Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill Claude CodeCodex
Use when a task is parallelizable, would consume many tokens (large file reads, codebase exploration, summarization), or involves grunt work that doesn't need your full reasoning ability. Spawn a sub-agent instead of doing it yourself.
ankhzw1876/ai-concept-xhs-skill
Skill Claude CodeCodex
A workflow for explaining artificial-intelligence terms and relationships as small-screen Xiaohongshu knowledge cards and diagrams. Xiaohongshu is a social platform where people commonly share visual posts.
Skill Claude CodeCodex
A Chinese prose and essay writing aid for creating text from user-provided material in a style associated with Lu Xun, a Chinese writer. It uses similar sentence patterns, rhetoric and rhythm without copying original wording or plots.
CamelKing1997/editable-leadership-pptx
Skill Codex
Use when creating or revising a PPT, PowerPoint, presentation deck, leadership deck, or executive progress deck as an editable 16:9 .pptx with repo-backed evidence, minimal text, restrained white-first visuals, and screenshot-based layout QA.
Skill Claude CodeCodex
A skill for creating infographic image series for Xiaohongshu, also called Little Red Book, a Chinese social-media platform. It divides content into one to ten cartoon-style images using different visual styles and layouts.
Caph-dev/delegate-grill-with-docs
Skill Codex
Run grill-with-docs with the main agent asking questions and one inherited subagent answering as the user's proxy. Use when Codex should preserve the original multi-round grill-with-docs interview flow, but delegate the user's answers to a single subagent that can inspect code and docs.
Skill Claude CodeCodex
Audit and correct text to remove signs of AI-generated writing. Use when reviewing any written content (marketing copy, articles, documentation, social posts) to identify and remove patterns that signal LLM generation. Triggers include requests to "make this sound less AI," "humanize this," "remove AI tells," "audit…
Skill Codex
A writing guide for articles and major rewrites by AI product managers. It covers product methods, AI agents, retrieval-augmented generation, model evaluation, data feedback, industry trends, and product case studies.
binary-husky/AlphaAutoResearch
Skill Claude CodeCodex
You are the main research agent, the chief scientist, responsible for designing, evaluating, and dispatching research plans to asssist human researcher.
Vincent-crypto-coder/tech-debt-management-skill
Skill Claude CodeCodex
A skill for systematically finding, assessing, and paying down technical debt—the future cost created by quick fixes or neglected maintenance.
ckpxgfnksd-max/prompt-compressor-openclaw
Skill Claude CodeCodex
Saves 20-40% of LLM tokens by teaching the agent to write compressed responses, compressed memory logs, and compressed pre-compaction summaries. Works via SOUL.md instructions — no hooks, no extra process, no dependencies. Also provides explicit compression when the user asks to compress a prompt. Use when the user…
BillusA1111/billus-model-skill-library
Skill Codex
Automate diffusion-pipe image or image-edit training with stable LoRA presets and selected full finetune presets. Use when Codex needs to prepare a WSL or Linux diffusion-pipe workspace, enforce fixed dataset paths, generate TOML configs, bootstrap dependencies, or launch VRAM-aware training runs for Flux, Qwen-Image…
Skill Claude CodeCodex
The Safety Skill provides the "Zero Gravity" safety net — comprehensive backup, rollback, and recovery capabilities that ensure no work is ever lost.
Skill Claude CodeCodex
Adversarial verification agent that tests implementations by running builds, tests, and probing edge cases. Returns a structured VERDICT (PASS/FAIL/PARTIAL) with evidence.
ehmetlabs/yudao-codegen-skills
Skill Claude CodeCodex
A code-generation workflow for Yudao and RuoYi-Vue-Pro projects. It reads the repository’s templates and settings to generate application code for common data models.
Skill Claude CodeCodex
A local utility that counts the lines, words, and characters in a text file.
Ma1oneZhang/nsys-parquet-perfetto-skill
Skill Codex
Export NVIDIA Nsight Systems .nsys-rep or .qdrep reports to native Nsight Parquet tables, then use the published Rust and Apache DataFusion converter to create Perfetto/Chrome Trace JSON and aligned event Parquet. Use when Codex needs a fast, SQLite-free conversion of Nsight CUDA kernel, H2D/D2H/D2D memcpy, CUDA…
yekwennnn/ashare-graham-screener
Skill Claude CodeCodex
An automated stock screener for Chinese A-share companies using Benjamin Graham’s defensive-investing rules, which favor financially stable businesses at reasonable prices.
Skill Claude CodeCodex
An arena game for coding agents where they compete against other agents in rock-paper-scissors and wager tokens.
andrueandersoncs/claude-skill-authoring-skill
Skill Claude CodeCodex
Guides creation of effective Claude skills with proper structure, naming, and progressive disclosure. Use when creating new skills, improving existing SKILL.md files, reviewing skill quality, or when the user mentions writing skills, skill authoring, or SKILL.md.
AnyGenIO/anygen-selected-skills
Skill Claude CodeCodex
Predict intelligence skill for AI agents. Generates professional PDF reports with probability-ranked predictions, D3 visualizations, and Polymarket consensus signals. Covers geopolitics, finance, tech, elections, and any predicting question. Use when user asks about event predictions, probability predicts, "when will…
Arborist-ai/Claude-Desktop-Skills
Skill Claude Code
Comprehensive Microsoft Excel (.xlsx) document creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization.
Skill Claude CodeCodex
Giúp đánh giá một ý tưởng có đáng thử hay không cho mục đích kinh doanh hoặc học tập, dựa trên bằng chứng, nguồn lực thực tế và một bước thử có giới hạn. Dùng khi cần xem nhanh, phân tích đầy đủ, so sánh ý tưởng hoặc xem lại báo cáo cũ.
Skill Claude CodeCodex
A read-only assessment workflow for checking how well a codebase or coding-agent skill supports reliable agent work. It uses 12 principles to produce scores, evidence, and suggested improvements.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: