Docs Gen
Generate and maintain documentation
whisper
by G1Joshi
Whisper OpenAI speech recognition. Use for speech-to-text.
llama
by G1Joshi
Meta Llama open-source LLM family. Use for local AI.
polars
by G1Joshi
Polars fast DataFrame library. Use for fast data processing.
issue-lifecycle
by troykelly
Use throughout all work - ensures GitHub issues are updated continuously as work happens, not batched at the end
ipv6-first
by troykelly
IPv6 is THE first-class citizen. All code, tests, documentation, and configurations MUST be IPv6-first. IPv4 MAY be added only for legacy support as a second-class citizen.
project-board-enforcement
by troykelly
MANDATORY for all work - the project board is THE source of truth. This skill provides verification functions and gates that other skills MUST call. No work proceeds without project board compliance.
milestone-management
by troykelly
Use for time-based grouping of issues into delivery phases. Creates, updates, and tracks milestones, associates issues and epics, monitors progress toward milestone completion.
issue-driven-development
by troykelly
Use for any development work - the master 13-step coding process that orchestrates all other skills, ensuring GitHub issue tracking, proper branching, TDD, code review, and CI verification
openai-gpt
by G1Joshi
OpenAI GPT models API for chat, completion, and embeddings. Use for AI integration.
session-start
by troykelly
Use at the beginning of every work session - establishes context by checking GitHub project state, reading memory, verifying environment, and orienting before starting work
deferred-finding
by troykelly
Use when a review finding cannot be fixed in current PR - creates properly documented tracking issue with full context, linked to parent, following full issue-driven-development process
keras
by G1Joshi
Keras high-level neural network API. Use for deep learning.
pexels-media
by troykelly
Source royalty-free images and videos from Pexels API for design, placeholders, or content. Supports search, curated/popular content, collections, multiple resolutions, and ALWAYS creates detailed sidecar metadata files.
pre-work-research
by troykelly
Use before starting implementation - research repository documentation, codebase patterns, and external resources to inform the approach
documentation-audit
by troykelly
Use when documentation drift is detected. Comprehensively audits codebase and creates/updates Swagger, features docs, and general documentation to achieve full sync.
fastai
by G1Joshi
fast.ai deep learning library. Use for practical deep learning.
scikit-learn
by G1Joshi
Scikit-learn machine learning library. Use for classical ML.
nlm-index
by nghyane
Index documentation sites or GitHub repos to NotebookLM
Commenting Intent
by obra
Comment WHY code exists and non-obvious decisions, not WHAT code does (mechanics)
Domain-Focused Naming
by obra
Name code by what it does in the domain, not how it's implemented or its history
Taro Documentation
by whinc
This skill should be used when the user mentions "Taro" in any technical context, asks about "Taro API", "Taro components", "Taro configuration", "Taro development", "Taro project", "mini program with Taro", "WeChat mini program", uses Taro methods (like "Taro.request", "Taro.navigateTo"), or discusses multi-platform development with Taro framework. Provides comprehensive Taro framework documentation including APIs, components, configuration, and development guides.
nim
by d-wwei
Invoke various LLMs (GLM-5, Kimi-k2.5, Llama 3.1, etc.) via NVIDIA NIM API to save main agent tokens and leverage specialized model capabilities.
quill-export
by emdashcodes
Extract meeting recordings and transcripts from the Quill macOS app database. Outputs formatted markdown with speaker identification, transcripts, and metadata. Use when working with Quill meeting data.
swift-docc
by nonameplum
Official Swift DocC documentation markup and syntax reference