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
Family coordination engine. Use this skill whenever the user mentions meals, meal planning, groceries, weekly schedule, family logistics, kid activities, custody schedule, co-parent coordination, family dashboard, weekly briefing, weekly prep, "what's for dinner", school events, pickup/dropoff, babysitter, pediatric…
Skill Claude CodeCodex
Review and audit code quality, architecture, and implementation. Verify code meets design specs, find bugs, identify improvements, and create change/bug/improve backlogs. Use when reviewing completed code, auditing implementations, or ensuring quality.
Skill Claude CodeCodex
Consult the user's vir knowledge base: notes distilled from their own past coding-agent sessions (decisions, gotchas, patterns, tools). Use before starting non-trivial work in a project, when the user asks 'what did I decide about X', 'have I hit this before', 'check my notes/vault', when debugging an error that may…
Skill Claude CodeCodex
Use before starting a long or expensive task (a large refactor, a change across many files, a long agent loop, a big test or eval run, a batch of LLM calls), and when asked how much AI budget is left.
Skill Claude Code
Long-term project memory through the post-cortex MCP server (tools named session, semanticsearch, updateconversationcontext, assemblecontext, queryconversationcontext, getstructuredsummary, manageworkspace, manageentity, admin). Use it whenever those tools are available and the work could benefit from what was learned…
IBM/data-intelligence-mcp-server
Skill Claude CodeCodex ✓ vendor
Use when the user wants to work on their glossary — including adding or updating definitions, translations, regulation-based classification, enrich glossary terms, classify terms by regulation, or any other glossary curation task. Trigger phrases include: "I want to work on my glossary", "add definitions", "update…
Skill Claude Code
Build the section structure, argument map, dependencies, and word budgets.
Skill Claude CodeCodex
DBOS Rust SDK (the dbos crate) for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing Rust code with DBOS, creating workflows and steps, using queues, using the DBOS Client from external applications, or building Rust applications that need to be resilient to failures.
Faizalimam990/Startup_builder_pro
Skill Codex
Build, upgrade, or rescue complete digital products and distinctive animated frontends in an existing repository or from a prompt. Use for end-to-end apps, SaaS, dashboards, ecommerce, major features, and premium content-led sites. Includes reference-led art direction, professional color and typography, UI library…
Skill Claude CodeCodex
A setup tool for connecting Claude Code to language-model services that use Anthropic's Messages API, such as DeepSeek, Kimi, OpenRouter, or a self-hosted service. It can also change Claude Code's displayed brand and package the result for distribution.
Skill Claude CodeCodex
Connect bank accounts to AI models using openfinance.sh.
Skill Codex
A research skill for analysing Xiaohongshu, also called RedNote, a Chinese social platform, and turning a creator’s posts or account data into an evidence-based content profile.
Skill Claude CodeCodex
Primary repo-owned workflow for turning an article URL or source file into WeChat or Xiaohongshu draft markdown plus saved illustration artifacts. Use this when the user wants OpenClaw itself to deep dive a source and generate a draft with illustrations, especially for prompts like "generate a wechat post with…
Skill Codex
A workflow initializer for creator.skill, a set of skills for gathering requirements, defining design rules, planning development, and building projects. It installs or upgrades the workflow in the current workspace from a release package or a local archive.
Skill Claude CodeCodex
Apply daily self-improvements to your AI agent using Agent Vitamins. Fetches the latest AV brief via MCP, ranks self-improvement actions by relevance to your setup, and applies the best one with your approval. Use when the user wants to improve their agent, run "/av-improve", or as part of the daily brief. Requires…
chiroro-jr/pencil-design-skill
Skill Claude CodeCodex
Design UIs in Pencil (.pen files) and generate production code from them. Use when working with .pen files, designing screens or components in Pencil, or generating code from Pencil designs. Triggers on tasks involving Pencil, .pen files, design-to-code workflows, or UI design with the Pencil MCP tools.
TheMattBerman/openclaw-100k-posts-kit
Skill Claude CodeCodex
Turn source patterns into brand-native, ready-to-post content concepts with visible lineage to the original outlier. Runs input through three psychology frameworks (Puppet Strings, Scroll Traps, and Care To Click) plus pattern transfer and brand voice translation. Use when: you have a pattern report, outlier analysis…
yuanqiyibiansheng/DeepSeek-Harness-GUI
Skill Claude CodeCodex
A collection of React Native and Expo development guidelines for mobile apps, including lists, animations, media, native features, and project structure.
Skill Claude CodeCodex
Use for unresolved or misplaced control in agentic systems, including workflows freezing truth, claims exceeding evidence, or unowned semantic choices. Conceptual comparisons alone do not require WAE.
Skill Claude CodeCodex
Git diff for AI agent repository instructions. Shows the blast radius of AGENTS.md and CLAUDE.md changes. Use when Git cannot show which agent inherited the edit, a Codex vs Claude Code split, or why one path inherited a stack.
Skill Claude CodeCodex
Multi-agent quality review (QA + Security + DevOps + SRE + TechLead + Documentation + PromptOps).
Skill Claude Code
Creates a new section from name and field list: folder, schema, component, config registration.
Skill Codex
A job-search workflow for BOSS, a Chinese recruitment platform, controlled through a browser you log into yourself.
Skill Claude Code
Use this skill when the user wants AI work they can trust without watching every step: the AI fixes direction first (rules, assumptions, failing checks sealed in git), builds to green, then proves the result with evidence for the human to review. Trigger when a repo has .add/, the user says "add", "/add", "start a…
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: