AI & ML

raine Skill

The agent debates an opponent LLM through a multi-turn conversation, then synthesizes the best approach and implements.

raine Skill

How to invoke the consult-llm CLI. Canonical reference for the invocation contract, flags, stdin/stdout format, and multi-turn. Load this before calling consult-llm from any workflow skill (/consult, /collab, /debate, /collab-vs, /debate-vs).

raine Skill

Standalone multi-model code review of an existing diff. Multiple LLMs review in parallel; agent deduplicates, prioritizes by severity/confidence, and optionally applies localized fixes.

langchain-ai Skill

Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt, and save the refined version. Use this once outcomes exist; use bootstrap-repo-analysis for a cold-start repo.

langchain-ai Skill

First-time analysis of a repository with no prior reviewer outcomes. Crawl historical merged-PR review feedback with the gh CLI (plus any preloaded samples), extract the team's review norms, and synthesize the initial per-repo review-style prompt. Use this for a cold-start repo; use continual-learning instead once the reviewer has accumulated finding outcomes.

doronz88 Bundle

Maintain the batched TSS-prefetch list of peripheral updaters (`PREFETCHABLE_UPDATERS` in `pymobiledevice3/restore/tss.py`). Use when onboarding a new device model, debugging a TSS rejection of the combined POST, or extending the prefetch to cover additional chips (e.g. Cryptex1, Timer, TCON, future Apple peripherals). Walks through enumerating candidates from `PreflightInfo.DeviceInfo`, adding entries safely, and validating with a non-destructive dry-run before a live restore.

doronz88 Bundle

Operate iOS and iPadOS devices with pymobiledevice3, from a local checkout or straight from PyPI via uvx on a fresh workstation. Use when an agent needs to inspect a connected device, collect logs or crash data, browse or copy files, manage apps, profiles, or backups, use developer services such as DDI/DVT/tunnels/sysmon/screenshots/simulated location, automate Safari or WebViews through WebInspector or WDA, write Python scripts against the pymobiledevice3 library, or add a thin repo-native device command on top of existing services. Prefer existing CLI and service modules, choose USB vs --rsd/--tunnel correctly, and require explicit user intent before state-changing or destructive actions.

easonc13-agent-sui-skills Bundle

Collection of AI agent skills for Sui blockchain development. Includes Move smart contract development, test coverage analysis, on-chain contract decompilation, and agent wallet management.

mergisi Skill

Trigger when the user asks which model to use, wants to compare model costs, says "what's cheapest for this task", "should I use Opus or Sonnet", "can a smaller model handle this", or "/model-cost-compare". Estimates token cost across Opus 4.6, Sonnet 4.6, GLM-5.1, Minimax M2.7, and local Gemma 4, then recommends the cheapest model capable of the task.

youdotcom-oss-agent-skills Bundle

Route research tasks between a cost-conscious agentic search workflow, You.com Research API scripts, and managed or payment-aware MCP fallback.

ceshine Bundle

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends the agent's capabilities with specialized knowledge, workflows, or tool integrations.

ceshine Skill

Retrieve the Markdown version of a public web page from a URL using the agent's built-in URL fetch capability and markdown.new. Use when a user asks for page content in Markdown, cleaner extracted page content for LLM use, or URL-to-Markdown conversion.

ceshine Bundle

Generate a commit message for staged git changes. Use this when the user wants a commit message, asks to summarize staged changes for a commit, or invokes a prompt that should draft a commit message from the index.

lherron Skill

Propose structured interpretations of underspecified requests. Use when a user's request is vague or incomplete but reasonable assumptions can be made. Rapidly prototypes intent by restating, structuring, and committing to a next action.

rbrown101010 Bundle

Use the genmedia CLI to search, inspect, run, and manage 1200+ fal.ai model endpoints. Trigger when the user mentions "genmedia", "fal CLI", or asks to "search models", "run a model", "fetch schema", "check pricing", "upload to fal", "queue async job", "track request", or any direct interaction with the fal.ai endpoint catalog. This is the foundational skill. Every other fal.ai-related skill in this repo executes its work through genmedia commands. Use `--json` whenever the output will be parsed by an agent.

rbrown101010 Bundle

Use when a user wants to search, export, organize, or automate Readwise or Reader data from Codex or another terminal agent, especially when browser auth should be avoided and an access token is available.

yimwoo Skill

Quick project status report synthesized from state files, artifacts, and git activity. No agent dispatch (<2s).

yimwoo Skill

Full specialist analysis via parallel agent dispatch. Researcher, Architect, and PM produce a prioritized report of what to build next (30-60s).

nvidia-nemo Skill

Verify a NeMo Speech change or pull request before commit, push, or review by checking the complete diff, formatting, tests, documentation, and DCO sign-offs. Use when asked to verify changes, prepare a commit or PR, or review a PR's validation and coverage.

nvidia-nemo Skill

Fix a GitHub issue in NeMo Speech (NVIDIA-NeMo/Speech). Read the issue, reproduce the bug with a failing test, implement the fix, and verify tests pass. Only opens a PR if the user explicitly asks for it.

nvidia-nemo Skill

Debug distributed training failures (NeMo, Megatron, PyTorch) from worker stderr logs and optional AIStore daemon logs. Finds root cause across NCCL timeouts, data loading errors, and storage failures.

nvidia-nemo Bundle

Guide NeMo Speech users through ASR fine-tuning with container setup and Lhotse training.

alirezarezvani Skill

Behavioral guardrails for LLM-assisted coding. Use when writing, reviewing, or refactoring code in any project to avoid overcomplication, keep changes surgical, surface assumptions early, and execute against verifiable success criteria.

lukerenton Skill

Builds new Claude Code agents with consistent structure, enforced standards, and project-aware configuration. Use when creating a new agent, when the user describes a specialised role they want delegated to, or when discussing team composition.

lherron Skill

Ground-up conceptual modeling partner for complex systems. Use when asked to rethink a system's conceptual model, define core nouns and invariants, reconcile mismatched terms across APIs/UI, map lifecycles/edges, or create a shared vocabulary and boundaries for a refactor or redesign.

pluginagentmarketplace Bundle

LLM architecture, tokenization, transformers, and inference optimization. Use for understanding and working with language models.

pluginagentmarketplace Bundle

AI agent development with LangChain, CrewAI, AutoGen, and tool integration patterns.

pluginagentmarketplace Bundle

Prompt design, optimization, few-shot learning, and chain of thought techniques for LLM applications.

berea-ch Skill

Speakeasy workflow: run 'agent context' FIRST, do task, run 'agent feedback' LAST. Triggers on speakeasy, SDK, OpenAPI.

elliotchen Skill

Use when the user asks about Claude Code internals, how tools/commands/skills differ, what the Harness does, how the system prompt is assembled, or wants to understand the architecture from startup to response. Also use when user asks "how do you work", "what can you do", "what tools do you have".

elliotchen Bundle

Automate browser interactions, test web pages and work with Playwright tests.

celo-org Bundle

ERC-8004 Agent Trust Protocol for AI agent identity, reputation, and validation on Celo. Use when building AI agents that need identity registration, reputation tracking, or trust verification across organizational boundaries.

glittercowboy Bundle

Orchestrator for WebView UI mockup workflow - delegates design iteration to ui-design-agent and implementation scaffolding to ui-finalization-agent. Use when user mentions UI design, mockup, WebView interface, or requests 'design UI for [plugin]'.

glittercowboy Bundle

Multi-agent parallel investigation for complex JUCE problems. Use when troubleshooting fails after Level 3, problems require novel research, or user requests /research command.

n24q02m Skill

Structured comparison of 2+ alternatives with consistent criteria and decision matrix

n24q02m Skill

Verify a claim using adversarial search — find both supporting AND contradicting evidence