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 standard process for researching and comparing competing products or services. It uses web searches, a fixed report format, and a separate review before a product requirements document is written.
chang9852/role-prompt-designer
Skill Claude CodeCodex
Design and generate AI Agent role/personality definitions using the SOUL/IDENTITY/AGENTS three-layer prompt architecture. Use when: (1) Creating a new AI Agent persona from scratch, (2) Writing or editing SOUL.md, IDENTITY.md, or AGENTS.md files, (3) Designing role prompts for AI assistants, chatbots, or autonomous…
Skill Claude CodeCodex
Reimplement a messy git branch with clean, narrative-quality commit history suitable for code review. Use when a branch has WIP commits, debug commits, or trial-and-error history that needs to be transformed into a reviewable story before creating a PR.
Skill Claude CodeCodex needs its repo
Bootstrap a new repo into Katala OS agent-context style — AGENTS.md inheriting the global baseline, cross-OS .gitattributes, shared pre-commit hook via core.hooksPath, optional hash-locked CONSTITUTION + manifest.lock.json + verify.sh, NEEDSREVIEW.md. Use when the operator asks to "start a new repo", "scaffold an…
Skill Claude CodeCodex
This is a Vue performance best practices knowledge base optimized for AI coding assistants.
Skill Codex
Initialize or update repository-level agent operating instructions, AGENTS.md, quality workflow docs, execution-plan templates, and harness guidance for an AI-agent-driven software project. Use when Codex is asked to set up a new repository for agent-driven development, bootstrap or merge AGENTS.md, auto-select…
gaoryan86/openclaw-workspace-audit
Skill Claude CodeCodex
Audit and optimize OpenClaw workspace documents (AGENTS.md, SOUL.md, USER.md, TOOLS.md, IDENTITY.md, HEARTBEAT.md, BOOT.md, MEMORY.md, memory/) for redundancy, dead content, format compliance, cross-file conflicts, and token efficiency. Use when user asks to audit workspace files, check document health, reduce token…
Skill Claude Code
Guides users through rules-first feature implementation from idea to production code. Validates specs, tasks, and implementation against project rules at every step. Use when building features, implementing specs, creating implementation plans, breaking down specs into tasks, or when user says "help me build"…
Skill Claude Code
Maintain a lightweight docs/tasks/ repo convention for coding-agent tasks and open questions: bootstrap the folder, create task/question markdown files, update status, close or reopen items, list open work, and rebuild the derived index.
ivanmeda993/claude-new-project-bootstrap
Skill Claude Code
Bootstrap a NEW project from scratch using Ivan's preferred stack and conventions, then write production-ready first feature code. Triggered when Ivan describes what he wants to build ("napravi mi novi projekat za X", "treba mi nova app", "novi monorepo", "scaffold a Next.js app", "new project for ...", "start a new…
lijnati/modern-saas-builder-skills
Skill Claude CodeCodex
Founder-minded senior product engineer and SaaS architect skill. Use when building, planning, architecting, validating, designing, testing, securing, deploying, or monetizing modern SaaS products, micro-SaaS, web apps, AI agents, Web3/Base applications, agent commerce, or Telegram bots/Mini Apps. Always active when…
Skill Claude Code
Consolidate a project's accumulated CLAUDE.md memory plus its recent Claude Code session transcripts into a new, separate CLAUDE.dream. .md file — merging duplicate notes, replacing stale/contradicted entries, and surfacing new insights from recent sessions. Never edits the original CLAUDE.md. Use when the user asks…
Skill Claude CodeCodex
Extract knowledge from the current chat session and persist it as an OKF v0.1 knowledge bundle under /.agents/knowledge/.
stephanemalho/multi-harness-agent-template
Skill Claude CodeCodex
Use when adding, changing, or fixing project behavior while respecting architecture, tests, and validation rules.
Skill Codex
Repository harness for agentic software development. Use when the user wants a repo to follow Harness Engineering or harness-first coding practices, asks to bootstrap or maintain AGENTS.md, architecture docs, execution plans, verification loops, repo-local automation, or requests harness-first setup for future…
Skill Claude Code
Capture solved problems and implementation insights as categorized documentation with YAML frontmatter for fast lookup.
3000isagoodcat/project-external-memory
Skill Codex
Set up and maintain durable external memory for long-running or multi-session projects. Use when an AI coding agent needs AGENTS.md continuity rules, a repo-level handoff file, persistent project memory, compact operational state, cross-session continuity, durable state updates, or a way to remember project status…
Skill Claude CodeCodex
Use GovernSpec to work with local-first AI task contracts. Trigger when a repository contains govern.yaml, .govern.yaml, kind GovernSpec, or kind GovernPack; when Codex needs to validate or inspect a task contract; compile contracts to AGENTS.md, prompts, OpenAI structured outputs, MCP plans, or generic skill bundles…
newtontech/PKU_PhD_Latex_Templete
Skill Claude Code
Run a 5-perspective independent review of the manuscript covering editorial fit, methodology, domain expertise, cross-disciplinary impact, and adversarial argument testing. Inspired by academic-research-skills multi-reviewer approach. Use for pre-submission quality check or simulating peer review.
hsleedevelop/agent-session-memory-mananger
Skill Claude CodeCodex
Use when setting up project memory for multi-agent workflows, initializing .ai/ documentation structure, or ensuring agents can hand off context across sessions and tools like Cursor, Gemini, Codex, Claude Code, and OpenCode.
Skill Claude CodeCodex
How to write good tests - behavior-focused assertions, the AAA structure, red/green/refactor, small vertical slices, and what to mock versus leave real. Use whenever writing a new test, modifying or fixing an existing test, reviewing someone else's tests, deciding whether something needs a test, choosing what to mock…
Skill Claude CodeCodex
Orchestrate a Coder→Quality iteration loop against a story's Verification contract. Use when a story has a complete Verification section and is ready for execution with automated review.
Skill Codex
Reduction-first coding for every change, whether building, fixing, refactoring, or cleaning up. Delete, merge, or replace before adding, so the project ends up smaller and simpler without losing anything the app needs, in code and in the text around it. Matters most for cleanups, refactors, and larger changes.
sergeionlyart/codex-office-playbook
Skill Claude CodeCodex needs its repo
Use when the user wants to turn repeatable office work into a workflow, script, or automation scenario and you need a proper spec before implementation.
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: