logophile
Editing mode for clarity and semantic density; use for prompts, docs, specs, emails, and naming.
探索开发、内容、数据与办公效率等 AI 技能。先比较用途和仓库热度,再查看技能说明与来源。
Editing mode for clarity and semantic density; use for prompts, docs, specs, emails, and naming.
Law-driven abstraction protocol: evidence first, seam test, minimal algebra, executable law check.
BMad Method v6: workflow-driven agile delivery (track selection, PRD/spec, UX, architecture, epics/stories).
Implement the Ralph Wiggum iterative AI loop for Codex/Claude Code: create /ralph-loop and /cancel-ralph commands, wire a stop hook or wrapper loop, persist a fixed prompt, track iterations, and detect a comple...
Finish the in-progress bead; validate via $close-the-loop; open a PR (do not merge). Explicit-only.
Jujutsu (jj) Git-compatible VCS. Use for any version-control work (status/diff/commit/branch/rebase/merge/etc.).
Lateral-thinking playbook for options and trade-offs; always deliver a five-tier strategy portfolio.
Mine Codex sessions to synthesize your top software design heuristics (no quotes, no evidence).
CLI for searching/reading Kotlin dependency sources from a Gradle project. Use when you need to locate/inspect 3rd-party Gradle libraries.
Create a new release for fuel. Use when asked to "release", "make a release", "tag a release", or "publish a new version".
Convert an approved plan into well-defined Fuel tasks with epics, dependencies, and review tasks. Use after exiting plan mode.
Create a detailed implementation plan for new features. Use when building something across multiple files/tasks, designing implementations, entering plan mode, exiting plan mode, or when explicitly requested. T...
API security best practices and common vulnerability prevention. Enforces security checks for authentication, input validation, SQL injection, XSS, and OWASP Top 10 vulnerabilities. Use when building or modifyi...
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation,...
Python development best practices including PEP 8 style guidelines, type hints, docstring conventions, and common patterns. Use when writing or modifying Python code.
Git workflow best practices including commit messages, branching strategies, pull requests, and collaboration patterns. Use when working with Git version control.
Build, debug, and optimize RealityKit scenes for visionOS, including entity/component setup, rendering, animation, physics, audio, input, attachments, and custom systems. Use when implementing RealityKit featur...
Guide and tooling for Ralph Driven Development (RDD), a spec runner that repeatedly invokes Codex (or other agents) over ordered specs until a magic phrase signals completion. Use when setting up or operating a...
Design and implement visionOS SwiftUI scenes that integrate RealityKit content. Use when building spatial UI with RealityView, Model3D, attachments, volumetric windows, ImmersiveSpace, or spatial gestures, or w...
Guide for creating and structuring skills with consistent formatting, clear documentation, and proper reference organization. Use when creating new skills or updating existing skill documentation.
Create and edit ShaderGraph and RealityKit material networks in .usda files. Use when manually editing USD ASCII files to build, modify, or troubleshoot materials, shader nodes, and connections for RealityKit.
Build and debug ARKit features for visionOS, including ARKitSession setup, authorization, data providers (world tracking, plane detection, scene reconstruction, hand tracking), anchor processing, and RealityKit...
Enforce repository coding standards for Swift 6.2 concurrency, Swift language rules. Use when reviewing or implementing Swift code changes.
Ralph Driven Development workflow that pulls Linear project issues via the Linear MCP and runs them sequentially with Codex. Use when automating task execution from a Linear project and when you need a runner t...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。