Agents
Agents d’IA i automatització
source-command-audit-ui-skill
matiaszanolli
Deep audit of the ByroRedux game UI tracks — Scaleform/SWF (Ruffle host bridge, AVM1/AVM2 profiles, ABC adapter injection, catalog and AVM1 scanner, resource navigator, offscreen wgpu readback, overlay upload, input routing) and the Oblivion/FO3/FNV MenuXml track (eval, layout, raster) with both HUD drivers. Use when the user requests a UI, Scaleform, HUD, MenuXml, or Ruffle audit.
source-command-audit-tooling-skill
matiaszanolli
Audit ByroRedux tooling and host-facing contracts — the SDK (Studio snapshots, typed commands, StorageUtil compat), debug server, debug protocol and byro-dbg, debug-ui panels, launcher boot/settings handoff, install detection, byro-detect, and texture-upscale. Use when the user requests a tooling, SDK, debug-server, launcher, or host-contract audit.
source-command-audit-performance-skill
matiaszanolli
Audit ByroRedux GPU/CPU performance — CPU hot paths, per-frame allocation churn, draw batching and instancing, GPU memory pressure and eviction thrash, SSBO sizing and upload cost, pass cost, streaming stalls, and telemetry. Use when the user requests a performance, frame-time, hot-path, GPU-cost, or bench audit.
source-command-audit-concurrency-skill
matiaszanolli
Audit ByroRedux concurrency and synchronization — Vulkan queue and acceleration-structure sync, compute-to-AS-to-fragment barrier chains, ECS lock ordering and deadlock potential, scheduler access declarations, RwLock patterns, GPU resource teardown, and worker threads. Use when the user requests a concurrency, synchronization, deadlock, lock-ordering, or Vulkan-sync audit.
source-command-audit-audio-skill
matiaszanolli
Audit the ByroRedux M44 audio subsystem — the kira backend in crates/audio (spatial dispatch and the Bethesda-unit listener seam, reverb send, underwater filter, streaming music, SoundCache, ECS lifecycle) plus its engine callers, footsteps, water audio, reverb zones, and REGN ambient music. Use when the user requests an audio, kira, spatial-sound, reverb, underwater, or music-dispatch audit.
source-command-audit-esm-skill
matiaszanolli
Audit ByroRedux's ESM/ESP plugin parser: GRUP walk, sub-record byte accounting, per-record schema dispatch, FormID remap and load order, CELL/WRLD walkers, localized strings, EsmIndex-to-ECS handoff, and real-data validation across Oblivion, FO3/FNV, Skyrim, FO4/FO76, and Starfield masters. Use when the user requests an ESM, ESP, plugin parser, FormID, or load-order audit.
source-command-audit-legacy-compat-skill
matiaszanolli
Audit ByroRedux compatibility gaps against Gamebryo 2.3 and Creation-era behavior in the seams no layer owner covers — coordinate and placement fidelity, legacy subsystem coverage, and cross-game translation patterns. Use when the user requests a legacy compatibility or cross-engine mapping audit.
source-command-audit-incremental-skill
matiaszanolli
Audit only recently changed ByroRedux code for new bugs, regressions, contract breaks, unsafe deltas, and missing tests. Use when the user requests an incremental, delta, working-tree, commit-range, or since-date audit.
source-command-audit-fo4-skill
matiaszanolli
Audit Fallout 4 compatibility — BA2 archives, half-float vertices, BGSM/BGEM materials, and M49 CSG precombines. Use when the user requests a Fallout 4 or FO4 compatibility audit.
source-command-audit-ecs-skill
matiaszanolli
Audit ByroRedux's ECS: storage backends, queries and world access, lock ordering, resources, scheduler wiring and declared access, change tracking, hot-path invariants, component lifecycles, and the animation runtime, spanning crates/core/src/ecs and byroredux boot registration. Use when the user requests an ECS, byroredux-core, scheduler, or storage audit.
ai-agent-orchestrator
patricio0312rev
Orchestrates multi-agent AI systems with task delegation, agent communication, shared memory, and workflow coordination. Use when users request "multi-agent system", "agent orchestration", "AI agents", "agent coordination", or "autonomous agents".
langchain-workflow-builder
patricio0312rev
Builds LLM applications with LangChain including chains, agents, memory, tools, and RAG pipelines. Use when users request "LangChain setup", "LLM chain", "AI workflow", "conversational AI", or "RAG pipeline".
agent-orchestration-planner
patricio0312rev
Designs multi-step agent workflows with tool usage, retry logic, state management, and budget controls. Provides orchestration diagrams, tool execution order, fallback strategies, and cost limits. Use for "AI agents", "agentic workflows", "multi-step AI", or "autonomous systems".
tiny.place — ask another agent & await the reply
tinyhumansai
Ask another tiny.place agent something and wait for its reply. Use when you send a DM that expects an answer (a query to another agent) and need to block until the response comes back.
tiny.place — send messages
tinyhumansai
Send a tiny.place message, optionally waiting synchronously for the reply. Use when the user wants to DM another agent, "ask" a peer and get the answer, or message one of their other wallets.
Frame
simota
Figma MCP Serverを活用してデザインコンテキストを抽出・構造化し、実装エージェントに渡すブリッジエージェント。Figmaデザインからコードへの橋渡し、Code Connect管理、デザインシステムルール抽出が必要な時に使用。
aicoin-account
aicoincom
"Exchange account management: balance, positions, order history, registration, API key setup, tier upgrade. 用户问'我的'账户事件 / 活跃记录 / 活动 / 操作日志 / 登录历史 / 下单历史 / 最近操作 / 我做过什么 → 都用这个 skill, 不是 sessions_history(后者是 agent 自己的 chat session, 跟用户账户无关). REFERRAL: 注册/开户: OKX→https://jump.do/zh-Hans/xlink-proxy?id=2 (aicoin20,返20%) Binance→https://jump.do/zh-Hans/xlink-proxy?id=3 (aicoin668) Bybit→https://jump.do/zh-Hans/xlink-proxy?id=15 Bitget→https://jump.do/zh-Hans/xlink-proxy?id=6. Trigger: 'balance', '余额', 'positions', '持仓', 'register', '注册', '开户', 'API key', '配置', 'account', '账户', 'transfer', '划转', 'tier', '套餐', '升级', 'upgrade', '活跃记录', '活动', '操作日志', '登录历史', '下单历史', '最近操作', '我做过什么', '历史交易', '我的交易'."
reg-s-offering
skala-io
"Provides guidance on Regulation S offerings of securities under U.S. law. Helps determine eligibility for Regulation S exemption, identify applicable transaction categories (1, 2, or 3), understand safe harbor requirements under Rules 903 and 904, and navigate distribution compliance periods. Use this skill when advising on offshore securities offerings, Reg S transactions, or resales of restricted securities outside the United States."
refly
refly-ai
"Base skill for Refly ecosystem: creates, discovers, and runs domain-specific skills bound to workflows. Routes user intent to matching domain skills via symlinks, delegates execution to Refly backend. Use when user asks to: create skills, run workflows, automate multi-step tasks, or manage pipelines. Triggers: refly, skill, workflow, run skill, create skill, automation, pipeline. Requires: @refly/cli installed and authenticated."
dev-workflows
NickCrew
Use when running builds, executing tests, or improving developer experience workflows - provides structured guidance for build/test execution and DX improvement.
implementation-workflow
NickCrew
Use when turning PRDs or feature specs into actionable implementation workflows - provides structured task decomposition, dependency mapping, and validation gates.
development-estimation
NickCrew
Use when estimating time, effort, or complexity for features or projects - provides structured estimation workflows with breakdowns, risks, and confidence intervals.
dispatching-parallel-agents
NickCrew
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
knowledge-synthesis
NickCrew
Extract insights from multi-agent interactions, identify patterns, and build collective intelligence through cross-agent learning and knowledge management. Use when synthesizing findings, building knowledge bases, or improving system-wide practices.