AI & ML

tools-only Bundle

MCP Server Reliability & Production Readiness

tools-only Bundle

Dependencies and LLM Providers

tools-only Bundle

Resource Evaluation: fp.dev — Agent-Native Issue Tracking

tools-only Bundle

<div align="center">

tools-only Bundle

All File Types Embedding Token Tracking Fix

tools-only Bundle

Research -- Text Selection Broken on Agent Response Panels

tools-only Bundle

Research - Research Sub-Agent Feature Deletion

tools-only Bundle

Document the multi-agent expert panel methodology as a reusable system for building datasets that inform skills and systems. The process — assign framework experts to repositories, ask structured questions, cross-examine, synthesize, map to requirements, validate — produced high-quality sourced findings. Capture this as a repeatable pattern. **Key elements to document**: - Expert assignment protocol (one agent per source repo, source-code-only evidence standard) - Question group design (themed questions → cross-examination → synthesis) - Cross-examination as adversarial validation (experts challenge each other's claims) - Phased output (discussion → requirement mapping → synthesis → validation) - Traceability chain (claim → expert citation → file:line evidence) - Session continuity handling (state file enables cross-session resumption) **Input artifacts**: `plugins/plugin-creator/skills/assessor/references/ARL/ARL-agent-instructions.md`, `qa-expert-panel.md`

tools-only Bundle

ZERG + Claude Code Agent Teams: Implementation Analysis

tools-only Bundle

Integrating Compound Engineering + Supermemory into the Halt Agent Harness

tools-only Bundle

MCP Tool YAML Configuration Implementation

tools-only Bundle

Revenue Variance Analysis (RVA) Agent Instructions

tools-only Bundle

Configurable MCP Tool Argument Exclusion

tools-only Bundle

第九课：使用 Claude Agent SDK 构建实战级研究智能体

tools-only Bundle

Instrumental Interaction: An Interaction Model for Designing Post-WIMP User Interfaces

tools-only Bundle

Summary

tools-only Bundle

Fix Report: MCP Management CLI Errors

tools-only Bundle

**Developer Guide: LLM Response Cleaning and Formatting**

tools-only Bundle

Goal

tools-only Bundle

Research - Single MD Prompt Migration

tools-only Bundle

Evaluation: LinkedIn Post — "Prompt Engineering is dead. Context Engineering is king."

tools-only Bundle

SMR SDK + MCP Control Proposal (2026-02-19)

tools-only Bundle

SMR SDK + MCP Control Proposal (2026-02-19)

tools-only Bundle

Research – Dev Install Script tiny-agent-os PyPI Package Setup

tools-only Bundle

Disable live agent text streaming by default and enable thoughts panel by default

tools-only Bundle

Image Generation Model Compatibility Fix

mjmirza Skill

Run an enterprise pre submission compliance audit on a mobile app project before uploading to the Apple App Store or Google Play. Use when the user is about to submit, ship, or release an iOS or Android app, when an app was rejected and needs a fix plan, when reviewing App Store Review Guidelines or Google Play policy compliance, or when the user mentions App Store rejection, Play Console rejection, Resolution Center, Data Safety form, privacy nutrition labels, account deletion requirement, in app purchase rules, or app review.

hlnd2t Skill

Generate the Windows-only OnServerVoiceData_IsPlayingDemo_Callee patch YAML from IVEngineClient2_IsPlayingDemo.windows.yaml using a deterministic preprocessor script. Use when locating the IVEngineClient2::IsPlayingDemo indirect call inside C_ServerVoiceHandler::OnServerVoiceData without LLM decompilation. Trigger: OnServerVoiceData IsPlayingDemo callee, voice demo call patch, IsPlayingDemo callsite

hlnd2t Skill

Find and identify the CBaseEntity_GetChangeAccessorPathInfo_1 virtual function in CS2 binary using IDA Pro MCP. Use this skill when reverse engineering CS2 server.dll or libserver.so to locate the second GetChangeAccessorPathInfo override by scanning CBaseEntity vtable slots near the known CBaseEntity_GetChangeAccessorPathInfo_2 slot for an implementation identical to CBaseEntity_GetChangeAccessorPathInfo_2. Trigger: CBaseEntity_GetChangeAccessorPathInfo_1

hlnd2t Skill

Agent fallback for the find-CNetworkGameServerBase_GetChallengeType preprocessor. Locates the CNetworkGameServerBase_GetChallengeType virtual function in CS2 engine2.dll / libengine2.so by decompiling its caller CNetworkGameServerBase_ReplyChallenge and reading the first virtual dispatch made on the server this-pointer. Use this skill only when the deterministic/LLM preprocessor (ida_preprocessor_scripts/find-CNetworkGameServerBase_GetChallengeType.py) could not resolve the vfunc — for example when the LLM_DECOMPILE step failed with a transient API error. Trigger: CNetworkGameServerBase_GetChallengeType

hlnd2t Skill

Final-guarantee fallback for the find-INetworkServerService_GetServerSerializersCRC preprocessor. Recovers INetworkServerService::GetServerSerializersCRC (a virtual function of the CNetworkServerService vtable) in CS2 engine2.dll / libengine2.so by decompiling its known predecessor CNetworkGameServer_WriteClassInfosAndSerializesToBuffer and identifying the virtual call on g_pNetworkServerService. Use this skill only when the deterministic/LLM preprocessor (ida_preprocessor_scripts/find-INetworkServerService_GetServerSerializersCRC.py) could not resolve the target. Trigger: INetworkServerService_GetServerSerializersCRC

hlnd2t Skill

Agent fallback for the find-CNetworkGameServerBase_CheckTimeouts-decompiles preprocessor. Locates the CNetworkGameServerBase_IsHLTV virtual function in CS2 engine2.dll / libengine2.so by decompiling its caller CNetworkGameServerBase_CheckTimeouts and reading the virtual dispatch made on the server this-pointer that gates the server-decided-timeout path. Use this skill only when the deterministic/LLM preprocessor (ida_preprocessor_scripts/find-CNetworkGameServerBase_CheckTimeouts-decompiles.py) could not resolve the vfunc — for example when the LLM_DECOMPILE step failed with a transient API error. Trigger: CNetworkGameServerBase_IsHLTV

hlnd2t Skill

Find and identify the velocity clamping branch inside CCSPlayer_MovementServices_FullWalkMove in CS2 binary using IDA Pro MCP, then generate a patch signature to disable it. Use this skill when reverse engineering CS2 server.dll or libserver.so to locate and patch the speed-clamp if-branch that caps player velocity to maxspeed inside FullWalkMove. Trigger: FullWalkMove speed clamp, velocity clamping patch, FullWalkMove SpeedClamp, disable maxspeed clamp

hlnd2t Skill

Find and identify the CNetworkMessages_GetNetworkSerializationContextData virtual function in CS2 binary using IDA Pro MCP. Use this skill when reverse engineering CS2 networksystem.dll or libnetworksystem.so to locate the getter vfunc by reusing the known CNetworkMessages_SetNetworkSerializationContextData slot and checking the adjacent CNetworkMessages vtable entry. Trigger: CNetworkMessages_GetNetworkSerializationContextData

hlnd2t Skill

Find and patch the water jump velocity inside CCSPlayer_MovementServices_CheckJumpButton in CS2 binary using IDA Pro MCP. This patch changes the water jump velocity from 100.0f to 145.0f by modifying the immediate operand of a mov instruction. Use this skill when reverse engineering CS2 server.dll or libserver.so to locate and patch the water jump height value. Trigger: water jump patch, CheckJumpButton water velocity, jump height patch, water jump 145

nvidia Bundle

Audit and update TensorRT-Model-Connect documentation when code, public APIs, family ownership, commands, or model support have changed.