Coding & Development

Orchestrate non-trivial Claude Code work; pins/routes Opus 5.5 and Sonnet 5.5 by ID for planning vs implementation seats.

Frevana OpenRouter skill for Anthropic Claude Sonnet 5 (anthropic/claude-sonnet-5) — balanced production coding companion to the Sonnet 5.5 skill.

Frevana OpenRouter skill targeting Anthropic Claude Sonnet 5.5 (anthropic/claude-sonnet-5.5) for feature work, bug fixes, polished docs, and everyday agentic coding.

Frevana OpenRouter skill targeting Anthropic Claude Opus 5.5 (anthropic/claude-opus-5.5) for demanding reasoning, large codebases, review, and long-horizon agents.

Route Claude 5 tiers (Haiku/Sonnet/Opus/Fable), effort, and subagents for cost-effective results; Claude 5 prompting, long-running execution, refusals, fallback.

Autonomous /orc orchestrator for Claude Code with Sonnet 5.5 efficiency mode and reviewer/verifier subagents — ship units unsupervised.

Capability-aware model routing including Claude Opus 5.5 effort ladder (low–max) across Codex/Copilot/Claude provider APIs.

Write/review/migrate prompts, CLAUDE.md, skills and subagents for Claude Opus 5.5 (and Opus 5→5.5). Applies Anthropic Prompting Claude Opus 5.5 guidance.

Adversarial review posture skill with Claude Opus 5.5 reference notes — disprove-before-approve for architecture and risky UI/site changes.

Single-pass whole-project audit leveraging Opus 5.5 1M context for security, architecture, and dependency review.

Fable 5.1 orchestrator skill that delegates implementation to Claude Sonnet 5.5 workers — decompose, dispatch, review, merge, PR.

Write/audit prompts another Claude will run — tuned for Claude Opus 5.5 (CC 2.1.280) with Sonnet 5.5 and Fable reference deltas.

Frevana OpenRouter skill for Anthropic Claude Opus 5 (anthropic/claude-opus-5) — soft-tagged sibling in the Claude 5 line alongside Opus/Sonnet 5.5 skills.

适用于 ROS 1 / ROS 2 机器人开发、迁移与联调的 skill。覆盖 catkin/catkin_tools、colcon/ament、package.xml、CMakeLists.txt、launch、URDF/Xacro、RViz、TF、Navigation2、ros2_control、串口/CAN、MCU 与 micro-ROS 等常见工程场景。

Automatically optimize AI agent credit usage by routing tasks to the most cost-efficient execution path. Use when you want to reduce AI API costs by 30-75% without quality loss, classify task complexity before execution, route simple tasks to free or low-cost models, split complex tasks into optimized sub-tasks, or detect vague prompts before wasting credits.

Traktor Pro QML modding handbook

Reduce decision-relevant uncertainty before execution. Use at the start of tasks where missing goals, constraints, context, or preferences could materially change the plan; ask at most one high-information question at a time and otherwise proceed with reasonable assumptions.

操控你的 X/Twitter 账号——查看时间线、搜索推文、发推、点赞、转推、收藏。

Generate valid fancy-kanban boards — markdown-embedded kanban boards with typed fields, swimlanes, workflow rules, and card face configuration for Obsidian and compatible tools

BREAK 业务风险枚举与规避知识库 — 查询业务安全风险、规避手段、攻击工具、威胁行为者、行业术语和典型案例，或基于知识库回答业务安全问题

Generate AI-friendly repository documentation with the SourceSage CLI. Use when Codex needs to run `sage` or `sourcesage` to create `.SourceSageAssets/Repository_summary.md`, analyze the current repository or another local repository, switch the output language between English and Japanese, use `--lite` to keep the summary small, change the output directory, or optionally create a deprecated tag-diff release report with `--diff`.

Online (incremental) covariance, correlation, and precision estimation in Python — the streaming complement to sklearn.covariance. Use when code needs a covariance/correlation matrix updated per observation, recomputes np.cov/np.corrcoef in a rolling loop, must judge or compare covariance estimates, or proposes a new covariance methodology. Points to task-specific skills.

这是一个创意的儿童折纸风格定格动画生日祝福视频生成器。当用户想要给小孩子制作个性化生日祝福动画时激活。该技能通过三段式的剧情（创意出场 -> 生日祝福 -> 暖心叮嘱），结合 5 大热门儿童 IP（汪汪队、小猪佩奇、奥特曼、海绵宝宝、哆啦A梦），生成用于 Gemini Omni Flash 的标准分镜提示词与中文配音指导。

Convert the current phase doc into an ordered execution plan and propose work packages (spec-first + tiered tests), including RTL/Hebrew checks.