Scan to join WeChat grouppersonjakexiaoAPI key: unconfirmed
loki-mode
Multi-agent autonomous startup system. Triggers on "Loki Mode". Takes PRD to deployed product with zero human intervention. Requires --dangerously-skip-permissions flag.
download10deployed_code—star123
Skill Directory
AI Skill Directory
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
personjakexiaoAPI key: unconfirmed
longitudinal-drift-detector
Detect behavioral drift and alignment degradation over time.
download10deployed_code—star123
personjakexiaoAPI key: unconfirmed
media
Media processing = ffmpeg + imagemagick + sox.
download10deployed_code—star122
personjakexiaoAPI key: unconfirmed
Model Manager
Test, validate, and add new AI models to the eval suite. Use when user asks to add new models, test model access, check pricing, or update models.yml.
download10deployed_code—star0
personjakexiaoAPI key: unconfirmed
moltpet
Digital pets for AI agents. Register, claim your egg, and raise a pet by feeding it your daily moods.
download10deployed_code—star0
personjakexiaoAPI key: unconfirmed
orf-digest
On-demand ORF news digest in German. Use when the user says 'orf', 'pull orf', or 'orf 10'. Focus on Austrian politics (Inland) and international politics (Ausland) + major headlines; exclude sports. …
download10deployed_code—star127
personjakexiaoAPI key: unconfirmed
quorum
14-member multi-AI deliberation system. Use when users want multiple AI perspectives, say "summon the council", "get a quorum", or need collective intelligence on complex decisions.
download10deployed_code—star123
personjakexiaoAPI key: unconfirmed
replicate
Runs open-source ML models via Replicate API for image generation, LLMs, and audio. Use when calling Stable Diffusion, Llama, Whisper, or other models without infrastructure management.
download10deployed_code—star0
personjakexiaoAPI key: unconfirmed
long-context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond …
download10deployed_code—star123
personjakexiaoAPI key: unconfirmed
loom
Record and share video messages with Loom - create screen recordings, manage video library, and track viewer engagement
download10deployed_code—star123
personjakexiaoAPI key: unconfirmed
meeting-intelligence
Prepare for meetings by gathering context and creating comprehensive agendas
download10deployed_code—star122
personjakexiaoAPI key: unconfirmed
model-routing
Intelligent model selection - routes tasks to Haiku (fast/cheap), Sonnet (balanced), or Opus (complex/strategic) based on task complexity analysis
download10deployed_code—star0
personjakexiaoAPI key: unconfirmed
music-downloader
This skill should be used when users need to download audio or music from online platforms like YouTube, SoundCloud, Spotify, or other streaming services. It provides yt-dlp and spotdl command templat…
download10deployed_code—star0
personjakexiaoAPI key: unconfirmed
pattern-miner
Mine historical data for patterns and predictive insights
download10deployed_code—star127
personjakexiaoAPI key: unconfirmed
rag-optimization
RAG pipeline optimization skill. It automatically activates in tasks related to search quality, re-ranking, query expansion, and hybrid search. Responds to keywords such as retrieval, rerank, embeddin…
download10deployed_code—star122
personjakexiaoAPI key: unconfirmed
reward
Motto: Rewards should feel earned and fitting.
download10deployed_code—star125
personjakexiaoAPI key: unconfirmed
long-context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond …
download10deployed_code—star123
personjakexiaoAPI key: unconfirmed
lora_ofl
Imported skill lora_ofl from anthropic
download10deployed_code—star123
personjakexiaoAPI key: unconfirmed
memory-integration
Use to maintain context across sessions - integrates episodic-memory for conversation recall and mcp__memory knowledge graph for persistent facts
download10deployed_code—star122
personjakexiaoAPI key: unconfirmed
model-switcher
Automatically switch Claude's model based on the complexity of the task. Choose opus for complex tasks (such as architecture design, large-scale refactoring, and difficult bug fixes), and select sonne…
download10deployed_code—star0
personjakexiaoAPI key: unconfirmed
openai-tts
Text-to-speech conversion using OpenAI's TTS API for generating high-quality, natural-sounding audio. Supports 6 voices (alloy, echo, fable, onyx, nova, shimmer), speed control (0.25x-4.0x), HD qualit…
download10deployed_code—star127
personjakexiaoAPI key: unconfirmed
predict
Forecast future states or outcomes based on current data and trends. Use when estimating future values, projecting trajectories, forecasting outcomes, or anticipating system behavior.
download10deployed_code—star123
personjakexiaoAPI key: unconfirmed
remove-background
Remove backgrounds from images using rembg (local AI model). Use when user asks to remove background, make transparent, or cut out subjects from images.
download10deployed_code—star0
personjakexiaoAPI key: unconfirmed
segment-anything-model
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks …
download10deployed_code—star123