AI & ML

yhy0 Bundle

Use when facing digital forensics or misc challenges involving disk images, memory dumps, network captures, steganography, file format analysis, encoding puzzles, sandbox escapes, or archive manipulation

yhy0 Skill

Use when stuck, looping on same approach, making no progress after multiple tool calls, or receiving a stagnation warning from the system. Also trigger when you catch yourself retrying the same command with minor variations, getting repeated Permission denied or timeout errors, or unable to advance past a specific step for 10+ tool calls.

nvidia-nemo-megatron-bridge Skill

Structured single-agent code review workflow for PRs, commits, and local diffs. Use when asked to review code, understand a PR, rubber duck a change, prepare GitHub review comments, compare a change against Megatron Bridge conventions, or produce high-signal findings without subagents or tmux.

nvidia-nemo-megatron-bridge Skill

Structured framework for exact HF↔MCore weight verification, forward-pass logit correlation, and optional strict numerical diagnostics. Use when debugging weight mismatches, verifying HF↔MCore checkpoint round-trips, choosing verification tools, or investigating conversion commits that caused parity failures. References existing tools and the add-model-support skill.

nvidia-nemo-megatron-bridge Skill

Bump a pinned dependency (TransformerEngine, Megatron-LM, NRX, etc.), regenerate the lockfile, open a PR, and drive it to green by attaching a watchdog to the "CICD NeMo" workflow and quarantining failing functional tests as flaky until the run is green.

endorlabs Skill

Demo Endor Labs capabilities using simulated data, no account required. Use when the user says "try endor", "demo", "endor without account", "show me what endor can do", or when MCP auth fails and user wants to see capabilities before signing up. Do NOT use when the user has a working Endor Labs account — use real scans instead.

endorlabs Skill

Onboarding wizard for Endor Labs. Guides users through prerequisites, MCP server configuration, authentication, namespace setup, and running their first scan. Use when the user says "endor setup", "configure endor", "endor auth", "set up endor", "install endor", "endor onboarding", or when any MCP tool fails with an auth or namespace error. Do NOT use when the user already has a working setup — route to specific skills instead.

msaad00 Skill

Discover AI agents, MCP servers, and configurations on this machine or environment. Use when: "find agents", "what's configured", "doctor", "what MCP servers", "show me what's installed", "mcp inventory".

msaad00 Skill

MCP server security registry and trust assessment — look up servers in the 1133-entry server security metadata registry, run pre-install marketplace checks, batch fleet risk scoring, assess skill file trust, and run SAST code scans. Use when the user mentions MCP server trust, registry lookup, marketplace check, or skill trust assessment.

msaad00 Skill

AI compliance and policy engine — evaluate scan results against OWASP, NIST, SOC 2, ISO 27001, CMMC, EU AI Act, AISVS v1.0, and related frameworks. Generate SBOMs and compliance reports. Use when: "compliance report", "NIST", "SOC 2", "ISO 27001", "OWASP", "EU AI Act", "AISVS", "generate SBOM", "policy check".

msaad00 Skill

Diagnose issues, check prerequisites, and validate configurations. Use when: "doctor", "debug", "why failing", "validate config", "check prerequisites", "something is broken", "db status", "fix my setup".

msaad00 Skill

Discover Snowflake Cortex, Snowpark, notebook, Streamlit, MCP, and AI-observability assets from the operator's environment, emit canonical agent-bom inventory JSON, and scan it without giving agent-bom long-lived Snowflake credentials. Use when a user asks to inventory Snowflake AI or Cortex infrastructure as canonical inventory.

msaad00 Skill

Use agent-bom to check package, SBOM, inventory, and agent dependency exposure against OSV, GitHub Security Advisories, NVD, EPSS, and CISA KEV with explicit data-boundary choices. Use when a user asks for CVE lookup, advisory intelligence, exploitability context, fix versions, GHSA/OSV/NVD enrichment, or package vulnerability triage.

yhy0 Skill

隐藏关卡众包渗透 — 将主赛场靶场包装为零界隐藏关卡，发帖+群发私信通知全论坛 agent。被 post-cycle 中策略 F7 触发，或手动调用。

jochenyang Skill

Create agent teams for parallel collaboration. Use when user mentions team, parallel, multi-agent, coordinate, collaborate, review team, multiple perspectives, or says "agent-teams".

jochenyang Bundle

MCP server development for AI agents. Designs tool schemas, implements Python/TypeScript servers, creates evaluation tests. Use when user asks to build MCP server, create tool integration, or develop Claude plugins. Supports GitHub/Notion/Slack integrations.

nvidia-nemo-megatron-bridge Skill

External NeMo-RL end-to-end validation workflow for Megatron-Bridge model/provider changes, including downstream compatibility checks, external RL lifecycle behavior, Megatron policy setup, HF import/export, checkpoint/resume, non-colocated vLLM refit, delta weight transfer, optional LoRA/generation variants, and questions such as "does this model work in NeMo-RL", "run NeMo-RL e2e", or "external RL loop validation". Covers running NeMo-RL Megatron policy jobs from a Bridge checkout, choosing GRPO/SFT/checkpoint/non-colocated refit variants, setting PYTHONPATH so NeMo-RL imports the local Bridge tree, and reporting pass/fail evidence.

nvidia-nemo-megatron-bridge Bundle

Guide for adding support for new LLM or VLM models in Megatron-Bridge. Covers bridge, provider, recipe, tests, docs, and examples.

nvidia-nemo-megatron-bridge Bundle

Profile, validate, and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs. Covers replay evidence, matched eager A/Bs, model-specific scopes, regressions, and failures.

nvidia-nemo-megatron-bridge Bundle

Create or update concise, agent-readable Megatron Bridge model verification cards. Use when adding a model support card, auditing cross-model convergence comparability or verification coverage, recording conversion, deterministic inference, training, checkpoint resume, post-SFT export, performance, or weak-scaling results, or preparing a model-support PR. Enforce the required core inventory, convergence-versus-performance contracts, optional performance items, public Slurm launcher commands, training metrics, important-feature allowlist, and a strict privacy boundary that excludes private runtime wiring, internal paths, credentials, and job metadata.

nvidia-nemo-megatron-bridge Bundle

Techniques for reducing peak GPU memory in Megatron Bridge, including expandable segments, PEFT plus sequence-parallel input re-gather, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM fixes. Use for GPU OOMs, inadequate memory headroom, LoRA or PEFT activation pressure, memory fragmentation, and memory regressions.

nvidia-nemo-megatron-bridge Bundle

Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT goal. Use when selecting a starting recipe, comparing library and benchmark configs, resizing parallelism for a GPU allocation, or distinguishing convergence changes, semantics-preserving execution tuning, and benchmark-only shortcuts.

nvidia-nemo-megatron-bridge Bundle

Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.

nvidia-nemo-megatron-bridge Bundle

Operational guide for sharding a VLM vision encoder across the language model's context-parallel ranks in Megatron-Bridge, including config knobs, code anchors, load-balance pitfalls, and measured impact.

nvidia-nemo-megatron-bridge Bundle

Analyze and compare PyTorch CUDA memory snapshots produced by Megatron Bridge's ProfilingConfig(record_memory_history=True). Replays the recorded allocation timeline to plot memory over time, compare two runs, and attribute peak memory to source code locations.

nvidia-nemo-megatron-bridge Bundle

Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute. Use for activation memory OOMs or regressions involving recompute_granularity, recompute_num_layers, recompute_modules, recompute_method, selective recompute, full recompute, or activation checkpointing.

nvidia-nemo-megatron-bridge Bundle

Select and validate an MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for a fixed workload and runtime. Covers backend availability, topology, matched A/B evidence, routing semantics, and failure diagnosis. Use when choosing a dispatcher or tracing a regression or crash to the MoE dispatcher configuration.

nvidia-nemo-megatron-bridge Bundle

Evidence-gated workflow for MoE performance optimization in Megatron Bridge. Covers measurement contracts, the Three Walls framework, parallel folding, profiling, matched A/B tuning, and final validation. Use for full MoE throughput tuning or diagnosing a regression involving memory, communication, compute, or host/launch overhead.

botlearn-ai Bundle

BotLearn — AI Agent capability platform CLI. **Core value: `learn`** — run the 5-stage learning loop (Read → Distill → Engage → Discover → Report) end-to-end on the model side. Triggers on: learn, learn from community, study the feed, distill, knowledge round, learning loop, read and reflect, summarize and report, what did I learn today, 学习一下, 去学习, 读社区, 从社区学, 蒸馏, 提炼一下, 复盘一下, 知识闭环, 跑一遍学习, 读完总结上报, benchmark, score, evaluate, skill check, measure, gear score, my score, results, report, recommend, install skill, uninstall skill, remove skill, improve, trial run, report run, just ran a skill, after running skill, update botlearn, continue botlearn, botlearn, community, social, post, comment, discuss, dm, channel, heartbeat, register, claim, setup, skill experience, share experience, skill-experience, post experience, attach file, upload file, upload image, post with attachment, attach image, 体检, 评估, 评测, 安装, 卸载, 上报执行, 执行上报, 试跑, 刚跑完, 社区, 发帖, 技能经验, 分享经验, 实战经验, 上传附件, 附件发帖, 附带图片, 继续, 我的分数, 更新, 注册.

tryghost Bundle

Create a database migration to add a table, add columns to an existing table, add a setting, or otherwise change the schema of Ghost's MySQL database. Use this skill whenever the task involves modifying Ghost's database schema — including adding, removing, or renaming columns or tables, adding new settings, creating indexes, updating data, or any change that requires a migration file in ghost/core. Also use when the user references schema.js, knex-migrator, the migrations directory, or asks to "add a field" or "add a column" to any Ghost model/table. Even if the user frames it as a feature or Linear issue, if the implementation requires a schema change, this skill applies.

antoniolg Skill

Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.

antoniolg Bundle

End-to-end YouTube publishing workflow using ordered scripts: prepare/concat video, upload draft, transcribe with Parakeet, generate copy with the calling model, optionally prepare English dubbing assets, render thumbnails, update YouTube metadata, then schedule socials (PostFlow) 15 minutes after publish.

lprior-repo Bundle

Gas Town multi-agent orchestration expert for workspace setup, rig management, agent runtime configuration (claude, opencode, codex, cursor, amp, gemini, copilot, auggie, pi, omp), bead/issue tracking with bd, convoy work tracking, polecat lifecycle, witness/refinery/deacon monitoring, formula workflows, molecules, mail/nudge communication, scheduling, escalation, dashboard/feed monitoring, and cross-rig coordination. Use this skill whenever the user mentions Gas Town, gt commands, rigs, polecats, convoys, beads issues, slinging work, multi-agent coordination, agent orchestration, or any gt CLI operation — even if they don't explicitly say 'Gas Town'.

lprior-repo Bundle

Deterministic planning agent that decomposes complex work into atomic beads using enhanced 16-section template.

lprior-repo Bundle

OpenCode CLI expert. Covers sessions, agents, providers, MCP servers, config, server mode, and GitHub integration.

lprior-repo Skill

Ruthless QA agent for Dioxus UI apps. Uses pure-Rust fantoccini (WebDriver) to automate headless Chrome. Verifies UI components, tests routing, and validates DOM updates. Includes screenshot capabilities.