AI & ML

nvidia Bundle

Use when monitoring GitHub pull request CI, diagnosing failed checks, rebasing branches onto github/main, applying narrowly scoped fixes, and updating PRs until their latest checks are green or a human blocker is identified.

nvidia Bundle

Measure one TensorRT-Model-Connect model through its public Task API or run a checked-in performance-matrix entry with comparable evidence.

nvidia Bundle

Review a TensorRT-Model-Connect GitHub PR or local contributor branch against the current post-#1093 model-family isolation architecture, repository rules, behavioral correctness, and exact-head validation evidence. Use for contributor self-review before marking a PR ready, or when deciding whether a community PR is compliant, decoupled, merge-ready, or needs maintainer feedback. The review is read-only unless the user separately asks to publish it or change the contribution.

wuyoscar Bundle

Design Jev questions from a task or an existing prompt. Set up a provider, batch independent decisions, and handle custom judgments, agent checkpoints, tool routing or context checks. Read only the guide needed for this task.

wuyoscar Bundle

Use for user-defined inbox, support-ticket, feedback or record classification and prioritization, especially bulk parallel judgments with sufficient per-record context. Accepts smoke_test to have the host agent write and validate a task-specific paired pilot before bulk work. Produces labels and review queues, not replies or automatic mailbox changes.

nvidia Bundle

Add a Hugging Face or local checkpoint to TensorRT-Model-Connect as a self-contained family, or extend the family that already owns it.

nvidia Bundle

Implement or review FP16 and BF16 behavior in one family-owned, strongly typed TensorRT network without changing unrelated families.

nvidia Bundle

Use when publishing an existing TensorRT-Model-Connect change as a GitHub pull request. Verifies authenticated repository access, branch and diff scope, validation evidence, commit identity, reviewer-facing text, exact pushed head, and the created draft PR without merging it.

nvidia Bundle

Diagnose a TensorRT-Model-Connect family whose native output disagrees with its declared reference or family-owned correctness contract.

nvidia Bundle

Draft, revise, or review Git commit messages, PR titles, PR descriptions, and squash or rebase merge messages. Use when Codex needs to summarize a diff for reviewers, convert rough notes into a commit or PR message, check a message against Git and Conventional Commits style, or prepare repository contribution text before pushing/opening a PR.

nvidia Skill

Prepare a TensorRT-Model-Connect development or validation environment from a fresh checkout on a host without a known working setup.

nvidia Bundle

Use when converting QA findings, black-box failures, red-team reports, regression evidence, or local bug notes into GitHub Issues for NVIDIA/TensorRT-Model-Connect. Standardizes checking issue templates, checking labels, de-duplicating existing issues, drafting a bug report, creating the issue on GitHub, applying the bug label, and verifying the created issue.

nvidia Bundle

Evaluate supported precision, quantization, or selected FP32-layer choices for one TensorRT-Model-Connect family with matched correctness and timing.

baijunjie Bundle

给当前项目装上（或更新）项目级 docs skill 与 doc-writer 子代理，让总索引、项目地图、产品文档的维护规则随仓库提交。用于"给这个项目配文档规范""初始化项目文档结构""让 agent 维护文档""更新项目里的 docs skill"等场景。

baijunjie Bundle

装上（或更新）通用 agent 工作流规范——注释规范、提交信息、分派子代理、交付前自检，外加五个通用子代理。默认装进当前项目，也可安装到用户级配置、对当前用户环境中的所有项目生效。用于"给这个项目配 agent 规范""装通用子代理""配一台新电脑""同步我的 agent 工作流""更新全局规则"等场景。

baijunjie Bundle

给当前项目装上（或更新）git worktree 开发流程规则，按宿主写入 AGENTS.md 或 CLAUDE.md，并让 .gitignore 忽略 worktree 目录。用于"给这个项目配 worktree 流程""让 agent 在独立分支上开发""初始化 git worktree 规范"等场景。

google Bundle

Use when local tools cannot provide a needed capability and a SAM agent mesh can: inspect mesh state, discover reachable services/tools, describe and call namespaced remote MCP tools, and reach OpenAI-compatible inference models hosted by mesh peers. Also use to set up, join, or reconnect a sam-node when its MCP tools are not callable yet.

google Skill

Use when the task should be delegated to a remote A2A agent on the SAM agent mesh: send it work with send_agent_task (with text, structured data, or file attachments), check agent capabilities with get_agent_card, poll results with get_agent_task, hold multi-turn conversations, and enforce data-residency labels on every call. Also use to set up the sam-a2a-bridge MCP server when those tools are not callable yet.

cogniztech Bundle

Cross-harness continuity for AI coding agents: persistent project state, shared memory, and handoffs via the `stateroot` CLI. Use when working in a project that has a `.stateroot/` directory — consume the auto-injected identity/resume digest on the first usable prompt, run `stateroot resume --harness <id>` only if that digest is missing (unpiped; never `| head` / `| tail` / line limits — the full digest is the state of record), `stateroot checkpoint` after every state-changing step, check the failed-approaches log before attempting an approach, and run `stateroot handoff write` before ending a session or switching agent harnesses.

baijunjie Bundle

装上（或更新）Concise+ 回答规则，让 Claude Code 使用自定义 output style，Codex 把等价规则合并进 AGENTS.md。默认装进当前项目，也可安装到用户级配置。用于"agent 报告太啰嗦""让它少说废话只给结论""别顺着我说""配输出风格""装 output style"等场景。

baijunjie Skill

Skill 编写规范。创建或修改 SKILL.md 时使用。规定 skill 只写 agent 推不出来的规则、必须自包含不引用代码、给判断标准而非操作脚本。

chartyr Bundle

Play or validate Slay the Spire 2 through the local sts2-ai-agent MCP tools, including access to live game metadata from the Mod API (cards/relics/monsters/etc.) for richer decision-making. Use when navigating the main menu, timeline, map, combat, rewards, shops, rest sites, events, chests, card selections, potions, or debug-enabled test flows, and when another agent needs a strict state-first workflow that avoids stale indexes, invalid room actions, and tool-profile confusion.

hlnd2t Bundle

Batch-dump vtables from IDA Pro MCP by searching mangled symbol patterns, then write a merged YAML file beside the binary. Use this skill when you need to find and export all vtables matching a name pattern (e.g., all GameSystem vtables) in one shot. Triggers: dump vtables, batch vtable dump, export vtables, dump all vtables matching pattern

fast-editor Skill

Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.

hlnd2t Skill

Find a function's vtable offset and index using IDA Pro MCP. Use this skill when you have a function address and need to determine its position in a vtable by iterating through vtable entries. Triggers: vtable index, vftable offset, virtual function table position, find function in vtable

hlnd2t Skill

Find a function's vtable address using IDA Pro MCP. Use this skill when want to get exact virtual address of a class. Triggers: get vftable address, get virtual function table, find vtable, get vtable

hlnd2t Skill

Write function analysis results as YAML file beside the binary using IDA Pro MCP. Use this skill after completing function identification and signature generation to persist the results in a standardized YAML format. For virtual functions with known vtable index, use write-vfunc-as-yaml instead.

hlnd2t Skill

Write patch analysis results, including patch_sig match VA/RVA, as a YAML file beside the binary using IDA Pro MCP. Use this skill after identifying a patch target and generating a unique signature to persist patch_name, patch_va, patch_rva, patch_sig, optional patch_sig_disp, and patch_bytes in a standardized format.

hlnd2t Skill

Write virtual function analysis results as YAML file beside the binary using IDA Pro MCP. Use this skill after completing virtual function identification, signature generation, and vtable analysis to persist the results in a standardized YAML format.

hlnd2t Skill

Write vtable analysis results as YAML file beside the binary using IDA Pro MCP. Use this skill after locating a vtable to persist the results in a standardized YAML format.

bankrbot Bundle

Discover, bet on, track, and settle Hunch prediction markets in natural language. Trigger when a user wants to bet, take a position, or get odds on a crypto outcome — token market-cap milestones and flips, launchpad races (Bankr vs pump.fun volume / #1-days / launches over a cap), token head-to-head outperformance, mcap strike-ladders, and up/down price rounds. Also trigger on "what can I bet on about $TOKEN", "odds on …", "take YES/NO on …", "show my Hunch bets", "did my market resolve". Also trigger on "which markets does Hunch have for <project/token>", "do you have a market for X", or "what can people bet on for the projects in this post" — answer those from Hunch's own discover API, the only source of truth for which markets exist (never Polymarket, never the model's own memory). Settles in USDC on Base via x402 ($1 minimum, no Hunch maximum); every bet returns an on-chain proof.

inkbox-ai Skill

Use when writing TypeScript or JavaScript code that imports from `@inkbox/sdk`, uses `npm install @inkbox/sdk`, or when adding email, mailbox imports, phone, text/SMS, iMessage, A2A task/message history, contacts, notes, contact rules, vault, tunnels, mailbox storage, mail clients (IMAP/SMTP), or agent identity features using the Inkbox TypeScript SDK.

inkbox-ai Skill

Use when writing Python code that imports from `inkbox`, uses `pip install inkbox`, or when adding email, mailbox imports, phone, text/SMS, iMessage, A2A task/message history, contacts, notes, contact rules, vault, tunnels, mailbox storage, mail clients (IMAP/SMTP), or agent identity features using the Inkbox Python SDK.

hlnd2t Skill

Write global variable analysis results as YAML file beside the binary using IDA Pro MCP. Use this skill after completing global variable identification and signature generation to persist the results in a standardized YAML format.

hlnd2t Skill

Find and identify the CNetworkMessages destructor virtual function in CS2 binary using IDA Pro MCP. Use this skill when reverse engineering CS2 networksystem.dll or libnetworksystem.so to locate the CNetworkMessages_dtor vfunc by scanning the last three entries of the CNetworkMessages vtable. Trigger: CNetworkMessages_dtor

hlnd2t Skill

Write struct member offset analysis results as YAML file beside the binary using IDA Pro MCP. Use this skill after identifying a struct member offset and optionally generating a signature for it to persist the results in a standardized YAML format.