Skills for Claude Code

These skills are associated with Claude Code because their author either published them under the harness's install path or tagged the repository for it on GitHub. Both are statements of intent by the author.

Neither is a test result. We have not run any of these with and without the skill enabled, so nothing here tells you whether a skill improves output, what it adds in tokens, or whether it duplicates behaviour the harness already has. When we run that comparison, the numbers will appear here with the task, the versions and the budget.

Worked on in the last 90 days (60)

Someone pushed a commit recently. This is the shortlist worth trying first.

syahiidkamil-software-engineer-ai-agent-atlas-postgresql-optimization — last commit 2026-06-25
PostgreSQL-specific development assistant focusing on unique PostgreSQL features, advanced data types, and PostgreSQL-exclusive capabilitie…
syahiidkamil-software-engineer-ai-agent-atlas-shadcn — last commit 2026-06-25
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, compone…
syahiidkamil-software-engineer-ai-agent-atlas-skill-creator — last commit 2026-06-25
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, e…
syahiidkamil-software-engineer-ai-agent-atlas-supabase-postgres-best-practices — last commit 2026-06-25
Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries,…
syahiidkamil-software-engineer-ai-agent-atlas-super-product-owner — last commit 2026-06-25
Complete Product Owner / Product Manager capability — a wiki-style knowledge map of product practice in active software development: the ro…
syahiidkamil-software-engineer-ai-agent-atlas-super-ui-ux-design — last commit 2026-06-25
Complete UI/UX design capability — a wiki-style knowledge map of design theory (UX laws, Nielsen heuristics, usability, visual hierarchy, t…
syahiidkamil-software-engineer-ai-agent-atlas-theme-factory — last commit 2026-06-25
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set…
giuseppe-trisciuoglio-developer-kit-adr-drafting — last commit 2026-06-22
Creates new Architecture Decision Record (ADR) documents for significant architectural changes using a consistent template and repository-a…
giuseppe-trisciuoglio-developer-kit-aws-cli-beast — last commit 2026-06-22
Provides advanced AWS CLI patterns for managing EC2, Lambda, S3, DynamoDB, RDS, VPC, IAM, and CloudWatch. Generates bulk operation scripts,…
giuseppe-trisciuoglio-developer-kit-aws-cloudformation-cloudfront — last commit 2026-06-22
Provides AWS CloudFormation patterns for CloudFront distributions, origins (ALB, S3, Lambda@Edge, VPC Origins), CacheBehaviors, Functions,…
giuseppe-trisciuoglio-developer-kit-aws-cloudformation-dynamodb — last commit 2026-06-22
Provides AWS CloudFormation patterns for DynamoDB tables, GSIs, LSIs, auto-scaling, and streams. Use when creating DynamoDB tables with Clo…
giuseppe-trisciuoglio-developer-kit-aws-cloudformation-rds — last commit 2026-06-22
Provides AWS CloudFormation patterns for Amazon RDS databases. Use when creating RDS instances (MySQL, PostgreSQL, Aurora), DB clusters, mu…
giuseppe-trisciuoglio-developer-kit-aws-cloudformation-s3 — last commit 2026-06-22
Provides AWS CloudFormation patterns for Amazon S3. Use when creating S3 buckets, policies, versioning, lifecycle rules, and implementing t…
giuseppe-trisciuoglio-developer-kit-aws-cloudformation-vpc — last commit 2026-06-22
Provides AWS CloudFormation patterns for VPC foundations, including subnets, route tables, internet and NAT gateways, endpoints, and reusab…
giuseppe-trisciuoglio-developer-kit-aws-cost-optimization — last commit 2026-06-22
Provides structured AWS cost optimization guidance using five pillars (right-sizing, elasticity, pricing models, storage optimization, moni…
giuseppe-trisciuoglio-developer-kit-aws-drawio-architecture-diagrams — last commit 2026-06-22
Creates professional AWS architecture diagrams in draw.io XML format (.drawio files) using official AWS Architecture Icons (aws4 library).…
giuseppe-trisciuoglio-developer-kit-bug-fix-brief — last commit 2026-06-22
Generates a structured Bug Fix Brief (BFB) to document issue corrections. Includes root cause analysis, repro steps, fix options, and fix c…
giuseppe-trisciuoglio-developer-kit-docs-updater — last commit 2026-06-22
Provides automated documentation updates by analyzing git changes between the current branch and the last release tag. Performs git diff an…
giuseppe-trisciuoglio-developer-kit-drawio-logical-diagrams — last commit 2026-06-22
Creates professional logical flow diagrams and logical system architecture diagrams using draw.io XML format (.drawio files). Use when crea…
giuseppe-trisciuoglio-developer-kit-memory-md-management — last commit 2026-06-22
Provides comprehensive memory file management capabilities including auditing, quality assessment, and targeted improvements for files such…
giuseppe-trisciuoglio-developer-kit-pr-review-comments — last commit 2026-06-22
Posts review findings from a JSON file as inline comments on a GitHub Pull Request, attaching each comment to its file and line. Use when y…
juneyaooo-social-account-doctor-social-account-doctor — last commit 2026-06-21
小红书 / 抖音 / 快手 / 视频号自媒体「(compose 素材打底 →) 找对标 → 拆爆款 → 套自己」四命令闭环。给我的账号 / 选题方向 / 原始素材（文档/图片/视频），吐出"可发的下一条笔记初稿"。当用户说"找对标"、"拆这条爆款"、"对着这条仿写"、"下一条…
conorluddy-ios-simulator-skill-ios-simulator-skill — last commit 2026-06-18
29 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility…
orchestra-research-ai-research-skills-autoresearch — last commit 2026-06-16
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with…
orchestra-research-ai-research-skills-axolotl — last commit 2026-06-16
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
orchestra-research-ai-research-skills-constitutional-ai — last commit 2026-06-16
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision,…
orchestra-research-ai-research-skills-distributed-llm-pretraining-torchtitan — last commit 2026-06-16
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.…
orchestra-research-ai-research-skills-fine-tuning-with-trl — last commit 2026-06-16
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimi…
orchestra-research-ai-research-skills-grpo-rl-training — last commit 2026-06-16
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
orchestra-research-ai-research-skills-huggingface-tokenizers — last commit 2026-06-16
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and…
orchestra-research-ai-research-skills-implementing-llms-litgpt — last commit 2026-06-16
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need…
orchestra-research-ai-research-skills-llama-factory — last commit 2026-06-16
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support
orchestra-research-ai-research-skills-llamaguard — last commit 2026-06-16
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, subs…
orchestra-research-ai-research-skills-mamba-architecture — last commit 2026-06-16
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM wit…
orchestra-research-ai-research-skills-miles-rl-training — last commit 2026-06-16
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with F…
orchestra-research-ai-research-skills-nanogpt — last commit 2026-06-16
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By An…
orchestra-research-ai-research-skills-nemo-curator — last commit 2026-06-16
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filteri…
orchestra-research-ai-research-skills-nemo-guardrails — last commit 2026-06-16
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination…
orchestra-research-ai-research-skills-nnsight-remote-interpretability — last commit 2026-06-16
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when ne…
orchestra-research-ai-research-skills-openrlhf-training — last commit 2026-06-16
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray,…
orchestra-research-ai-research-skills-peft-fine-tuning — last commit 2026-06-16
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU me…
orchestra-research-ai-research-skills-prompt-guard — last commit 2026-06-16
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<…
orchestra-research-ai-research-skills-pyvene-interventions — last commit 2026-06-16
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conduct…
orchestra-research-ai-research-skills-ray-data — last commit 2026-06-16
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train,…
orchestra-research-ai-research-skills-rwkv-architecture — last commit 2026-06-16
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequenti…
orchestra-research-ai-research-skills-sentencepiece — last commit 2026-06-16
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6M…
orchestra-research-ai-research-skills-simpo-training — last commit 2026-06-16
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0)…
orchestra-research-ai-research-skills-slime-rl-training — last commit 2026-06-16
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom…
orchestra-research-ai-research-skills-sparse-autoencoder-training — last commit 2026-06-16
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpre…
orchestra-research-ai-research-skills-torchforge-rl-training — last commit 2026-06-16
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean…
orchestra-research-ai-research-skills-transformer-lens-interpretability — last commit 2026-06-16
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookP…
orchestra-research-ai-research-skills-unsloth — last commit 2026-06-16
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
orchestra-research-ai-research-skills-verl-rl-training — last commit 2026-06-16
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or o…
pedrohcgs-claude-code-my-workflow-audit-reproducibility — last commit 2026-06-10
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Re…
pedrohcgs-claude-code-my-workflow-capture-environment — last commit 2026-06-10
Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lock…
pedrohcgs-claude-code-my-workflow-checkpoint — last commit 2026-06-10
Save a structured state snapshot before stopping or handing off. Captures the active plan, recent decisions, file pointers (with line numbe…
pedrohcgs-claude-code-my-workflow-coauthor-brief — last commit 2026-06-10
Generate a co-author / collaborator handoff brief for a multi-author, multi-machine project — summarizing what changed since the last brief…
pedrohcgs-claude-code-my-workflow-commit — last commit 2026-06-10
Stage, commit, push, open a PR, and merge to main. Use ONLY on explicit commit intent — user says "commit", "ship it", "push this", "open a…
pedrohcgs-claude-code-my-workflow-compile-latex — last commit 2026-06-10
Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when user says "compile", "build the slides", "rebuild the PDF", "r…
pedrohcgs-claude-code-my-workflow-compress-session — last commit 2026-06-10
Distill the current conversation into a structured note (decisions made, open questions, file pointers with line numbers, next 1–3 actions)…

Page 23 of 24

How this page is ordered

Entries are grouped by whether anyone is still working on them, using the date of the most recent push to the repository. They are not ordered by stars, because a star is a bookmark somebody left once and never took back.

Where we have not checked an entry yet, it says so rather than being mixed in with the verified ones.