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.
baixinghao/intent-gate-service
Skill Claude CodeCodex
A procedure for sending an unresolved decision to a DingTalk group, where people can answer through the bot. DingTalk is a team messaging platform commonly used in China.
Skill Claude CodeCodex
Quality-first automatic Premiere editing for weak and strong models (PPMCP).
Skill Claude Code
Unified Airtable skill — MCP, public REST API, internal web API, Omni AI, scripting, formulas, webhooks, automations, field types, and gotchas. Auto-triggers on any Airtable task.
Skill Claude CodeCodex
Static analysis for Unity IL2CPP games via il2cpp-decompiler-agent MCP (listdumps, loadproject, searchsymbols, getclassinfo, decompilemethod). Use when runtime is IL2CPP, GameAssembly.dll is involved, or remakes like Who's Your Daddy Remake. Always MCP-first — do not start with Il2CppStudio CLI.
Skill Claude CodeCodex
Author a new terva skill, a reusable SKILL.md instruction set that terva loads on demand. Install it where terva discovers it, in the project .terva/skills/ or the global $TERVAHOME/skills/. Use for create/add/write-a-skill requests, not extensions.
Skill Claude CodeCodex
When the user asks you to perform git operations, create branches, open PRs, manage releases, or resolve conflicts, follow this guide. These are the procedural patterns you should apply consistently.
Skill Claude CodeCodex
Deduction search over the 2dph brain (Ladybug graph: ops corpus, portfolio, ssh hosts) with bin/brain/search.go instead of reading files or grepping repos. Use whenever a question starts with "where is", "what runs on", "which file describes", "who is", "how is X done", before opening any documentation.
Skill Claude Code
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…
Skill Claude CodeCodex
Helps plan and fund a large, specific, one-time savings goal with a dollar target and timeline — house down payment, car, wedding, sabbatical. Use when a user says "I'm saving for a house down payment", "how much do I need to save monthly for X", "help me set a savings target with a deadline", or "I want to buy a car…
444136347/dsh-capability-discovery
Skill Claude CodeCodex needs its repo
Use when a user asks to find, compare, or evaluate an existing DeepSeek Harness plugin, Skill, MCP server, agent extension, profile, or similar ecosystem capability.
Skill Claude CodeCodex
Expertise in high-performance native codebase scanning and validation using Rust. Trigger this skill when asked to "scan the codebase natively", "run rust scanner", or "validate bxc core using rust".
Skill Claude CodeCodex
Worker-prompt lifecycle and the Architect/Analyst review gates — prompt frontmatter (status, reviewround, outputstatus), the draft→in-review→approved loop, the append-only review logs, the output gate (review-output → promote), and the tasks/{todo,run,done} transitions. Use when drafting, reviewing, or executing a…
Skill Claude CodeCodex
Draft or repair a disabled Synapsor Safe Action when a developer asks to make one application data change safe for an AI agent.
Skill Claude Code
Run a long-lived, headless per-project GOAL orchestrator on hyperpanes — hold a project's goal list, spawn a fable/opus spec agent per goal, have it fan work out to sonnet impl agents via the durable work queue, watchdog wedged agents, rotate across Claude accounts on limits, and loop 24/7. Use when the user wants a…
Skill Claude CodeCodex
Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA, scaling laws, deep learning profundo, o episódio de novembro 2023 na OpenAI, superinteligência segura.
Skill Claude CodeCodex
Apply security guidelines when designing, building, or reviewing AI chatbots, LLM-powered apps, autonomous/tool-using agents, and mobile apps (React Native/Expo, Flutter) — covering agent controls (authorization checks, plan validation, execution limits, audit logging), LLM/prompt security (prompt injection, RAG…
rabee-elkholy/android-harness-kit
Skill Claude CodeCodex needs its repo
Use when developing business logic, UseCases, Repositories, ViewModels, or reproducing and fixing bugs using strict Red-Green-Refactor cycles. Requires writing and proving a failing test before writing implementation code.
Skill Claude Code
Multi-agent market validation skill. Spawns 6 parallel research analysts (Community uses last30days for fresh 30-day signal; Claim Verifier uses deep-research for fact-checking) and delivers a BUILD / CONDITIONAL / PIVOT / STOP verdict with a 7-pillar scorecard. Use when user says "should I build this", "/sib"…
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
jlldavies/go4-llm-design-patterns
Skill Claude CodeCodex
Use when designing, architecting, planning, or debugging any system with an LLM in it — agents, agent loops, RAG and retrieval, prompt pipelines, multi-agent or subagent orchestration, tool use and MCP, memory and context management, evals, or production guardrails. Trigger BEFORE committing to an approach — choosing…
Skill Claude CodeCodex
Extend this cloned Helios example app — add new controls, scenes, knobs, image flows, or features on top of @reactor-models/helios (pinned to ^0.9.0) without breaking the patterns the existing code already uses. Covers the SDK's connection / events / messages model, the phase-based UI architecture, the state snapshot…
Skill Claude CodeCodex
create a new automated task or add a listener in Systema Auxilium.
Skill Claude CodeCodex
Use this read-only skill before consequential agent actions to separate capability from authority. It checks identity, scope, purpose, consent, evidence, revocation, appeal, continuity/exit, and legitimacy; it never grants permission or executes the action.
Skill Claude CodeCodex
Deeply analyze an API endpoint and generate complete, structured test coverage. Use this skill whenever the user provides an API endpoint, a Swagger/OpenAPI spec, or describes an API to test. Triggers on: "analyze this API", "generate test cases for this endpoint", "what should I test on this API", "test coverage for…
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: