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
Delegate a multi-step coding task to sidekick — a local orchestrator that decomposes the task into a DAG of subtasks, fans out auto-approved coding sub-sessions on isolated git worktrees (Claude Code on the claude branch, Kimi/Moonshot on the kimi branch — same envelope either way), runs acceptance checks, and merges…
Skill Codex
Find current Polygres guidance for setup, application integration, retrieval design, and troubleshooting by navigating the hosted skills library. Use when a task needs published Polygres guidance through web access.
Skill Claude Code
Use when the user asks to enhance, refine, polish, or "look at" the release notes for a tag of @epam/ai-dial-ui-kit — typically a freshly cut stable release (e.g. 0.11.0). Reads the CI-generated notes off the GitHub release, classifies and rewrites each bullet in this project's editorial voice, and saves a draft to…
Skill Claude CodeCodex
Research independent web questions with authorized host subagents, then synthesize cited evidence and gaps. Use for requested parallel or multi-angle research, not ordinary lookups. Check child MCP access before fan-out; disclose serial fallback when delegation is unavailable.
Skill Claude Code
Reset this task's context window while continuing the same work — write a handoff, then have Argus kill this session and start a brand-new one on the identical task/worktree/branch, seeded with the handoff. Use when the conversation has grown large and a fresh context window would help, but the underlying task should…
mattppal/formatting-notion-pages
Skill Claude CodeCodex
Apply rich formatting to Notion pages - toggles, callouts, headers, and styled text. Use when creating or formatting Notion documents via the Notion MCP server.
Skill Codex
Adversarially verify claims that code, fixes, tests, CI, deployments, logs, or systems are correct, complete, healthy, or safe to merge. Use when asked to prove, verify, validate, confirm, double-check, review the agent's own work, check whether a bug is actually fixed, or decide whether green signals justify a…
Skill Claude CodeCodex
Frontend design skill fused from Impeccable + custom extensions. Covers design philosophy, anti-AI-slop patterns, typography, color (OKLCH), spatial design, motion, interaction, responsive, UX writing, state management, engineering, and 4 style variants. Includes 20 command skills for audit/critique/polish/animate/etc.
Skill Claude CodeCodex
A Chinese-language skill for checking the completeness and consistency of academic manuscripts. It traces claims to original papers, code, and experiment records, then checks related text, tables, scripts, figures, and stored memories.
Skill Claude CodeCodex needs its repo
Manage projects, tasks, wikis, and teams in Kanbu — a self-hosted project management platform built for AI agents. Use when the user asks about project management, task tracking, kanban boards, sprints, wikis, team workload, or anything related to Kanbu. Also triggers on task creation, updates, comments, subtasks…
Skill Claude CodeCodex
A Chinese patent-application writing skill that creates a formatted DOCX document, including the abstract, claims, description, and technical drawings. CNIPA is China’s government agency for patent applications.
Skill Claude CodeCodex needs its repo
PROPOSAL: Add explicit skill chaining to Agent Skills spec. Defines chain metadata field for ordered skill execution with async option for sequential/parallel loading. Use to propose chaining feature to https://agentskills.io.
Skill Codex
Use when a user asks an agent to inspect, refine, or generate an API/oRPC/OpenAPI contract from website recordings captured by the Harpist Chrome extension. Covers using the published harpist npm CLI through bunx/npx, avoiding sandboxed execution, starting or reusing the local Harpist bridge, syncing extension…
Skill Codex
Installation instructions for codex-compressor, a tool that manages Codex settings and hooks. They describe standalone setup and plugin-hook setup on macOS, Linux, and Windows.
Skill Claude CodeCodex
A communication adviser based on Nonviolent Communication, a framework for expressing needs clearly while reducing blame and defensiveness.
Skill Claude CodeCodex
Safeguard LLM calls using adaptive/extended thinking against token truncation. Use this skill when configuring API parameters for reasoning models (like Claude 3.7 Sonnet), when structured JSON outputs are returned unparseable or incomplete, or when designing cost-sensitive pipelines that utilize LLM reasoning.
Skill Claude CodeCodex
Auto-orchestrating UI design skill that prevents generic AI-generated output. Detects project context and target platform, explicitly asks the user which platforms to design for, resolves brand color direction through user choice or auto-selection, presents curated design style options, and generates a CJX-ready…
Skill Claude CodeCodex
A database-access skill supporting direct connections and API-based access across multiple databases, with auditing. A database stores structured application data, such as users, orders, or settings.
Easternguy/podcast-from-research
Skill Claude CodeCodex
Research-to-podcast pipeline for learning new topics: 20-angle full-coverage research (with blind-spot discovery) → steered NotebookLM audio overview → MP3 delivered to you, with everything ingested into a local GBrain knowledge base for permanent recall. When the user says "create a podcast on X", this handles it…
Skill Claude CodeCodex
A Chinese-language reviewer for educational and knowledge-service content, such as course scripts, articles, lectures, and popular explanations. It evaluates whether the content can lead learners from a problem to a useful change in understanding.
Skill Claude CodeCodex
Turn a GitHub pull request into an interactive review map with AI insights, reviewed in the browser. Use when the user asks to review, map, or visualize a PR.
Skill Claude Code
Deep analysis of a single paper: download PDF, extract figures, generate structured 20+ section note, fill LLM placeholders.
yamanidev/claude-code-configuration
Skill Claude Code
Workflow for drafting a logo mark for a side project or utility, producing a self-contained HTML gallery of 4–6 concept directions per round — each rendered in SVG at large, medium, and favicon sizes on both light and dark backgrounds. The user opens the gallery in a browser, picks favorites by short letter code, and…
Skill Claude CodeCodex needs its repo
Guidance for AI coding agents working on the adeptability (adept) codebase. Humans: see README.md for usage and CONTRIBUTING.md for the contributor workflow.
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: