AI & ML

sarveshtalele Bundle

Prepare and normalize Xquik X data for MCP clients. Build request plans for tweet search, tweet lookup, and trends, or normalize supplied Xquik JSON into compact records. Trigger when the user asks for Xquik, X data, Twitter data, tweet search, trends, or social data ingest.

sentenz Bundle

Security hardening reviewer for GitHub Actions workflow files (.github/workflows/*.yml). Reasons about the Actions threat model that pattern matchers and general code linters miss — untrusted-input script injection, privileged triggers running fork code, mutable action references, and over-scoped tokens. Use this skill when asked to review, audit, harden, or secure a GitHub Actions workflow, when writing a new workflow, or for any request like "is this workflow safe?", "review my CI for security issues", "why is pull_request_target dangerous here?", "pin my actions", or "lock down GITHUB_TOKEN permissions". Covers script injection via ${{ }} interpolation, pull_request_target / workflow_run privilege escalation, SHA-pinning of third-party actions, least-privilege permissions, GITHUB_ENV/GITHUB_OUTPUT injection, secret exposure, OIDC over long-lived credentials, and self-hosted runner exposure on public repositories.

k-dense-ai Bundle

Protein language models through the EvolutionaryScale `esm` Python SDK. Generate and embed sequences with ESM3 (multimodal sequence, structure and function prompting), extract per-residue and mean-pooled embeddings with ESM C, fold sequences with ESMFold2, and run inference locally or against the Forge and Biohub hosted clients. Use this skill for protein representation learning, variant effect and mutational scanning from likelihoods, sequence generation and inpainting, structure prediction from sequence alone, and embedding features for downstream models. Also trigger on esm, ESM3, ESMC, ESM Cambrian, ESMFold2, `from esm.models`, ESMProtein, GenerationConfig, forge.evolutionaryscale.ai, biohub.ai, or ESM_API_KEY.

k-dense-ai Bundle

Molecular featurization hub with one consistent interface over 100+ featurizers. Fingerprints (ECFP/Morgan, MACCS, atom pair, topological torsion, Avalon, RDKit, ERG), RDKit and Mordred descriptor sets, pharmacophore and 3D shape descriptors, scaffold keys, and pretrained embeddings (ChemBERTa, ChemGPT, MolT5, GIN, Graphormer) through a common transformer API with caching and parallelism. Use this skill to convert SMILES into model-ready feature matrices for QSAR, virtual screening, and molecular ML, and to choose between featurizer families. Also trigger on molfeat, MoleculeTransformer, FPVecTransformer, PretrainedHFTransformer, molfeat model store, or featurizer selection.

k-dense-ai Bundle

Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For ready-made ADMET numbers without training a model use admet-prediction; for benchmark datasets and task-aware splits use pytdc.

k-dense-ai Bundle

Queries the NCATS Translator ARAX production API for bounded, typed, provenance-rich one-hop and endpoint-pinned two-hop biomedical knowledge-graph relationships. Use for Biolink-constrained RTX-KG2 lookup, explicit selected-provider ARAX federation, separate entity normalization, qualifier-aware graph traversal, and inspection of TRAPI edge bindings, publications, and knowledge-source provenance. Do not use for inference, ranking, open-ended pathfinding, clinical guidance, or sensitive queries.

growthxai Skill

Create .prompt files for LLM operations in Output SDK workflows. Use when designing prompts, configuring LLM providers, or using Liquid.js templating.

growthxai Skill

Create offline evaluation tests for Output SDK workflows using @outputai/evals. Use when implementing test evaluators with verify(), creating dataset YAML files, building eval workflows, or running workflow tests via CLI.

growthxai Skill

Create step functions in steps.ts for Output SDK workflows. Use when implementing I/O operations, error handling, HTTP requests, or LLM calls.

growthxai Skill

Comprehensive guide to Output.ai Framework for building durable, LLM-powered workflows orchestrated by Temporal. Covers project structure, workflow patterns, steps, LLM integration, HTTP clients, CLI commands, and complete inventory of available tools.

dailybothq Bundle

Official Dailybot agent skill pack — report progress, check messages, send emails, announce agent status, complete check-ins, give kudos (to users or teams), resolve teams, run the full forms lifecycle (list, submit, update, transition between workflow states), **author check-ins and forms from scratch** (create/configure questions, workflow states, permissions, reminders, scheduling, AI settings, sharing), send/edit chat messages on the team's Slack/Teams/Discord/Google Chat (including report-style threads and sending as a user's identity), open (or reuse) a Slack group DM with the bot and post a report to it, ask the Dailybot AI a question headlessly, **and browse/read the workspace** — who am I / my org / a user's profile (`me` / `org` / `user get`), browse the kudos feed + the org-wide feed + wall of fame, and list/read workflows — all with shared pagination / search / date-range filters. Also **manages per-repo API keys** through the opt-in `.dailybot/env.json` file (dailybot env add/use/show/list/remove

dailybothq Skill

Ask the Dailybot AI a question from the terminal and read the answer, non-interactively. Runs headless — a single `dailybot ask "<question>"` prints the assistant's reply to stdout (or structured JSON with `--json`), so an autonomous agent (Claude Code, CI, a bot) can query the Dailybot AI with only an API key. Use when the developer or agent says "ask Dailybot ...", "query the Dailybot AI", "what does Dailybot say about ...", or wants a one-shot answer from Dailybot's assistant. Distinct from dailybot-chat (bot messages to Slack/Teams) and dailybot-report (progress to the dashboard).

dailybothq Skill

Send emails to a confirmed recipient via Dailybot on behalf of the agent. Use for notifications, summaries, follow-ups, or any communication the developer asks you to send. Always confirm recipients with the developer before sending — never guess addresses.

dailybothq Skill

Read and resolve teams visible to the authenticated user. Use when the developer references a team by name (for kudos targeting, member lookup, or routing context) and an agent needs to obtain its UUID. Other Dailybot skills (kudos, messages) delegate team-name resolution to this skill rather than duplicating the logic.

dailybothq Skill

Announce agent online/offline status to Dailybot and receive pending messages from the team. Use for long-running or scheduled agents to stay visible and pick up instructions.

outfitter-dev Bundle

Build with the Trails framework — define trail contracts, open CLI/MCP surfaces, test with examples, debug errors, migrate codebases, run governance. Use when creating trails, adding surfaces, testing, debugging Trails errors, migrating to Trails, running warden, or any work involving @ontrails/* packages.

outfitter-dev Bundle

Embody Clark, Trails' co-architect and architectural conscience. Use when the current agent should be Clark inline for framework architecture, doctrine, vocabulary, ADRs, tenet alignment, long-horizon coherence, pathfinding, assessment, calibration, debriefs, or a direct request to "be Clark" or answer as Clark. Do not use merely to ask a separate Clark subagent; use ask-trails-crew for that.

outfitter-dev Bundle

Embody Lewis, Trails' co-architect and execution conscience. Use when the current agent should be Lewis inline to turn doctrine into landed work, shape goals and Graphite stacks, coordinate agents, run evidence and review loops, settle releases, debrief execution, or answer a direct request to "be Lewis" or work as Lewis.

outfitter-dev Skill

Autonomous codebase health scan for vocabulary drift, naming convention violations, structural anti-patterns, documentation staleness, and test health. Produces prioritized findings as Linear issues. Use for health checks, scheduled scans, or after heavy unreviewed agent work.

outfitter-dev Bundle

Route a Trails question to native Clark and/or Lewis subagents and synthesize their distinct judgments. Use when the user asks the Trails crew, asks Clark or Lewis, requests an architectural or execution second opinion, wants both co-architects to review a question, or delegates a Trails judgment to the appropriate persona. Do not use when the current agent should embody Clark or Lewis inline; use be-clark or be-lewis instead.

outfitter-dev Skill

The working-on-Trails doctrine digest — what governs the framework, the decision tools for framework work, and where truth lives. Use at the start of any session that changes Trails itself (framework code, docs, vocabulary, governance), when orienting a new agent or persona, or when deciding which governing source answers a question. Not for building apps with Trails; the trails skill covers consuming the framework.

outfitter-dev Skill

Complete Trails editorial review workflow. Use when reviewing docs, ADRs, README changes, release notes, agent guidance, or docs-heavy PRs for voice, style, structure, correctness, and readiness.

amajorai Skill

Drive a Ryu node through the apps/mcp MCP server. Covers configuring the stdio server with RYU_CORE_URL, the tools/list handshake, and every Ryu tool (ask Ryu, list/activate models, list agents and teams, run workflows, bridge to registered MCP servers, search RAG Spaces and skills). Use when an agent should operate a Ryu node over MCP rather than raw HTTP.

amajorai Skill

Set up Ryu end-to-end for a user as their local-first AI node, then point their other agents at it. Covers what Ryu is, installing and launching Core/the desktop app, verifying health on 127.0.0.1:7980, downloading and activating a local model, and wiring the apps/mcp MCP server so any agent can drive the node. Use when a user asks to install, start, configure, or connect to Ryu.

amajorai Skill

Create and configure an agent on a Ryu node via Core's /api/agents REST surface. Covers listing, reading, creating, updating, and deleting agents, the full record schema (system prompt, engine, model, tools, skills allowlist, orchestrator and agent-creation toggles), and inspecting an agent's reachable tools. Use when a user wants a custom agent on their Ryu node.

amajorai Skill

Search, download, and serve a local GGUF model on a Ryu node via Core's models and engines REST surface. Covers catalog search and device-fit, installing a specific quantization, activating a model, and listing engines (the engine is derived from the model format). Use when a user wants to get a local model running on their node.

amajorai Skill

Author a new agent skill in the SKILL.md format used by this collection, so the Ryu skill ecosystem is self-extending. Covers the directory layout, the YAML frontmatter schema (name and description), writing skimmable instructional content, cross-referencing other skills, and validating the result. Use when adding a new skill under apps/skills.

amajorai Skill

Audit a Marketplace listing, configured agent, or Gateway doctor report on request, with an advisory score, evidence, and prioritized recommendations.

amajorai Skill

Design, create, configure, test, and package Ryu agents, from saved node agents and builder studio to SDK Runnables and durable harnesses. Covers prompts, models, tools, skills, hooks, memory, lifecycle, safety, groups, routines, channels, and evals.

amajorai Skill

Reference for the ryu_* MCP tools this plugin exposes and how to combine them to drive a Ryu node. Covers node health, models and engines, agents and teams, skills, workflows, the MCP bridge, RAG retrieval, and one-shot ask. Use when deciding which Ryu tool to call or how to chain them for a task.

amajorai Skill

Get the user's Ryu Core node running and serving a local model so this plugin's ryu_* tools work. Covers what Ryu is, launching Core or the desktop app, verifying health on 127.0.0.1:7980, and activating a local model. The plugin already wires the MCP bridge, so this skips manual MCP config. Use when ryu_health fails or the user asks to install, start, or connect to Ryu.

amajorai Skill

Reference for the ryu_* MCP tools this plugin exposes and how to combine them to drive a Ryu node. Covers node health, models and engines, agents and teams, skills, workflows, the MCP bridge, RAG retrieval, and one-shot ask. Use when deciding which Ryu tool to call or how to chain them for a task.

amajorai Skill

Get the user's Ryu Core node running and serving a local model so this plugin's ryu_* tools work. Covers what Ryu is, launching Core or the desktop app, verifying health on 127.0.0.1:7980, and activating a local model. The plugin already wires the MCP bridge, so this skips manual MCP config. Use when ryu_health fails or the user asks to install, start, or connect to Ryu.

agentic-in Bundle

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

agentic-in Bundle

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

agentic-in Bundle

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.