AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
hlnd2t Skill Generate Signature For PatchGenerate and validate unique byte signatures for instructions that need to be runtime-patched using IDA Pro MCP. Use this skill when you need a signature to locate a specific instruction for patching (e.g., force/skip a branch, NOP a call, change an immediate operand). Triggers: patch signature, signature for patch, patch instruction signature, nop signature, jump patch signature, skip branch signature, force branch signature
-
hlnd2t Skill Generate Signature For FunctionGenerate and validate unique byte signatures for functions using IDA Pro MCP. Use this skill when you need to create a pattern-scanning signature for a function that can reliably locate it across binary updates. Triggers: generate signature, byte signature, pattern signature, function signature, unique signature, sig for function
-
hlnd2t Skill Generate Signature For GlobalvarGenerate and validate unique byte signatures for global variable using IDA Pro MCP. Use this skill when you need to create a pattern-scanning signature for a global variable that can reliably locate it across binary updates. Triggers: global variable signature, signature for global variable
-
hlnd2t Skill Find Centitysystem Init DecompilesFinal-guarantee fallback for the find-CEntitySystem_Init-decompiles preprocessor. Recovers the struct members, indirect virtual-function offsets, and de-inlined helpers that CEntitySystem::Init sets up, by decompiling CEntitySystem_Init in CS2 server.dll / libserver.so and following de-inlined callees when a target is no longer accessed directly. Use this skill when the deterministic/LLM preprocessor (ida_preprocessor_scripts/find-CEntitySystem_Init-decompiles.py) could not resolve every target because a member or vfunc was inlined or de-inlined in a way the LLM_DECOMPILE references do not cover. Trigger: CEntitySystem_m_sEntSystemName, CEntitySystem_m_eNetworkSerializationMode, CEntitySystem_m_Symbols, CEntitySystem_m_ComponentUnserializerInfoAllocator, CEntitySystem_m_pNetworkFieldChangedEventQueue, CEntitySystem_m_pNetworkFieldScratchData, CEntitySystem_m_pFieldChangeLimitSpew, CEntitySystem_m_EntityMaterialAttributes, INetworkMessages_SetNetworkSerializationContextData, IFlattenedSerializers_CreateFieldCh
-
hlnd2t Skill Generate Signature For VfuncoffsetGenerate and validate unique byte signatures for instructions containing a virtual-function offset using IDA Pro MCP. Use this skill when you need a signature for an instruction like call qword ptr [rax+538h], where the vfunc offset (0x538) must be explicitly fixed in the first instruction bytes. Triggers: vfunc offset signature, signature for vfunc offset, virtual function offset signature, call [reg+offset] signature
-
inkbox-ai Bundle Browser UseSystem prompt for an AI agent with Browser Use browser automation and Inkbox email. Drop this into your agent loop to get browser automation and email tools out of the box.
-
inkbox-ai Skill Inkbox Agent Self SignupUse when guiding or implementing the Inkbox agent self-signup flow, including verification, resend-verification, signup restrictions, and optional signup fields like agent handles or mailbox local parts.
-
plur-ai Skill Plur MemoryPersistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
-
plur-ai Bundle Effective MemoryThe essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.
-
hlnd2t Skill Generate Signature For StructoffsetGenerate and validate unique byte signatures for instructions containing a struct member offset using IDA Pro MCP. Use this skill when you need a signature for an instruction like mov [rcx+1A8h], eax or cmp dword ptr [rdi+0B0h], 0, where the struct offset must be explicitly fixed in the first instruction bytes. Triggers: struct offset signature, signature for struct offset, structure member offset signature, mov [reg+offset] signature, struct field signature
-
hlnd2t Skill Find Cnetworkmessages GetisforserverFind and identify the CNetworkMessages_GetIsForServer virtual function in CS2 binary using IDA Pro MCP. Use this skill when reverse engineering CS2 networksystem.dll or libnetworksystem.so to locate the GetIsForServer vfunc by reusing the known CNetworkMessages_SetIsForServer slot and checking the adjacent CNetworkMessages vtable entry. Trigger: CNetworkMessages_GetIsForServer
-
hlnd2t Skill Find Ivengineserver2 GetclientsteamidFinal-guarantee fallback for the find-IVEngineServer2_GetClientSteamID preprocessor. Recovers IVEngineServer2::GetClientSteamID (a virtual function of the IVEngineServer2 interface) in CS2 server.dll / libserver.so by decompiling its known predecessor CBasePlayerController_HandleCommand_JoinTeam and identifying the vtable-slot fetch on g_engine. Use this skill only when the deterministic/LLM preprocessor (ida_preprocessor_scripts/find-IVEngineServer2_GetClientSteamID.py) could not resolve the target. Trigger: IVEngineServer2_GetClientSteamID
-
hlnd2t Skill Find Ccsbotmanager Addbot BotnavignoreFind and patch the g_pNavMesh null-check inside CCSBotManager_AddBot in CS2 binary using IDA Pro MCP. This patch removes the navigation mesh requirement so bots can be added even without a nav mesh loaded. Use this skill when reverse engineering CS2 server.dll or libserver.so to locate and patch the nav mesh check in AddBot. Trigger: bot nav ignore, AddBot nav mesh patch, bot without nav, CCSBotManager nav ignore
-
hlnd2t Skill Find Cnetworkmessages Vtable DecompilesFind and identify CNetworkMessages_AllowAdditionalMessageRegistration and CNetworkMessages_IsAdditionalMessageRegistrationAllowed virtual functions in CS2 binary using IDA Pro MCP. Use this skill when reverse engineering CS2 networksystem.dll or libnetworksystem.so to locate both vfuncs by reusing the known CNetworkMessages_RegisterNetworkFieldChangeCallbackInternal slot and checking the two adjacent CNetworkMessages vtable entries. Trigger: CNetworkMessages_AllowAdditionalMessageRegistration, CNetworkMessages_IsAdditionalMessageRegistrationAllowed
-
hlnd2t Skill Find Ccsgamerules Sm MapgcbaninformationFind and identify the CCSGameRules__sm_mapGcBanInformation global variable in CS2 binary using IDA Pro MCP. Use this skill when reverse engineering CS2 server.dll or libserver.so to locate the GC ban information map structure by decompiling CCSPlayerController_ResourceDataThink's sub-function (Linux) or searching for the "Notification about user penalty" string (Windows).
-
hlnd2t Skill Find Inetworkserverservice IsactiveingameFinal-guarantee fallback for the find-INetworkServerService_IsActiveInGame preprocessor. Recovers INetworkServerService::IsActiveInGame (a virtual function of the CNetworkServerService vtable) in CS2 engine2.dll / libengine2.so by decompiling its known predecessor CSteam3ServerS1_InitGameServer and identifying the virtual call on g_pNetworkServerService. Use this skill only when the deterministic/LLM preprocessor (ida_preprocessor_scripts/find-INetworkServerService_IsActiveInGame.py) could not resolve the target. Trigger: INetworkServerService_IsActiveInGame
-
hlnd2t Skill Find Inetworkserverservice IsserverrunningFinal-guarantee fallback for the find-INetworkServerService_IsServerRunning preprocessor. Recovers INetworkServerService::IsServerRunning (a virtual function of the CNetworkServerService vtable) in CS2 engine2.dll / libengine2.so by decompiling its known predecessor CNetworkGameClientBase__ProcessNetworking and identifying the virtual call on g_pNetworkServerService. Use this skill only when the deterministic/LLM preprocessor (ida_preprocessor_scripts/find-INetworkServerService_IsServerRunning.py) could not resolve the target. Trigger: INetworkServerService_IsServerRunning
-
parcha-ai Bundle PrecapWrite a precap — the recap of a task as if it were already finished — before or during long-running work, then use it to check whether the run is still on the imagined path. Use when the user says "/precap", "precap this", "write the precap", "what will this take", "imagine this is done", or "are we still on track"; at the start of any task expected to span many steps, hours, or sessions; on resume when a precap.md exists in the working directory; and whenever a long-running agent needs to verify it is doing what it set out to do. It investigates the repo, plan, and git state so the imagined path is grounded rather than guessed. Not a substitute for plan approval or for asking the user about scope.
-
parcha-ai Bundle Hands FreePhone-call bridge for coding agents — when the user is away from the keyboard, the agent calls them (as Unc). Use when the user says "activate hands free" / "deactivate hands free" (also hands-free, handsfree), asks to route questions or approvals to a phone call, or says they're stepping away but want the work to keep moving. Works on Claude Code, Codex, and pi.
-
superduck-ai Bundle Agent ReadinessRun a full 5-phase agent-readiness audit on the current repository — scan, discover apps, evaluate 82 criteria via parallel subagents, validate, and generate report + dashboard with persistent score history
-
vanillagreencom Bundle DevLoad when implementing an issue or applying review fixes as a dev agent.
-
vanillagreencom Bundle Dev 2Load when implementing an issue or applying review fixes as a dev agent.
-
vanillagreencom Bundle OrchPRIMARY AGENT ONLY. Load to orchestrate a Linear or GitHub work item from preparation through merge.
-
vanillagreencom Bundle Second OpinionLoad for a cross-model review, challenge, audit, or quick consult.
-
vanillagreencom Bundle Second Opinion 2Load for a cross-model review, challenge, audit, or quick consult.
-
loopx-project Skill Swe Marathon Five ArmMigrate historical SWE-Marathon agent configurations to the shared Codex runtime.
-
blogminhquy Skill Javis BuilderTạo hoặc sửa năng lực của Javis: agent, skill, workflow, loop, plugin. Kèm mẫu file chuẩn và luật chống trùng.
-
imvml Skill Map MCP Diagnosis SkillThis is what Coworker matches against the user's message to decide whether to apply the skill. Get it wrong and nothing else here runs. Use whenever someone asks about browse abandonment, drop-off, lost demand or falling conversion on a NORDVELL product; asks why shoppers are leaving a product page; asks whether to discount, promote, mark down or run an offer on a product; or asks what to do about a product that is underperforming. Also applies to follow-up questions in the same conversation, such as asking for a discount after a diagnosis, or asking the agent to act on what it found. To use ONLY when the mcp server MAP_I_DIAGNOSIS_MCP_V1 is invoked.
-
theexperiencecompany Skill Pr Image EmbeddingEmbed images (benchmark charts, screenshots, diagrams) inline in a GitHub PR or issue description from an agent session, without bloating the code diff. Use when a PR needs visual evidence and you cannot drag-and-drop into the browser.
-
arvo-ai Skill JiraJira integration for searching recent development context, tracking incidents, and managing issues during RCA
-
arvo-ai Skill FlyioFly.io integration for application monitoring, machine lifecycle management, metrics, logs, and incident remediation
-
arvo-ai Skill SlackSlack integration tools for reading channel messages and thread replies
-
arvo-ai Skill CorootCoroot eBPF-powered observability integration for kernel-level infrastructure monitoring, incidents, traces, logs, service maps, deployments, nodes, costs, and risks
-
arvo-ai Skill GithubGitHub code repository integration for investigating code changes, deployments, commits, PRs, and suggesting fixes during RCA
-
arvo-ai Skill GitlabGitLab code repository integration for investigating code changes, deployments, commits, MRs, and suggesting fixes during RCA
-
arvo-ai Skill NotionNotion workspace integration for searching pages, managing databases, creating postmortems, and exporting RCA findings
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include generate-signature-for-patch, generate-signature-for-function, generate-signature-for-globalvar. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.