶段中保留上下文，而不是依赖任意的自动压缩。

xu-xiang Bundle

为 Claude Code 会话提供的全面验证系统。

xu-xiang Skill

使用 JUnit 5, Mockito, MockMvc, Testcontainers 和 JaCoCo 进行 Spring Boot 的测试驱动开发（TDD）。适用于添加新功能、修复 bug 或重构场景。

xu-xiang Bundle

创建并更新路演 PPT (Pitch Deck)、单页简介 (One-Pager)、投资者备忘录 (Investor Memo)、加速器申请、财务模型以及融资材料。当用户需要面向投资者的文档、预测、资金用途表、里程碑计划或需要跨多个融资资产保持内部一致性的材料时，请使用此技能。

xu-xiang Skill

构建健壮、高效且可维护 Go 应用程序的惯用法（Idiomatic Go）、最佳实践与规范。

xu-xiang Skill

PostgreSQL 数据库模式，涵盖查询优化、架构设计、索引和安全。基于 Supabase 最佳实践。

xu-xiang Skill

自动从 Claude Code 会话（Session）中提取可重用的模式（Pattern），并将其作为已学习的技能（Skill）保存以备将来使用。

xu-xiang Skill

Django 验证循环（Verification Loop）

xu-xiang Skill

数据库迁移最佳实践，涵盖模式变更、数据迁移、回滚以及零停机部署，适用于PostgreSQL、MySQL及常用ORM（Prisma、Drizzle、Django、TypeORM、golang-migrate）。

xu-xiang Skill

Deployment Patterns

xu-xiang Skill

适用于 Spring Boot 服务的 Java 编码规范：命名、不可变性、Optional 使用、流（Stream）、异常、泛型及项目布局。

xu-xiang Bundle

一种基于本能（Instinct）的训练系统，通过钩子（Hooks）观察会话，创建带有置信度评分的原子化本能，并将其进化为技能（Skills）、命令（Commands）或智能体（Agents）。

xu-xiang Skill

Spring Boot 项目的验证循环：构建、静态分析、带有覆盖率的测试、安全扫描以及发布或 PR 前的差异审查。

xu-xiang Skill

项目指南技能（示例）

first-fluke Bundle

Bug diagnosis and fixing specialist - analyzes errors, identifies root causes, provides fixes, and writes regression tests. Use for bug, debug, error, crash, traceback, exception, and regression work.

first-fluke Bundle

Analyze conversation histories from multiple AI tools (Grok, Claude, Codex, Gemini, Qwen, Cursor, Antigravity) and generate themed daily/period work summaries. Filter by date or time window.

first-fluke Bundle

Design-first ideation that explores user intent, constraints, and approaches before any planning or implementation. Use for brainstorming, ideation, exploring concepts, and evaluating approaches.

first-fluke Bundle

Create or update OMA skills in the SSL-lite human-readable format. Use when adding a new `.agents/skills/{skill-name}/SKILL.md`, converting an existing skill to the standardized Scheduling / Structural Flow / Logical Operations / References structure, or validating whether a skill has enough routing, execution, resource, and safety detail.

galihadiprayoga Skill

Gunakan untuk sesi ideation terstruktur sebelum memulai fitur baru, debugging kompleks, atau refactor besar. Trigger: "brainstorm fitur X", "kita mau bikin Y gimana", "ada masalah dengan Z", "/brainstorm". Output: keputusan pendekatan + asumsi + open questions — bukan kode.

galihadiprayoga Skill

Gunakan untuk membuat dokumen spec/design formal dari hasil brainstorm atau deskripsi fitur. Trigger: "buat spec untuk X", "tulis design doc", "spec fitur Y", "/spec-writer". Output: file spec di docs/superpowers/specs/YYYY-MM-DD-{slug}-design.md — bukan kode.

galihadiprayoga Skill

Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.

galihadiprayoga Skill

FastAPI best practices covering project structure, Pydantic v2 schemas, dependency injection, async handlers, authentication, authorization, transactional service layers, and testing with httpx and pytest.

ysyecust Skill

レビュー優先の整理、フォロー/追加の推薦、ユーザーの実際の声で書かれたチャネル別ウォームアウトリーチのドラフトを通じて、ユーザーのXとLinkedInネットワークを再編成します。フォローリストを整理したい、現在の優先事項に向けて成長したい、または高品質な関係を中心にソーシャルグラフのバランスを取り直したい場合に使用します。

cor-incorporated Skill

Organizes files and folders by analyzing content, detecting duplicates, and restructuring directories. Use when the user says: 'organize my files', 'clean up downloads', 'find duplicates', 'restructure folder', 'organize photos', 'desktop cleanup', 'sort files', 'archive old projects', 'folder structure'. Handles Downloads cleanup, duplicate detection, project reorganization, and photo sorting. Do NOT use for code refactoring (use senior-fullstack), git operations, or codebase restructuring within a software project.

cor-incorporated Skill

PR review severity を Haiku AI で再分類。regex 偽陽性を除外する片方向ゲート。/classify-review [PR番号] で実行。regex が CRITICAL/HIGH 検出した際の偽陽性チェック専用。

cor-incorporated Skill

Manage Context7 CLI skills: search, install, list, remove, info via ctx7. Use when the user wants to find, install, list, remove, or inspect Context7 skills. Triggers: 'search skills', 'install skill', 'list my skills', 'remove skill', 'ctx7', 'context7'. Do NOT use for general package management (npm, pip), non-Context7 CLI commands, or skill authoring.

natan-mohart Skill

Compares a company's key financial ratios against true peer medians and quartiles, flagging which peers were excluded and why, so the read is defensible rather than a single flattering comparison. Use whenever the user wants to benchmark a company against competitors, needs a peer comparison for a board deck or investor update, or has a benchmarking claim with no stated peer set or exclusion logic behind it.

natan-mohart Bundle

Scores every metric red, amber, or green against its target via a bundled calculator, and specifically flags when a leading indicator is already red while the lagging outcome it predicts still shows green, catching a problem before it shows up in the number everyone's watching. Use whenever the user wants a KPI dashboard or scorecard, needs to connect leading indicators to the lagging outcomes they predict, or has a dashboard that reports metrics with no status thresholds and no link between leading and lagging measures.

natan-mohart Bundle

Computes NPV, IRR, payback, and simple ROIC for a capital project via a bundled calculator that checks IRR against the company's actual hurdle rate, not just WACC, and flags when a project would be approved on NPV-at-WACC alone despite failing the real bar the company sets. Use whenever the user is evaluating a capex project, needs a capital investment decision case, or has a project evaluated only against WACC with no explicit hurdle-rate check.

natan-mohart Bundle

Scores customer credit risk on payment behavior, concentration, and credit rating via a bundled calculator, and separately flags customers whose exposure concentration alone justifies a credit limit regardless of how well they've paid historically. Use whenever the user wants to assess counterparty or customer credit risk, is setting or reviewing credit limits, or has a credit risk process that scores payment history but never checks exposure concentration on its own.

natan-mohart Bundle

Buckets receivables and payables by age via a bundled calculator, computes DSO and DPO, ranks the specific overdue accounts worth chasing first by dollar impact, and flags when the business is paying suppliers well before it collects from customers. Use whenever the user wants to see what's overdue and who to chase first, needs DSO/DPO for a cash or working capital review, or has an AR/AP process with no ranked priority on which specific accounts to act on first.