AI & ML

mattolson Skill

Add a new AI coding agent to Agent Sandbox. Creates all required files (Dockerfile, templates, CI, docs) and wires the agent into the CLI, proxy, and build system.

mattolson Bundle

Read this when you are an AI coding agent running inside an Agent Sandbox container. Explains the network proxy, allowlist policy, filesystem/git constraints, how to discover your own limits from the read-only .agent-sandbox directory, how to use GitHub (issues, pull requests, CI) through `gh api`, and what to do when a request fails with "Blocked by proxy policy" (HTTP 403) or a direct connection is refused. Use it before fighting a network/permission error or concluding a tool is broken.

snapsynapse Bundle

Version, validate, package, verify, recover, and hand off Agent Skill bundles across local folders, registries, platform uploads, and agent sessions. Use for MANIFEST.yaml, CHANGELOG.md, bundle hashes, stale evals, frontmatter portability, derived skill packages, or version identity that must survive filename changes and cross-platform movement. Do not use for ordinary Git version control that does not involve an Agent Skill bundle. Compatible with the agentskills.io open standard.

cryptorugmunch Skill

Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What GitNexus tools are available?", "How do I use GitNexus?"

avivk5498 Bundle

Bootstrap lean multi-agent orchestration with beads task tracking. Use for projects needing agent delegation without heavy MCP overhead.

lightly-ai Skill

Read before adding or changing backend code in lightly_studio - FastAPI routes, services, resolvers, SQLModel tables, or database access. Explains the api/services/resolvers/models layering, the Base/Create/Table/View model split, request flow, error handling, DuckDB and PostgreSQL persistence, Alembic migrations, and how to navigate the package.

getsentry Bundle

Manage dotagents dependencies and runtime config. Use when asked to "add a skill", "install skills", "remove a skill", "configure plugins", "configure subagents", "dotagents init", "agents.toml", "agents.lock", "sync skills", "list skills", "set up dotagents", "configure trust", "add MCP server", "add hook", "wildcard skills", "global scope", "project scope", "dotagents doctor", or any dotagents-related task.

tokamak-network Skill

You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its qu

tokamak-network Skill

Use when working with code refactoring context restore

tokamak-network Skill

Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.

henmessi Skill

Branch skill for building and improving hooks. Use when creating new hooks, adapting marketplace hooks, validating hook structure, writing hook scripts, or improving existing hooks. Triggers: 'create hook', 'improve hook', 'validate hook', 'fix hook', 'PreToolUse', 'PostToolUse', 'Stop hook', 'hook script', 'adapt hook', 'prompt hook', 'command hook'.

kart-rc Skill

AI-powered PR Author Agent that transforms Observability Diff Plans into Pull Requests. Use when: (1) Generating instrumentation code from Scout Agent output, (2) Creating OTel configuration, correlation headers, lineage specs, (3) Scaffolding telemetry validation tests, (4) Creating GitHub/GitLab PRs with observability artifacts. Triggers: "generate PR from diff plan", "create instrumentation PR", "scaffold observability code", "generate OTel config".

worldwonderer Bundle

把长视频按 Agent 选择的原片区间剪成短片。作为两阶段创作流程中的剪辑环节，读取 clip_plan.json 与源视频， 输出 edited_source.mp4；随后 Agent 按输出时间线写 narration.json。单独调用且未传 --no-narration-map 时， 仍支持旧版单阶段路径，把原片时间的 narration.json 映射为 narration_mapped.json。 触发词：视频剪辑、剪辑式解说、video cut、clip plan、拼剪。

worldwonderer Bundle

从输入视频端到端生成中文解说成片。用户提供 .mp4 / .mov / .mkv / .webm，并要求添加旁白、 配音、总结、短剧/电视剧/电影/纪录片/科普解说时使用。负责编排 video-* 技能链：视频理解 → Agent 制定故事与视听方案 → 剪辑 → 配音 → 合成。触发词：视频解说、视频旁白、生成解说、 视频 recap、video recap、voiceover、narration、auto-dub、recap。

timogilvie Bundle

Expand Linear issues into comprehensive task packets that enable autonomous AI agent execution with minimal oversight. Transforms brief issue summaries into detailed specs with context, constraints, success criteria, and validation steps.

stablyai Bundle

Verify that an application works correctly using `stably verify`. Use when an AI agent has made code changes and needs to validate the feature works in a real browser. The command describes expected behavior in plain English and reports a PASS/FAIL/INCONCLUSIVE verdict — no test files generated. Triggers on: "verify this works", "stably verify", "check if this works", "validate my changes", "verify my feature", "does this work", "check the app", "verify the feature".

stablyai Bundle

AI rules for writing tests with Stably Playwright SDK. Use this skill when writing or modifying Playwright tests with Stably AI features. Covers when to use Playwright vs Stably methods, plus minimal patterns for aiAssert, extract, getLocatorsByAI, agent.act, Inbox, and Google auth.

kasture-rohit Bundle

An MCP server that interfaces with VMware Aria Operations to run regulatory compliance checks (ISO 27001, PCI DSS, CIS, etc.) against the VCF environment.

sandgrouse Bundle

Adobe Express environment essentials, two-runtime architecture, project setup, and MCP server configuration. Use when starting add-on development, understanding iframe vs sandbox boundaries, configuring MCP servers, setting up local projects, or validating manifest configuration.

yibeichan Bundle

State-space models (SSMs) for fMRI analysis: HMM, HMM-MAR, sticky/HDP-HMM, IO-HMM, SLDS, rSLDS, SNLDS. Covers resting-state, task-based (MID, SST, N-back), and naturalistic fMRI (movie, gaming). Python code generation (hmmlearn, ssm, pyhsmm, osl-dynamics, glhmm), HRF-aware modeling, fMRIPrep/XCP-D preprocessing, CIFTI/parcellation/ICA, model selection, and single-subject + group-level inference. Trigger keywords: HMM on brain data, brain state dynamics, dynamic FC, switching dynamics, latent states from BOLD, HRF deconvolution for state models, SLDS/rSLDS on neural timeseries, choosing K for fMRI, state-space + neuroimaging, task paradigms (MID, SST, N-back, movie-watching) with dynamic/latent-state analysis, temporal dynamics beyond standard GLM.

yibeichan Bundle

BIDS standard for all data types — MRI, DWI, PET, EEG, MEG, iEEG, fNIRS, behavioral, annotations, motion capture, microscopy, physiology, and multi-modal datasets. Covers BIDS naming conventions (entities, suffixes, extensions), dataset creation, modality-specific conversion tools (heudiconv, dcm2bids, MNE-BIDS, pypet2bids), validation, project directory layout (sourcedata, rawdata, derivatives, code, stimuli, phenotype), derivatives organization, DataLad version control, multi-experiment projects, and sharing on OpenNeuro. Trigger keywords: BIDS dataset, BIDS format, BIDS naming, BIDS entities, BIDS convert, organize project, project structure, rawdata, derivatives, sourcedata, phenotype, participants.tsv, dataset_description.json, multi-modal BIDS, behavioral data BIDS, EEG BIDS, DWI BIDS, PET BIDS, annotation data, research data management, DataLad, OpenNeuro, data sharing.

chaseai-yt Skill

Recommend a model and a scoped handoff for a task in Claude Code or Codex. Use when choosing who should handle a task, seeking a second opinion, getting unstuck, or delegating focused work; execute one handoff when requested.

chaseai-yt Bundle

SUPERSEDED by /claudex-loop (formerly /crucible; adds a Phase 0 research/recon pass + rebuilt interview) — prefer that skill unless you explicitly want this one. Two-act plan hardening. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan or design, one question at a time, recommending an answer for each and exploring the codebase when it can answer itself, until every branch of the decision tree is resolved. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-me-codex", "grill me then have codex review", "grill me and stress-test the plan", "interview me about this plan then get a second model on it", or is about to build something high-stakes (auth, schema, concurrency, migrations, payments) and wants both alignment AND a cross-mo

chaseai-yt Bundle

SUPERSEDED by /claudex-loop (formerly /crucible; its docs-aware mode covers this variant) — prefer that skill unless you explicitly want this one. Two-act plan hardening with living documentation. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan, one question at a time, challenging it against your project's existing domain model and glossary (CONTEXT.md), sharpening fuzzy terms, stress-testing with concrete scenarios, cross-referencing code, and updating CONTEXT.md + ADRs inline as decisions crystallise. ACT 2 (Claude ↔ Codex) — Claude writes the locked plan to PLAN.md and OpenAI Codex adversarially reviews it in a read-only sandbox (VERDICT:APPROVED/REVISE), Claude revises and re-submits to the SAME Codex session until APPROVED or a MAX_ROUNDS cap, then you sign off before any code. Use when the user says "/grill-with-docs-codex", "grill me against the docs then have codex review", "stress-test this against our domain model then get a second model on it", or is about to build something

showcase-gig-platform Bundle

Create and iteratively improve Cursor Agent Skills using the Anthropic skill-creator workflow. Use when the user wants to create a skill from scratch, refine an existing skill with test prompts and feedback, or follow a structured draft→test→review→improve loop for skills.

famaoai-creator Bundle

Kyberion sovereign operator system — governed mission control, pipeline execution, knowledge management, approval workflows, and bidirectional knowledge sync for enterprise operators (SBI group). Use when the operator needs to run Kyberion pipelines, create/track missions, search the knowledge base, manage approval gates, export audit trails, or sync knowledge between Cowork and Kyberion.

famaoai-creator Skill

Coordinate Claude Code work with Kyberion by capturing the user prompt, opening or resuming a governed mission, selecting the right preference profile, and closing with an explicit review handoff.

jarmak-personal Skill

Translates task requirements into Codex CLI commands. Used by codex-driver agent to execute coding tasks via OpenAI Codex.

jarmak-personal Skill

Translates task requirements into Cursor CLI commands. Used by cursor-driver agent to execute coding tasks via Cursor.

jarmak-personal Skill

Translates task requirements into Gemini CLI commands. Used by gemini-driver agent to execute coding tasks via Google Gemini.

jarmak-personal Skill

Translates task requirements into GitHub Copilot CLI commands. Used by copilot-driver agent to execute coding tasks via Copilot.

jarmak-personal Skill

Intelligently routes and delegates coding tasks to the best AI agent (Codex, Cursor, Gemini, Copilot). Use /delegate <task> to automatically pick the optimal agent based on task type and complexity.

ggprompts-tabzbeads Bundle

Control Chrome browser via 71 MCP tools - screenshots, clicks, forms, downloads, network capture, TTS, history, cookies, emulation. Use when working with browser automation.

thudm Skill

Guide for adding and validating evaluation dataset configuration in slime. Use when user wants to configure eval datasets via --eval-config or --eval-prompt-data, add per-dataset overrides, or customize evaluation rollout behavior.

flox Skill

CUDA and GPU development with Flox. Use for NVIDIA CUDA setup, GPU computing, deep learning frameworks, cuDNN, and cross-platform GPU/CPU development.

flox Skill

Manage reproducible development environments with Flox. **ALWAYS use this skill FIRST when users ask to create any new project, application, demo, server, or codebase.** Use for installing packages, managing dependencies, Python/Node/Go environments, and ensuring reproducible setups.