Agent Skills

by firecrawl

Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.

llama-factory

by firecrawl

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

deepspeed

by firecrawl

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

constitutional-ai

by firecrawl

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

dspy

by firecrawl

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

ml-paper-writing

by firecrawl

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.

clip

by firecrawl

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.

axolotl

by firecrawl

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

🔥🔥FreeQuick setup

llava

by firecrawl

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

model-pruning

by firecrawl

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

nemo-curator

by firecrawl

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

guidance

by firecrawl

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

autogpt-agents

by firecrawl

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

nemo-evaluator-sdk

by firecrawl

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

langchain

🔥🔥🔥✓ VerifiedFreeNeeds API keys

by firecrawl

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

long-context

by firecrawl

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

building-dashboards

by axiomhq

Designs and builds Axiom dashboards via API. Covers chart types, APL and metrics/MPL query patterns, SmartFilters, layout, and configuration options. Use when creating dashboards, migrating from Splunk, or configuring chart options.

query-metrics

by axiomhq

Runs metrics queries against Axiom MetricsDB via scripts. Discovers available metrics, tags, and tag values. Use when asked to query metrics, explore metric datasets, check metric values, or investigate OTel metrics data.

controlling-costs

🔥🔥🔥✓ VerifiedFreeAdvanced setup

by axiomhq

Analyzes Axiom query patterns to find unused data, then builds dashboards and monitors for cost optimization. Use when asked to reduce Axiom costs, find unused columns or field values, identify data waste, or track ingest spend.

axiom-sre

by axiomhq

Expert SRE investigator for incidents and debugging. Uses hypothesis-driven methodology and systematic triage. Can query Axiom observability when available. Use for incident response, root cause analysis, production debugging, or log investigation.

🔥🔥🔥🔥✓ VerifiedFree

spl-to-apl

by axiomhq

Translates Splunk SPL queries to Axiom APL. Provides command mappings, function equivalents, and syntax transformations. Use when migrating from Splunk, converting SPL queries, or learning APL equivalents of SPL patterns.

🔥🔥🔥✓ VerifiedPaid serviceNeeds API keys

filesystem-agents

★ 9

by vercel

Companion skill for the Building Filesystem Agents course on Vercel Academy. Use when the user mentions "filesystem agents", "the course", "teach me", or asks about ToolLoopAgent, Vercel Sandbox, or bash tools in the context of the Academy course.

agent-friendly-apis

★ 9

by vercel

Companion skill for the Agent-Friendly APIs course on Vercel Academy. Use when the user mentions "agent-friendly APIs", "API documentation", "llms.txt", "the course", "teach me", or asks about agent-friendly docs, documentation patterns, or building Claude Code skills in the context of the Academy course.

video-inpainting

by runcomfy-com

Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language), Lucy Edit Restyle (identity-stable region-aware restyle), and Seedream 4-0 edit-sequential (when treating the clip as a frame stack). Picks the right route based on whether the change is prose-driven, identity-locked, or needs frame-by-frame still inpaint chained into a video. Triggers on "video inpaint", "video inpainting", "remove from video", "mask region in video", "clean up video", "remove object from clip", "video patch", "frame-by-frame edit", "remove watermark from video", "remove passing person", or any explicit ask to edit a region across video frames.

happyhorse-1-0

by runcomfy-com

Generate text-to-video with HappyHorse 1.0 on RunComfy. Documents HappyHorse 1.0's strengths (#1 on Artificial Analysis Video Arena, native 1080p with in-pass synchronized audio, multi-shot character consistency, 6-language prompt support), the duration / aspect-ratio / resolution schema, and when to route to Wan 2.7 / Seedance 2 / LTX 2 instead. Calls `runcomfy run happyhorse/happyhorse-1-0/text-to-video` through the local RunComfy CLI. Triggers on "happyhorse", "happy horse", "happyhorse 1.0", "happyhorse video", or any explicit ask to generate video with this model.

image-to-video

by runcomfy-com

Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning iterations on the wrong model. Calls `runcomfy run <vendor>/<model>/image-to-video` (or endpoint variant) through the local RunComfy CLI. Triggers on "image to video", "image-to-video", "i2v", "animate image", "make this move", or any explicit ask to turn a still into video.

codex-pet

by runcomfy-com

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into `${CODEX_HOME:-$HOME/.codex}/pets/<name>/` and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as `runcomfy run openai/gpt-image-2/edit` to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no `$imagegen`, no OPENAI_API_KEY required, only RUNCOMFY_TOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

🔥✓ VerifiedFree

ai-avatar-video

by runcomfy-com

Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar), Wan-AI Wan 2-7 (audio-driven mouth sync via `audio_url` on a portrait), HappyHorse 1.0 (Arena #1 t2v / i2v with in-pass audio), and Seedance v2 Pro (multi-modal cinematic with reference audio + reference subject). Picks the right model for the user's actual intent — UGC voiceover, virtual presenter, dubbed product demo, lip-synced character, dialog scene — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "talking head", "lip sync", "avatar video", "make X speak", "audio to video", "audio driven avatar", "virtual presenter", "AI spokesperson", "dubbed video", "UGC avatar", "HeyGen alternative", "Synthesia alternative", "digital human", "make this portrait talk", "video from voiceover", or any explicit ask to put words in a face.

vercel-react-best-practices

🔥🔥🔥🔥✓ VerifiedFreeQuick setup

by vercel

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

signoz-creating-alerts

★ 6

by signoz

Create a new SigNoz alert rule from a natural-language intent: threshold, anomaly, log-volume, error-rate, latency, or absent-data alerts across metrics, logs, traces, and exceptions. Make sure to use this skill whenever the user says "alert me when…", "notify me if…", "set up monitoring for…", "page me on…", "create an alert for…", or asks for a new alert/notification rule, even if they don't say the word "alert" explicitly. Also use it when someone asks to be notified about error rates, latency spikes, log volume, CPU/memory pressure, or anomalous behavior on a service or host.