173 results (4.0ms) page 5 / 9
zrt-ai-lab / opencode-skills-video-creator exact

视频创作技能。图片+音频合成视频,支持淡入淡出转场、自动拼接片尾、添加BGM。当用户提到「生成视频」「图文转视频」「做视频号」时触发此技能。

zrt-ai-lab / opencode-skills-searchnews exact

当用户要求"搜索新闻"、"查询AI新闻"、"整理新闻"、"获取某天的新闻",或提到需要搜索、整理、汇总指定日期的AI行业新闻时,应使用此技能。

zrt-ai-lab / opencode-skills-smart-query exact

智能数据库查询技能。通过SSH隧道连接线上数据库,支持自然语言转SQL、执行查询、表结构探索。当用户需要查询数据库、问数据、看表结构时使用此技能。

git 0.00
EpicenterHQ / epicenter-git exact

Git commit and pull request guidelines using conventional commits. Use when creating commits, writing commit messages, creating PRs, or reviewing PR descriptions.

open-horizon-labs / skills-salvage exact

Extract learning before restarting. Code is a draft; learning is the asset. Use when work is drifting, approach has reversed 3+ times, or scope is expanding while "done" keeps fuzzing.

noartem / skills-shadcn-vue exact

shadcn-vue for Vue/Nuxt with Reka UI components and Tailwind. Use for accessible UI, Auto Form, data tables, charts, dark mode, MCP server setup, or encountering component imports, Reka UI errors.

aim 0.00
open-horizon-labs / skills-aim exact

Clarify the outcome you want - a change in user behavior, not a feature shipped. Use at the start of any work to ground the session in strategic intent.

julianobarbosa / claude-code-skills-shell-prompt exact

Modern shell prompt configuration with Powerlevel10k and Zsh Vi Mode. Use when configuring shell prompts, setting up vi/vim keybindings in zsh, customizing cursor styles per mode, adding mode...

benchflow-ai / skillsbench-harbor exact

Harbor framework for agent evaluation. Use when: (1) Running harbor commands (harbor run, harbor tasks check), (2) Creating/validating SkillsBench tasks, (3) Understanding task format or debugging...

open-horizon-labs / skills-problem-space exact

Map what we're optimizing and what constraints we treat as real. Use before jumping to solutions, when hitting repeated blockers, or when patches keep accumulating.

open-horizon-labs / skills-execute exact

Do the work. Pre-flight, build, detect drift, salvage if needed. Use when you have a clear aim and are ready to implement.

open-horizon-labs / skills-problem-statement exact

Define the framing of a problem. Change the statement, change the solution space. Use when starting work, when solutions feel wrong, or when you suspect an X-Y problem.

ship 0.00
open-horizon-labs / skills-ship exact

Deliver code to users. Optimize the path from merged code to working install. Use when execution is complete and you need to get changes into users' hands.

open-horizon-labs / skills-review exact

Check work and detect drift before committing. A second opinion that catches misalignment early. Use at natural pause points, before PRs, or when something feels off.

open-horizon-labs / skills-solution-space exact

Explore candidate solutions before committing. Use when you have a problem statement and need to evaluate approaches - band-aid, optimize, reframe, or redesign.

open-horizon-labs / skills-dissent exact

Devil's advocate. Seek contrary evidence before locking in. Use when about to make a significant decision, when confidence is high but stakes are higher, or when the team is converging too quickly.

gmh5225 / awesome-skills-agent-platforms exact

Guide for multi-platform skill compatibility across Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, and other AI coding agents.

Mo7amedhassan11 / add-skill-installer exact

安裝 Agent Skills 到本機。當用戶想要「安裝技能」、「新增 skill」、「從 GitHub 安裝 skill」、或「install skill from repo」時觸發此技能。

kevintsai1202 / add-skill-installer exact

安裝 Agent Skills 到本機。當用戶想要「安裝技能」、「新增 skill」、「從 GitHub 安裝 skill」、或「install skill from repo」時觸發此技能。

yanko-belov / code-craft-skill-awareness exact

Always active. Tracks usage of code-craft skills across sessions. Log skill applications to enable analytics and identify gaps.