GitHub
designing-innovation-experiments
Turn Innovation PRDs into concrete experiment plans with explicit hypotheses, metrics, and evaluation methods for RAG quality, agents, and automation outcomes.
Skills IA Documentation
Découvrez les skills Documentation, comparez leurs dépôts et consultez leurs instructions.
Catégories: Documentation
Documentation Effacer les filtres
Explorer
GitHub
analyzing-innovation-portfolio
Analyze the CustomGPT.ai Labs Innovation workbook and cost tracking data to surface portfolio-level insights, trends, and recommendations for where to focus Innovation efforts.
GitHub
customgpt-rag-retrieval
Automatically retrieve relevant information from the organization's CustomGPT.ai knowledge base when answering questions about documented topics, policies, procedures, or technical specifications.
GitHub
broadcasting-innovation-status
Turn Innovation project updates into clear, audience-specific status communications for Slack, email, and executive summaries.
GitHub
drafting-innovation-prd-one-pagers
Generate tight, one-page PRDs for CustomGPT.ai Labs projects aligned to Why/How/What, success metrics, and fast experimentation constraints.
GitHub
structuring-innovation-intake
Normalize raw innovation ideas into structured backlog entries for the CustomGPT.ai Labs Innovation workbook, using consistent Why/How/What, success metrics, and ownership fields.
GitHub
architecting-innovation-agents
Propose multi-agent and workflow architectures for CustomGPT.ai Labs projects, showing how Claude Code, CustomGPT.ai, and supporting tools interact to deliver the desired business outcome.
GitHub
planning-innovation-cost-and-capacity
Use the Innovation cost tracking data and project list to estimate spend, capacity, and tradeoffs across CustomGPT.ai Labs projects.
GitHub
producing-innovation-demos
Create compelling demo narratives, flows, and presenter scripts for CustomGPT.ai Labs projects using existing demo links, project docs, and Innovation context.
GitHub
packaging-customer-pilots
Turn successful Innovation projects into customer-facing pilot or POC offerings with clear scope, pricing, timelines, and success criteria.
GitHub
sss-blog
SSS Blogプロジェクトの運用スキル。ブログ記事作成、短編小説作成、サムネイル追加、プロジェクト構造の理解、デプロイ作業を支援します。記事追加、コンテンツ作成、Git操作、プロジェクトについての質問に対応します。
GitHub
liku-orchestrator
Path-grounded multi-agent orchestration using the Liku directory hierarchy (skills.xml inheritance, todo.md + LikuErrors.md audit trail, SQLite memory). Use when you need to initialize Liku, generate an agent b...
GitHub
writing-phaser-3-games
Provides battle-tested patterns, best practices, and code examples for building Phaser 3 games. Use when writing game code, implementing game mechanics, setting up scenes, handling physics, animations, input, o...
GitHub
plan-to-spec
将 Plan Mode 的讨论结论固化为可执行的 Markdown 施工图纸。当用户完成 Plan 讨论、准备进入开发阶段时使用。生成 overview.md（战略层）、taskXX_*.md（战术层）、summary.md（审计层）三类文档，实现上下文序列化，避免 Pla...
GitHub
governance-docs-standard
【WHEN】当用户要新增/修改/评审“治理层文档”（README.md、CLAUDE.md、以及用户显式指定的其他治理层文档）时启用； 【WHEN】当输出提案 vN.md、落地修改治理层文档、或产出 vN-review.md 时启用。 【WHEN NOT】不用于业务功能...
GitHub
governance-docs-codex-review
【WHEN】当需要对“治理层文档”进行 Codex 审阅并输出 vN-review.md 时调用。 【WHEN NOT】不用于提案生成；不用于落地修改；不用于业务/代码设计。
GitHub
codex-collab
【WHEN】当用户命令中明确包含"codex协作"、"codex协同"、"与codex合作"等指令时启用； 【WHEN】当用户要求使用 codex MCP 工具进行代码分析、原型生成、review 等协作开发场景时启用。 【WHEN NOT】不用于单独的代码实现任务...
GitHub
analytic-skills-guide
Guide for AI agent to use the tools offered by this library to perform analytic tasks.
GitHub
material-design
Create UI components and designs following Google Material Design 3 (Material You) guidelines. Use when building Material UI components, implementing Material theming, working with elevation, color systems, typ...
GitHub
data-import
车险经营数据导入技能，支持CSV/JSON解析、验证、优先级管理
GitHub
chart-visualization
ECharts图表配置技能，包括柱状图、折线图、组合图等可视化组件
GitHub
data-validation
使用 Minion 框架进行智能数据验证
GitHub
kpi-calculation
KPI指标计算技能，包括目标拆解、达成率、增长率、时间进度等核心业务计算
GitHub
test-generation
使用 Minion 框架生成智能测试用例
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.