Instruccions per a IA
Disseny d’instruccions i plantilles per a models d’IA
review
jh941213
현재 브랜치의 변경사항 코드 리뷰. "리뷰", "review", "검토" 키워드에 활성화.
fast-mode
kevinslin
Operate Codex in fast-mode by skipping skill loading and going directly to task execution, while allowing only explicitly whitelisted skills from a local allow-list file. Use when a user requests fast-mode, minimal overhead, or "no skills unless allowed."
mastermind-adapters
monoes
Mastermind adapters — install, enable, disable, reload, and remove LLM adapter plugins per org. Supports claude-local, gemini-local, codex-local, cursor, hermes, http, and custom adapters.
Skill Sanitizer
cyberxuan-XBX
First open-source AI sanitizer with local semantic detection. 7 layers + LLM intent analysis. Zero cloud — your prompts stay on your machine.
oracle
goncalossilva
Get a second opinion by bundling a prompt + a curated file set, then asking another powerful LLM for debugging, refactor advice, design checks, or code reviews.
brand-archetype-selection
mike-coulbourn
Provides Jungian brand archetype frameworks, the 12 archetypes with profiles, the 70/30 primary/secondary rule, archetype combinations, and selection templates. Auto-activates during brand archetype selection, emotional positioning, and brand personality work. Use when discussing brand archetypes, Jungian archetypes, 12 archetypes, Hero, Outlaw, Magician, Creator, Lover, Jester, Everyman, Caregiver, Ruler, Sage, Explorer, Innocent, 70/30 rule, Mark-Pearson, or archetype combinations.
resend-design-skills
resend
Use when needing Resend design resources. Routes to brand guidelines, visual identity, and other design sub-skills.
seedance-prompt
rich5000
为字节跳动即梦平台的 Seedance 2.0 视频生成模型撰写高质量提示词。当用户提到即梦、Seedance、Seedance 2.0、AI视频生成、AI短片、AI广告片，或需要为视频生成模型编写提示词/prompt时，使用此 Skill。涵盖文生视频、图生视频、多模态参考、一镜到底、产品广告、视频编辑等全场景提示词模板和最佳实践。
Dispatch Worker
OmniNode-ai
Dispatch a background worker with role-templated prompt and auto-populated collision fences
decision-store skill
OmniNode-ai
Record, query, and conflict-check architectural and design decisions across the OmniNode platform
/onex:delegate — single-command delegation
OmniNode-ai
"Single-command delegation to a model you choose: one you run, or your own provider key. Runs onex delegate \"<prompt>\" --result-only which builds the payload, dispatches node_delegate_skill_orchestrator, and prints only the final answer on stdout (on failure, one error line on stderr). Handled inline — no subagent, no payload file, no cat of workflow_result.json."
ai-engineer-expert
personamanagmentlayer
Expert-level AI implementation, deployment, LLM integration, and production AI systems
claude-dev-pack
Peiiii
"Developer toolkit: build, test, deploy, and debug with curated skills."
claude-design-pack
Peiiii
"Design toolkit: UI/UX, themes, brand guidelines, and generative art."
temp-files
llama-farm
Guidelines for creating temporary files in system temp directory. Use when agents need to create reports, logs, or progress files without cluttering the repository.
project-os
Peiiii
AI project OS for autonomous loop, automated orchestration, and rule-driven execution.
claude-office-pack
Peiiii
"Office toolkit: PDF/Word/PPT/Excel + internal comms."
generate-subsystem-skills
llama-farm
Generate specialized skills for each subsystem in the monorepo. Creates shared language skills and subsystem-specific checklists for high-quality AI code generation.
reflect
llama-farm
Analyze the current session and propose improvements to skills. Proactively invoke this skill when you notice user corrections after skill usage, or at the end of skill-heavy sessions. Also use when user says "reflect", "improve skill", or "learn from this".
claude-content-pack
Peiiii
"Content toolkit: research, writing, summarization, and insights."
pptx
MarcelLeon
"演示文稿创建、编辑和分析。当 Claude 需要处理演示文稿（.pptx 文件）时使用，包括：(1) 创建新演示文稿，(2) 修改或编辑内容，(3) 使用布局，(4) 添加评论或演讲者备注，或任何其他演示文稿任务"
ideation
nicknisi
Transform raw brain dumps (dictated freestyle) into structured implementation artifacts. Use when user has messy ideas, scattered thoughts, or dictated stream-of-consciousness, or when they want to plan a feature, spec something out, or turn rough ideas into actionable specs. Produces contracts and implementation specs written to ./docs/ideation/{project-name}/.
blog-post-writer
nicknisi
Transform brain dumps into polished blog posts in Nick Nisi's voice. Use when the user says "write a blog post," "draft a post," "write about [topic]," "turn my notes into a blog post," or provides scattered ideas, talking points, or conclusions that need shaping into a cohesive narrative.
doc-coauthoring
MarcelLeon
引导用户通过结构化工作流共同撰写文档。当用户想要编写文档、提案、技术规范、决策文档或类似的结构化内容时使用。此工作流帮助用户高效传递上下文、通过迭代精炼内容，并验证文档对读者是否有效。当用户提到编写文档、创建提案、起草规范或类似文档任务时触发。