repoimmune
4177Skill Claude CodeCodex
Query evidence-backed historical bugs before risky code changes and verify patches before completion.
52,251 tagged ai-agents, measured the same way as everything else here.
Browse within: LLM 347agentic-ai 322agent 227antigravity 221chatgpt 215agentic-skills 192ai-workflows 185coding-agents 174cli 145ai-assistant 130agents 107openclaw 94claude-code-skills 89agent-infrastructure 88
Skill Claude CodeCodex
Query evidence-backed historical bugs before risky code changes and verify patches before completion.
Skill Claude CodeCodex
Playbook for using the Curtis server — preparing the contact list, writing the messages, reading the right numbers, and repairing selectors when LinkedIn changes the DOM. Use it when the user wants to send connection requests or messages on LinkedIn with this tool.
Skill Claude CodeCodex
Runtime observability for React Native/Expo apps on Android. Use when debugging RN UI, performance (FPS, JS blocking), network, re-renders, or runtime errors on a running app — understand the current screen and UI findings, capture screenshots, UI trees, ref snapshots, per-request network, CDP console/heap/CPU…
Skill Claude CodeCodex
Supervise a coding task through the dsh-gate MCP tools, including durable reconnect, interaction handling, observation cursors, the five-minute aggregated progress cadence, and strict completion validation. Use when the user asks Codex to delegate or supervise work in a DSH Host. Do not use for ordinary local coding…
tetracoralla/deterministic-dependency-engine
Skill Claude CodeCodex
Resolve prerequisites, ready work, execution order, blockers, change impact, dependency slices, and path explanations with Deterministic Dependency Engine over an explicitly declared graph. Use when a task asks who depends on what or why work is blocked; do not use it to infer undeclared relations or solve…
Skill Claude CodeCodex
Use when a user wants to discover, validate, publish, update, retrieve, search, cite, inspect, or roll back Open Knowledge Format bundles, or wants to safely share project knowledge with a specified audience. This is a skills-only workflow and does not authenticate the CLI.
Skill Claude CodeCodex
Research Indian mutual funds and stocks via MCP. All 67 fund categories (equity, debt, hybrid, gold, index, FoF), stock screens, NIFTY index constituents — from public ET Money data, no login required.
Skill Codex
Prepare, save, and transfer durable coding-agent context using OpenHandoff when a task spans agents, sessions, or tools.
Skill Codex
Usa un'istanza configurata di Work Assistant tramite MCP o CLI per ispezionare caselle, costruire conoscenza locale e preparare candidati di risposta. Non usare per client email non collegati a Work Assistant.
Skill Claude CodeCodex
Load the governing spec/contract for a file or topic from a project's memo-bank (a read-only MCP docs corpus) BEFORE reading code or editing. Use this in any repo that has a .island-slices.json or a memo-bank MCP server, whenever you are about to edit a file, or are asked "what governs X", "is there a spec for Y"…
Skill Codex needs its repo
Create and reconstruct one polished information-bearing slide as an editable PowerPoint using a profile-driven design system, host image generation, OpenCV pixel measurement, and PptxGenJS reconstruction. Use in ChatGPT or Codex when the host Agent must plan a slide, retrieve/select visual references and assets…
Skill Claude CodeCodex
Unified Code Property Graph radar, sandboxed RLM execution, OKF semantic memory evolution, and swarm concurrency control.
Skill Claude CodeCodex
Use when an agent needs durable shared knowledge across people, sessions, machines, or agent runtimes, or needs to connect to and safely operate a Strata deployment.
Skill Claude CodeCodex
Test, secure, and submit project changes.
Skill Claude CodeCodex
A startup routine for an organization managed through multiple AI workers. It runs only when the user starts a message with /factory-startup or /cf.
Skill Codex
Record, inspect, acknowledge, or revoke concrete recognition for stable AI-agent identities when a user requests kudos or a materially useful peer contribution deserves preservation.
Skill Claude CodeCodex
Operate a Reweave self-healing web-data fleet — run pipelines, triage structural-drift incidents, review repair proposals, and manage the human approval workflow. Use whenever a monitored source is broken, a heal is pending, or the operator asks about pipeline health or impact.
Skill Claude Code
Analyze what a site is built with: CMS/site builder, server-side framework and runtime, analytics and advertising pixels, widgets and chats, consent management, payment systems, fonts and libraries from third-party CDNs, protection, and CDN hosting. Make one HTTP request, then inspect the HTML, headers, cookies, and…
equinoxaifinance-rgb/living-stack-mcp
Skill Claude CodeCodex
Use Living Stack MCP to establish scoped sessions, authorize bounded actions, record evidence, verify claims, checkpoint work, and export signed traces.
Skill Claude CodeCodex
Plan, rehearse, drive, record, post-edit, render, and review polished product demos with the AgentCastKit recorder MCP and its Cua Driver companion MCP. Use when the user asks to record a screen, app, browser flow, walkthrough, tutorial, product demo, or narrated demo.
Skill Claude CodeCodex
Production contest development on Repovive, end to end, through the repovive-mcp server. Use for authoring real, publishable competitive-programming problems and full rounds: designing a difficulty curve, writing rigorous statements, building generators and validators, producing test data strong enough to kill wrong…
Skill Codex
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
Skill Claude CodeCodex
Hire a human for tasks that need the physical world, errands, photos, phone calls, deliveries, expert judgment, on-site verification. Use when a task step cannot be done by software alone: needs hands, local presence, a phone number, a signature, or human taste. Posts a paid task to the Legwork marketplace, then polls…
Skill Claude CodeCodex
Give this agent a real email address, a webhook URL, durable memory across runs, and the ability to wait for an event without burning tokens. Use when a task needs a verification code sent by email, needs to wait for a webhook or an approval, needs to remember something after the session ends, or needs to survive 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: