13,658 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
JustinPerea/midjourney-cc-skill
Skill Claude CodeCodex
Use when generating images with Midjourney, constructing MJ prompts, iterating on MJ output quality, choosing between --sref/--oref/style codes, scoring image results, or building reusable prompt patterns. Also use when exploring MJ style codes, animating images, or debugging why a prompt isn't producing the intended…
Plugin Claude Code
Bundles 55 skills, 20 agents, 2 hooks · 10,686 tokens together
Usage skills for the sparq RDF triplestore + SPARQL 1.1/1.2 engine (Rust/CLI/HTTP/Python/WASM + reasoning, SHACL, full-text, vector, GeoSPARQL, RSP-QL, ZK query proofs).
GoogleCloudPlatform/cortex-framework
Skill Claude CodeCodex
Reference guide for business rules, naming conventions, and data modeling standards enforced during data product development.
aiopshwang/data-analysis-ml-agent-skills
Plugin Claude Code
Bundles 7 skills · 418 tokens together
Evidence-first AI agent skills for reliable data analysis, machine learning, and reproducible model validation.
Skill Claude CodeCodex needs its repo
A bridge that lets text-only AI models work with images by sending images to a configured image-recognition model and returning descriptions.
imkohenauser/antigravity-starter-ja
Skill Claude CodeCodex
A skill that builds a searchable map of a code repository and traces how files and named pieces of code depend on one another.
PrinceGabriel-lgtm/freshcontext-mcp
MCP server Claude CodeCodexCursor +2
Freshness-aware AI retrieval with 21 MCP tools for timestamped, decay-ranked live signals. Runs locally from the freshcontext-mcp npm package.
lebsral/DSPy-Programming-not-prompting-LMs-skills
Command Claude Code
You are a routing assistant for DSPy AI skills. Understand the user's problem, pick the best skill, and generate a ready-to-run prompt.
Plugin Claude Code
Bundles 1 skill, 1 command · 75 tokens together
Transform raw prompts into professional-grade, codebase-aware instructions. Features: 7-Layer Enhancement Framework, multi-level codebase scanning, monorepo detection, multilingual support, risk assessment, and 13 professional prompt templates.
Skill Claude Code
Export Claude Code and Codex conversation history to Hugging Face as structured training data. Use when the user asks about exporting conversations, uploading to Hugging Face, configuring codeclaw, reviewing PII/secrets in exports, or managing their dataset.
Skill Codex
Discover proven Outcomes and turn a rough request into one complete execution prompt for a fresh agent. Also author and validate source-owned Outcomes for Possible.
Cursor rule Cursor
TokenDiet honesty contract for LLM cost. Apply whenever the conversation is about LLM API cost, spend, token usage, prompt caching, batching, model choice/downgrade, or "how much will this save." Enforces: describe technical waste + published provider rates only, NEVER a fabricated dollar total.
MCP server Claude CodeCodexCursor +2
LLM-powered logical reasoning with Prolog - Calculator for logic. Runs locally from the prolog-reasoner Python package.
Skill Claude CodeCodex
Detect prompt injection, jailbreaks, and adversarial attacks in LLM inputs before processing. 5 analysis layers, F1 84.4% internal / 98.87% external, 24ms, runs offline.
menghuanshiguang/dsv-bridge-skill
Skill Claude CodeCodex
An image-understanding bridge for local AI systems that cannot read or interpret pictures. It sends images to DeepSeek’s vision mode and returns a text answer.
Plugin Claude Code
Bundles 20 skills · 2,374 tokens together
Neural network interpretability with nnsight 0.8 - tracing, intervening, patching, steering, debugging, and remote execution on NDIF.
MCP server Claude CodeCodexCursor +2
Automatic Discretization of Features with Optimal Target Association. Runs locally from the autocarver Python package.
nickstellarstreamai/ai-opportunity-finder
Plugin Claude Code
Bundles 7 skills · 399 tokens together
7 Claude skills that find hidden AI opportunities inside your company. The same Discovery Sprint methodology used by Morningside AI on $15K consulting engagements.
Skill Claude CodeCodex
Optimizes prompts using full GEPA methodology (Genetic-Pareto Evolution). Use when user wants to improve a prompt's accuracy on test cases, mentions "optimize prompt", "improve prompt", or has examples of desired input/output pairs. Implements Pareto frontier selection, trace-based reflection, and crossover mutations.
Skill Claude CodeCodex
Run a single prompt across multiple LLMs in parallel via OpenRouter, then synthesize their responses into one answer with a judge model. Use when the user wants multi-model fusion, ensemble LLM queries, parallel model comparison, or a second opinion across providers.
Skill Claude CodeCodex
Job-level health: cluster alive, step lag, slowdown proxy, comm trend.
Plugin Claude Code
Bundles 12 skills · 844 tokens together
Skills for the Memgraph graph database: Cypher, data modeling, indexes, algorithms, query modules, and GraphRAG.
aristoteleo/awesome-skill-generate
Skill Claude CodeCodex
Run or adapt dynamo preprocessing with dynamo.preprocessing.Preprocessor, including the recipe branches monocle, seurat, sctransform, pearsonresiduals, and monoclepearsonresiduals. Use when converting or reproducing docs/tutorials/notebooks/100tutorialpreprocess.ipynb, preprocessing an AnnData object for downstream…
Skill Claude CodeCodex
Creates detailed English natural-language image prompts for NSFW scenes, including nudity, erotic clothing, solo play, sex toys, partnered intercourse, oral/manual/body stimulation, multi-participant compositions, exhibitionism, bondage, rough play, fluids, fantasy partners, and explicitly requested restricted or…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: