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 Codex
A workflow for splitting substantial work into smaller independent tasks handled by specialized subagents. It coordinates exploration, implementation, and review while keeping final decisions in the main session.
Skill Claude CodeCodex
A local usage profiler that explains how this coding agent spends tokens and reaches limits.
Skill Claude CodeCodex
Base MCP — gives your AI assistant access to a Base Account via the Base MCP server (mcp.base.org). Wallet, portfolio, sending, swapping, signing, x402 payments, batched contract calls, and transaction history across supported chains.
revfactory/claude-code-harness
Skill Claude Code
A guide to implementing a Language Server Protocol (LSP) server, the software that gives code editors features such as completion, diagnostics, and definition lookup.
Skill Claude CodeCodex
Use this skill inside a Hermes conversation when a user wants Hermes to deploy hermes-arxiv-agent end to end in either local/Feishu mode or optional GitHub Pages mode, including cloning the appropriate repo, installing Python dependencies, generating the correct cron prompt, and creating a daily cron job.
Skill Claude CodeCodex
Write the scenarios an agent is tested with, each proved against the real world before it is kept. Use whenever scenarios, test cases or a suite are wanted for an agent whose contract and world have already been built.
Skill Claude Code
Manage the Feishu/Lark bridge daemon for Claude Code and Codex. Use for: CLI install guidance, setup guidance, start/stop/status/logs/doctor, checking bridge health, or explaining how to configure the Feishu bot. This skill is Feishu/Lark-only.
Skill Claude Code
Delegate a coding task to Mistral Vibe and supervise the result via git diff. Trigger: /vibe . Claude orchestrates, Vibe codes. Also handles /vibe-report [--since N] [--project NAME] [--fails] — token/cost/failure report.
Skill Claude CodeCodex
Agent-native image workflow and optional prompt optimizer for /bananahub and generic agent image generation requests. Normalizes non-English prompts into English by default, generates or edits images across Gemini/Nano Banana, OpenAI GPT Image, chat-compatible routes, and Codex/host-native image tools when available…
Skill Claude CodeCodex
Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked…
Skill Claude CodeCodex
Generate one contrarian, non-obvious insight on whatever the user is thinking about. The thing nobody else would say.
Skill Claude CodeCodex
A command-line guide for controlling browser tabs and interacting with web pages through WebMCP. It includes commands for opening pages, switching tabs, and inspecting available page tools.
Skill Claude CodeCodex
Use when converting academic paper PDFs or structured text into professional, high-standard PowerPoint (PPTX) presentations for defense or seminars.
Skill Claude CodeCodex
Working reverse-engineered Claude Code CLI rebuilt from source analysis to reproduce the original terminal workflow.
KyrieCheungYep/ky-markdown-rebuilder
Skill Codex
Rebuild visual documents into reliable Markdown by combining text extraction with page or screenshot alignment. Use when converting or cleaning up PDFs, slide decks, PPT/PPTX files, HTML pages, long screenshots, Word-like reports, whitepapers, course materials, business decks, scanned documents, or visually dense…
Skill Claude CodeCodex
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Skill Claude CodeCodex
Multi-agent coordination layer with persistent memory. Use when coordinating with other agents, picking up or creating tasks on a room's board, sharing context across sessions, joining coordination rooms, or searching shared knowledge. Triggers on "coordinate", "negotiate", "share memory", "mycelium", "the board"…
ricardoherediaj/football-analytics-tutorials
Skill Claude CodeCodex
Build post-match team + player reports (24-chart dashboard, per-player dashboards, stats CSV) from a WhoScored URL.
Skill Codex
A skill for designing courses as sourced, checkable products that can be improved over time. It says that creating the course files alone does not mean the course is finished.
Skill Claude CodeCodex
Build a frontend with a deliberate visual direction held through palette, typography, structure, and texture, with on-screen strings that name real information rather than fabricated demo data or filler labels. Use when building or restyling a frontend.
Skill Claude CodeCodex
Research a competitor across the web and produce a cited, structured brief.
Skill Claude CodeCodex
Build and deploy a Coralogix dashboard for a given service from its logs, spans, metrics, and service specs. Discovers telemetry via cx CLI commands, emits importable Coralogix JSON, verifies every PromQL and DataPrime query live through the cx CLI, and creates or updates dashboards via cx dashboards create and cx…
Skill Claude Code
Create visually rich PowerPoint (.pptx) presentations from academic papers, research notes, or any content the user wants in slide format. Uses PptxGenJS + LaTeX formula rendering. Always use this skill when the user wants PPT/PPTX output instead of Beamer/LaTeX slides. Trigger on: powerpoint, pptx, PPT, make a ppt…
mgonto/executive-assistant-skills
Skill Claude Code
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
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: