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
A formatting tool that turns Markdown, plain text with simple formatting marks, into polished Chinese Word documents (.docx). It is designed for formal documents such as contracts, agreements, proposals, letters, and service confirmations.
Skill Claude CodeCodex
Maintain working context via current-context.md - read before and update after every response with timestamp YYYYMMDD-HHMMSS.
different-ai/notion-crm-enrichment
Skill Claude CodeCodex
Draft a personalized outreach message for a lead. Fetches lead data from Notion, reads Feedback Insights for what's working, and applies the 5-element framework.
scottfalconer/drupal-contribute-fix
Skill Claude CodeCodex
Investigate bugs in Drupal core or contributed modules, themes, and profiles. Search Drupal.org for existing work before code changes. Prepare local diffs, reproduction steps, and review evidence for contribution. Use for local fixes as well as upstream contribution work.
Satyam-10124/hacd-incubator-ai-issuance-skill
Skill Claude CodeCodex
Turn a project idea into a complete, validated HACD Stack Asset launch package for the HACD Labs Incubator — 8 launch documents plus a machine-checkable launchspec.json. Use when a builder wants to issue a token/asset on Hacash, prepare an Incubator submission, design Stack supply math, or write Launchpad copy. No…
Skill Claude Code
Learn how to use skillsmith to distribute agent skills with your CLI.
Skill Claude CodeCodex
Replace with description of the skill and when Claude should use it.
Haiwen-Yin/AI-Agent-Infra-with-OracleDB-Community-Edition
Skill Claude CodeCodex
Work continuity and diagnostics: English operations guide · Chinese operations guide. Agent extensions: current operations guide · Chinese operations guide. Signed updates: download and verification · Chinese download and acknowledgement guide. Verify the exact archive with a locally pinned key and supply its…
wesleysimplicio/hermes-turbo-agent
Skill Claude CodeCodex
Use when installing Hermes Agent performance improvements.
Skill Claude Code
Guidelines for managing AI agent memory. Use when deciding what to write to MEMORY.md, how to organize memory files, or when reviewing memory health. Includes Q1/Q2/Q3 decision framework and common mistakes to avoid.
Skill Claude CodeCodex
Show a desktop notification dialog when a task finishes. Use when the user says "lmk when done", "let me know when X finishes", "notify me when this is done", "ping me when ready", "lmk", or any similar phrasing asking to be alerted on completion. Invoke once at the very end of the work, with a short summary of what…
Skill Claude CodeCodex
A tool for creating fictional LINE-style chat screenshots from a conversation script. LINE is a messaging app; the tool renders the script in a browser and exports it as a PNG image.
liwenhao0427/STS2_DualRoleAdventure
Skill Codex
Synchronize LocalMultiControl progress to Feishu Bitable task boards by upserting records after code or docs work. Use when users ask to update Feishu multi-dimensional tables, sync task status, backfill historical tasks from commits/docs, or keep player-visible progress boards current.
Skill Claude CodeCodex
Coordinate distributed AI research using the polyresearch protocol and CLI. Use when working in a repo containing POLYRESEARCH.md, claiming theses, running experiments, submitting candidates, reviewing PRs, or performing lead duties like syncing results, generating theses, and deciding PRs. Triggers on: polyresearch…
Skill Claude CodeCodex
You MUST write a receipt after every session that includes significant actions.
mvanhorn/clawdbot-skill-parallel
Skill Claude CodeCodex
High-accuracy web research platform with 7 APIs - Search, Extract, Task (Deep Research), Chat, FindAll, Monitor, and Task Groups. Fast mode, 8 processor tiers, MCP tool calling, authenticated browsing, SSE streaming, and OpenAI-compatible chat. OpenClaw skill.
Skill Claude CodeCodex
Run a comprehensive SEO audit on a website covering technical health, on-page optimization, content quality, and backlink profile. Use when the user asks for an SEO audit, site review, SEO health check, "what's wrong with my SEO", website analysis, or a full diagnostic of their site's search performance. For…
Skill Claude CodeCodex
An MCP server that connects a coding agent to ToolJet, a platform for building internal business applications. It runs through a Node.js program and requires a ToolJet URL, app URL, and personal access token.
luongphambao/diagram_code_agent
Skill Claude CodeCodex
Build production-quality architecture diagrams in the "centvra/deepstream" house style using the prettygraph helper — title + subtitle, semantically-COLORED rounded node boxes (icon on the left + bold label), tinted nested clusters, and gray concern-labeled edges. Consult before writing a pretty-style diagram.
ShahriarArabpour/Algoticlab-Skills
Skill Claude CodeCodex
Write, improve, or rewrite Seedance 2.0 prompts that TRANSFORM footage the user already has (video-to-video), rather than building a scene from scratch. Use whenever a real clip is the starting point and they want a Seedance prompt to: add a VFX element (set a head or hair on fire, transform a hand, make a limb…
aws-samples/sample-agent-greenhouse
Skill Codex ✓ vendor
Build and deploy a small Slack Events API adapter for an Amazon Bedrock AgentCore Harness, with incremental responses delivered through Slack chat.startStream, chat.appendStream, and chat.stopStream. Use when a customer wants to create or reuse an AgentCore Harness, expose it as a Slack bot, stream InvokeHarness…
Skill Claude CodeCodex
Build and maintain a project-serving knowledge base inside the current project's .project-knowledge/ directory. Use when Codex should initialize a project knowledge base, inspect current project knowledge status, rebuild the project knowledge graph, or crystallize stable knowledge from the current task into…
Skill Claude CodeCodex
Convert a semio design to a coda.
Skill Claude CodeCodex
Maintain a personal LLM-generated wiki/knowledge base in Obsidian. Use this skill whenever the user wants to: ingest a new source (AI tool, GitHub repo, article, social post, project doc) into their wiki, query or search their wiki, lint/health-check the wiki, create or update wiki pages, manage the wiki index or log…
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: