MLOps
模型部署、评估与运维
grepai-embeddings-lmstudio
yoanbernabeu
Configure LM Studio as embedding provider for GrepAI. Use this skill for local embeddings with a GUI interface.
hooked-model
wdavidturner
Use when asked to "build habit-forming products", "Hooked model", "trigger action reward investment", "create sticky behavior loops", or "design habit loops". Helps design products that form unprompted user habits. The Hooked Model (created by Nir Eyal) explains how products create habits through Trigger, Action, Variable Reward, and Investment.
convert-elixir-elm
aRustyDev
Bidirectional conversion between Elixir and Elm. Use when migrating projects between these languages in either direction. Extends meta-convert-dev with Elixir↔Elm specific patterns. Use when migrating server-side Elixir logic to frontend applications, translating BEAM concurrency patterns to The Elm Architecture, or refactoring Elixir codebases for browser-based UI. Extends meta-convert-dev with Elixir-to-Elm specific patterns.
grepai-embeddings-openai
yoanbernabeu
Configure OpenAI as embedding provider for GrepAI. Use this skill for high-quality cloud embeddings.
convert-elm-elixir
aRustyDev
Convert Elm code to idiomatic Elixir. Use when migrating Elm frontend applications to Elixir (Phoenix LiveView), translating Elm's functional patterns to Elixir, or refactoring Elm codebases to leverage OTP. Extends meta-convert-dev with Elm-to-Elixir specific patterns.
product-led-growth
wdavidturner
Use when asked about "product-led growth", "PLG strategy", "self-serve growth", "freemium model", "free trial design", "product-led sales", "PQL", or "bottoms-up growth". Helps design and optimize product-led growth motions where the product drives acquisition, activation, and monetization. Based on frameworks from Elena Verna and Hila Qu.
metrillm
MetriLLM
Benchmark local LLM models — measures performance (tok/s, TTFT, memory), quality (reasoning, math, coding, instruction following, structured output, multilingual), and computes a hardware fitness verdict. Works with Ollama.
growth-loops
wdavidturner
Use when asked to "growth loops", "build a growth engine", "design a viral loop", "create a content loop", "move beyond paid acquisition", or "why isn't growth compounding". Helps design self-reinforcing growth systems where output becomes input. The Growth Loops framework (from Brian Balfour / Reforge and Elena Verna) shifts thinking from linear funnels to compounding loops.
depresearch
Quintui
CLI tool for AI-powered research of open-source repositories. Use when you need to understand how a feature works in an external codebase without cloning it yourself.
dlt-dagster
untitled-data-company
Runs dlt pipelines in Dagster as software-defined assets (Component or Pythonic @dlt_assets) or as a single standard Dagster asset. Use when orchestrating dlt with Dagster; scaffolding loads.py/defs.yaml; jobs/schedules; secrets/env; incremental/backfill via apply_hints; parallelization (one asset per resource); Dagster Cloud deployment; or external compute (ECS, Fargate — refer to dagster-integrations). Triggers: dagster-dlt, dlt on Dagster, deploy dlt with Dagster, standard Dagster asset, external compute.
dlt-skill
untitled-data-company
Creates and maintains dlt (data load tool) pipelines from APIs, databases, and other sources. Use when the user wants to build or debug pipelines; use verified sources (e.g. Salesforce, GitHub, Stripe) or declarative REST API or custom Python; configure destinations (e.g. DuckDB, BigQuery, Snowflake); implement incremental loading; or edit .dlt config and secrets. Use when the user mentions data ingestion, dlt pipeline, dlt init, rest_api_source, incremental load, or pipeline dashboard.
affiliate-motivation-and-training
dmend3z
This skill equips the agent to motivate and train affiliate partners effectively. It should be used for tasks like creating weekly updates, sharing success stories, developing training modules, writing personal outreach scripts, planning reactivation campaigns, and designing performance coaching and incentive programs.
ClawdStrike
cantinaxyz
"Security audit and threat model for OpenClaw gateway hosts. Use to verify OpenClaw configuration, exposure, skills/plugins, filesystem hygiene, and to produce an OK/VULNERABLE report with evidence and fixes."
prompt-engineer
repo-phuocdt
Transform rough prompts/ideas into production-ready LLM prompts. Use when crafting, refining, or optimizing prompts for any AI model (Claude, GPT, Llama, etc.) with advanced techniques like CoT, constitutional AI, RAG optimization.
Article Pipeline
0xAxiom
Ratio: 5:2 (1250x500px) for X Articles
codex
Zpankz
Execute OpenAI Codex CLI for code analysis, refactoring, and automated editing. Also use for delegating complex debugging and research to GPT models for second opinions.
ctxsift-install
aakashH242
CtxShift is a skill that helps you focus on your tasks by reducing context clutter and enabling faster state recollections. \
the-vm-standard
front-depiction
The VM Standard - inviolable covenants governing View Model architecture in this codebase. These covenants SHALL NOT be violated under any circumstance.
copilot-invoke-once
igamenovoer
Programmatically invoke GitHub Copilot CLI via the copilot command (headless -p, --silent, --stream on off, --resume/--continue) to automate tasks like producing code review notes for specific files/dirs, investigating an issue, or drafting an implementation plan. Use when you need scriptable, non-interactive Copilot runs with optional streaming progress and session continuation.
rusty-page-indexer
Algiras
High-performance semantic indexing and retrieval of local PDF and Markdown files with multi-repo support.
effect-ai-provider
front-depiction
Configure and compose AI provider layers using @effect/ai packages. Covers Anthropic, OpenAI, OpenRouter, Google, and Amazon Bedrock providers with config management, model abstraction, and runtime overrides for language model integration.
explore-dnn-model
igamenovoer
Manual invocation only; use only when the user explicitly requests explore-dnn-model by name. Explore how to run a given DNN model checkpoint in the current Python environment by locating weights + upstream source code, resolving dependencies with user confirmation, running reproducible experiments under tmp/, and producing reports about I/O contracts, timing, and profiling.
context-engineering
Zpankz
Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
matlab-medical-imaging-toolbox
rrmaram2000
"MATLAB Medical Imaging Toolbox. Functions - medicalVolume, dicomread, dicominfo, dicomCollection, niftiread, niftiinfo, nrrdread, medicalref3d, intrinsicToWorld, worldToIntrinsic, volshow, sliceViewer, imregmoment, imregdeform, imregtform, radiomics, intensityFeatures, shapeFeatures, textureFeatures, medicalSegmentAnythingModel, segmentCells2D, dicomConnection, dicomquery, dicomget. Tasks - load medical scans, read DICOM series, open NIfTI or NRRD files, convert patient and voxel coordinates, visualize 3D volumes, overlay segmentation, align MRI or CT scans, register pre and post treatment images, extract radiomics features, segment with MedSAM or Cellpose, connect to PACS server, label ground truth, resample to isotropic spacing. Domains - DICOM, NIfTI, NRRD, MRI, CT, PET, PET/CT fusion, ultrasound, X-ray, brain imaging, liver segmentation, cardiac imaging, lung nodules, tumor analysis, clinical workflows, PACS integration."