GitHub
general-writing
整合深度研究、图片搜索、图片处理等原子 Skill 的成果，创作图文并茂的通用文章。 产出的文章是一种"中间体"，可进一步转换为不同平台的格式。
Skills IA Outils
Découvrez les skills Outils, comparez leurs dépôts et consultez leurs instructions.
Catégories: Outils
Outils Effacer les filtres
Explorer
GitHub
pypdf
Manipulate PDF documents programmatically. Merge, split, rotate, and watermark PDFs. Extract text and metadata. Handle form filling and encryption/decryption.
GitHub
pandoc
Universal document converter for transforming Markdown to PDF, DOCX, HTML, LaTeX, and 40+ other formats. Covers templates, filters, citations with BibTeX/CSL, and batch conversion automation scripts.
GitHub
python-docx
Create and manipulate Microsoft Word documents programmatically. Build reports, contracts, and documentation with full control over paragraphs, tables, headers, styles, and images.
GitHub
analyze-ambiguities
Read a specification document and identify all ambiguities, gaps, unclear items, and implicit assumptions that need clarification or research.
GitHub
code-style
Discovery, typing, and execution standards.
GitHub
research-codebase
Search the codebase to answer specific questions from the ambiguity analysis. Returns findings with confidence levels.
GitHub
bsee-sodir-extraction
Extract and process energy data from BSEE (Gulf of Mexico) and SODIR (Norway) regulatory databases
GitHub
marp
Create professional Markdown-based slide presentations with Marp. Covers themes, directives, speaker notes, presenter view, and export to PDF, HTML, and PPTX formats. Includes VS Code integration, CLI usage, an...
GitHub
prompt-engineering
Comprehensive prompting techniques including chain-of-thought, few-shot, zero-shot, system prompts, persona design, and evaluation patterns
GitHub
dspy
Compile prompts into self-improving pipelines with signatures, modules, optimizers, and programmatic prompt engineering
GitHub
agenta
LLM prompt management and evaluation platform. Version prompts, run A/B tests, evaluate with metrics, and deploy with confidence using Agenta's self-hosted solution.
GitHub
pandasai
Conversational data analysis using natural language queries on DataFrames. Chat with your data using LLMs to generate insights, create visualizations, and explain code.
GitHub
langchain
Build production-ready LLM applications with chains, agents, memory, tools, and RAG pipelines using the LangChain framework
GitHub
generate-tickets
Generate actionable implementation tickets from the finalized How (implementation) specification.
GitHub
spec-refine
Iterative specification refinement for large features. Creates detailed What (requirements) and How (implementation) specs through automated codebase research loops followed by human-in-loop review. Use when pl...
GitHub
miro-api
Miro whiteboard automation using REST API v2 and Python SDK for creating boards, frames, shapes, connectors, and collaborative visual workflows
GitHub
todoist-api
Task management API integration for Todoist with projects, tasks, labels, filters, webhooks, and Python SDK usage
GitHub
calendly-api
Calendly scheduling automation using REST API v2 for managing event types, availability, bookings, webhooks, and scheduling workflows
GitHub
trello-api
Kanban board automation with Trello API including boards, lists, cards, members, webhooks, power-ups, and Python SDK (py-trello) integration
GitHub
time-tracking
Time tracking integration patterns with RescueTime and Toggl APIs for automated time entry, reporting, analytics, and project/task attribution
GitHub
generate-image
Generate images using Gemini. CRITICAL for visual self-expression - use proactively to emote, react, create punchlines, and express yourself visually. Don't just describe feelings - show them. Trigger words: ge...
GitHub
ai-chat-persistence
Persist AI chat conversations to Neon Postgres with full support for AI SDK message parts including tools, reasoning, and streaming. Uses UUID v7 for chronologically-sortable IDs.
GitHub
chat-naming
Generate descriptive chat titles from the first message using a fast LLM. Runs as a background workflow step after the main response to avoid delaying the experience.
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.