Agent Tooling
Skills that build, configure or extend agents and other skills.
Search and filter within Agent Tooling
13161 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deepline-feedbackgetaero-io/gtm-eng-skillsRetired. Reporting feedback and sharing a session are documented by the CLI itself: run `deepline feedback send --help` and `deepline sessions send --help`. Kept only so installed CLIs that still list this skill keep syncing. | Stars: 82 | Updated | Claude CodeCodex | Verified | Install |
| deepline-playsgetaero-io/gtm-eng-skillsDeprecated alias. Play work is now part of `deepline-gtm`, and the CLI documents plays itself. Use when a user or script still invokes `/deepline-plays`: immediately load and follow the `deepline-gtm` skill instead. Triggers: play, plays, workflow, waterfall, webhook, cron. | Stars: 82 | Updated | Claude CodeCodex | Verified | Install |
| find-qualified-titlesgetaero-io/gtm-eng-skillsUse when finding real role-holders at known company domains from an ICP, especially prompts like 'find all job titles at these companies', 'find qualified titles', 'find RevOps or marketing-ops buyers', or when exact title discovery should precede paid people search. | Stars: 82 | Updated | Claude CodeCodex | Verified | Install |
| linkedin-url-lookupgetaero-io/gtm-eng-skillsRetired. LinkedIn URL lookup is part of `deepline-gtm`. Kept only so installed CLIs that still list this skill keep syncing. | Stars: 82 | Updated | Claude CodeCodex | Verified | Install |
| example-skillNVIDIA/SkillSpectorDocuments manifest locations for an example skill. | Stars: 26k | Updated | Claude CodeCodex | Verified | Install |
| friendly-greeterNVIDIA/SkillSpectorA friendly greeting skill that says hello to users | Stars: 26k | Updated | Claude CodeCodex | Verified | Install |
| underdeclared-agentNVIDIA/SkillSpectorA helpful assistant agent | Stars: 26k | Updated | Claude CodeCodex | Verified | Install |
| nan-overflow-detectionkali20gakki/msAgent多卡分布式训练中的 loss/gnorm 精度溢出检测与根因追溯。基于 MSProbe dump 数据,先跨 rank 定位首次出现 NaN 的源卡,再在源卡上追溯具体的溢出根因算子。 当用户需要:(1) 多卡分布式训练场景下的 NaN/Inf 溢出检测 (2) 找出首先出现 NaN 的源卡 (3) 追溯根因计算算子 (4) loss/gnorm NaN 问题定位 时使用此 skill。 | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| rl-consistency-dump-analysiskali20gakki/msAgent通用训推一致性(prefill)的 dump 数据分析 skill。分析**已采集**的训推两侧 dump:探查 dump 结构 → 语义边界映射(不要求算子同名)→ 逐边界精确门禁比对 → 定位首差异 → ULP 量化区分舍入/逻辑级 → 追放大链 → 差异点隔离验证(打桩迭代:输出打桩指令给采集侧,等它用 msprobe `load` 覆盖边界再采后比下游,枚举所有独立差异点)→ 排除根因假设 → 输出整体结论 → 产出分析报告。与具体框架/硬件解耦,适用 msprobe PrecisionDebugger 或等价工具采的任何 dump。触发词:训推一致性分析、dump 数据分析、dump 已采好帮我分析、首差异定位、所有差异点、差异点隔离、打桩指令、对齐报告、训推不一致结论、比较两侧 tensor。采集与打桩再采由 rl-prefill-consistency-dump 负责,本 skill 只消费已落盘 dump、输出打桩指令驱动再采。 | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| rl-prefill-consistency-dumpkali20gakki/msAgent训推一致性(prefill)采集侧:为训练/推理两侧采集可比的 prefill dump(输入对齐 PROMPTS_ONLY → 参数对齐校验(dump 前前置:校验两侧 config 超参/结构/权重,不一致输出参数不一致点并对齐)→ msprobe 接入采集 → 采集验证 → 恢复代码)。按用户需求判断用法:① 仅采集 dump——用户只要 dump 数据,走采集主流程(0→7→9),直接产出两侧可比 dump;② 配合分析——用户要求找所有独立差异点/差异点隔离验证/配合 rl-consistency-dump-analysis 分析时,才按分析侧打桩指令用 msprobe `load` 覆盖边界二次采集(阶段 8)再恢复代码。差异分析、首差异定位、打桩指令、整体结论由 rl-consistency-dump-analysis 承担。触发词:训推一致、训推一致性、prefill 比对、msprobe dump/采集、精度比对数据采集、打桩二次采集、参数对齐校验、参数不一致点、mHC 配置不一致、权重不同步、清卡验环境后采数据;已采 dump 的分析转 rl-consistency-dump-analysis。 | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| train-infer-op-diff-scannerkali20gakki/msAgentRL 强化学习训练与推理(rollout)路径的算子差异性扫描。当用户提供训练启动脚本路径,要求对比 Megatron 训练路径与 vLLM 推理路径的算子差异(尤其是融合算子 vs 单算子不一致)时使用此 skill。典型触发词包括"训推算子扫描"、"训推差异性"、"算子差异报告"、"融合算子对比"、"train vs infer op diff"。注意:本 skill 通过运行完整 RL 训练脚本(集成 profiling)来采集真实运行时算子(非静态源码扫描,非独立分离运行)。当训练、推理使用不同脚本时禁止触发。 | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| aisbench-dataset-compression-herdingkali20gakki/msAgent当用户直接要求进行数据集压缩测评,或在量化调优过程中需要使用 AISBench 评测工具输出数据集精度等场景时使用。 本 Skill 负责:使用 AISBench 数据集压缩代码、用 RBF Kernel Herding 算法生成压缩后的数据子集(coreset),并按用户目标交付两种产物之一: ① 接入量化调优主流程:产出独立的 coreset 数据集配置(不覆盖原始数据),回传「全集 config_name + coreset config_name」给编排层,供 evaluation.yaml 切换; ② 仅数据集压缩测评(不做量化调优):基于 example 模板生成「全集测试脚本」和「子集测试脚本」两份 shell 脚本。 暂时支持 AIME 2025 和 GPQA,其他数据集需要再结合 aisbench tools目录下 herding_coreset_selector 源码进行分析。 | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| ascend-computation-analysiskali20gakki/msAgentAnalyze Ascend NPU computation-side profiling data for single-card runs or a selected rank from multi-card runs. Use this skill when the user asks to diagnose computation bottlenecks, AI Core / AI Vector / AICPU hotspots, dynamic shape overhead, block dim issues, redundant TransData/Transpose/Cast, cross-stream waits, frequency/runtime-state issues, or fusion opportunities. | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| ascend-fusion-op-replacekali20gakki/msAgent针对昇腾 NPU 上的 PyTorch 模型,识别可做融合算子替换的代码段、替换为 torch_npu 融合算子并做性能/精度验证。当用户提到融合算子、NPU 算子替换、RMSNorm/SwiGLU/RoPE/Attention 融合、torch_npu 亲和算子等关键词是,使用本 Skill。 | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| ascend-profiler-collect-adaptionkali20gakki/msAgentAdapt torch_npu.profiler interface for AI frameworks and training/inference code on Ascend NPU. Use this skill whenever users need to integrate profiling, add performance data collection, or instrument PyTorch code with torch_npu.profiler on Huawei Ascend NPU platforms. Triggers on: "torch_npu profiler", "NPU profiling", "Ascend profiler", "profiler adaptation", "profile training", "profile inference", "add profiler to framework", "性能采集", "profiling 数据", "昇腾 profiler", and any request to add performance monitoring to Ascend NPU code. | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| quant-tuning-infer-ditkali20gakki/msAgent在 W8A8 动态量化后,用 MindIE-SD 冒烟测试 DiT 量化权重是否可加载(可选 skill)。与 `quant-tuning-evaluate`(DiT 扩展节)的区别:本 skill 仅做"能跑通 + 权重可用"的轻量验证(4~16 条 prompt,几分钟出结果),不算分;后者产出视频集交 `quant-tuning-score-dit`(AISBench-VBench 16 维度)评分,是调优回路一环。不引入 vLLM-Ascend、不做精度指标评估(FID/CLIP-score 等)。 | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| quantization-expert-experience-tuning-ruleskali20gakki/msAgent量化专家经验调优库:按「L1 通用专家调优意见 → L2 结构化专家调优意见 → L3 模型专属专家调优意见」三级递进, 输出量化精度调优的完整手段(离群值抑制 / 量化方法·粒度·对称性选型 / 校准集调整 / 敏感层回退 / 模型专属策略), 每条结论附专家原因分析与专家意见可信度等级。 本 Skill 是专家经验库,负责说明可选离群值抑制算法并询问用户选择哪些算法,以及回答「怎么调、哪些层需要回退及为什么」;不运行离群值抑制 processor,不修改 YAML、不执行量化、不做 EP 检查 / 服务化 / 任务评测。 | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| platform-rulescoupler-io/skillsUse this skill to keep the platform rules that Coupler.io skills state as fact current: budget flexibility, deliverability thresholds, attribution windows, published benchmarks, plan limits, sale dates. Triggers include: 'refresh the platform rules', 'check the Google Ads rules', 'is the Klaviyo benchmark still current', 'a platform changed its budget rules', 'add this rule to the registry'. Works from registry.md, a catalog of every rule, its source, when it was checked and which skills use it, so a refresh checks the sources instead of rereading every skill. | Stars: 41 | Updated | Claude CodeCodex | Verified | Install |
| apply-anthropic-skill-best-practicesNeoLabHQ/context-engineering-kitComprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure | Stars: 1.8k | Updated | Claude CodeCodex | Verified | Install |
| apply-anthropic-skill-best-practicesNeoLabHQ/context-engineering-kitComprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure | Stars: 1.8k | Updated | Claude CodeCodex | Verified | Install |
| apply-anthropic-skill-best-practicesNeoLabHQ/context-engineering-kitComprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure | Stars: 1.8k | Updated | Claude CodeCodex | Verified | Install |
| check-human-issueswandb/senpaiOpen GitHub Issues for human input and respond to the researcher team. Use this skill whenever you need to handle a human_issue event, respond to human issues, ask humans a question, or check team communications. Also triggers for: "any human messages?", "check issues", "respond to humans". | Stars: 39 | Updated | Claude CodeCodex | Verified | Install |
| senpai-status-checkwandb/senpaiProduce a fresh, read-only status report for a Senpai research track from GitHub, W&B, and the current agent's local controller state. | Stars: 39 | Updated | Claude CodeCodex | Verified | Install |
| wandb-primarywandb/senpaiComprehensive primary skill for agents working with Weights & Biases. Covers both the W&B SDK (training runs, metrics, artifacts, sweeps) and the Weave SDK (GenAI traces, evaluations, scorers). Includes helper libraries, gotcha tables, and data analysis patterns. Use this skill whenever the user asks about W&B runs, Weave traces, evaluations, training metrics, loss curves, model comparisons, or any Weights & Biases data — even if they don't say "W&B" explicitly. | Stars: 39 | Updated | Claude CodeCodex | Verified | Install |
| tlivey49/tlivetlive — remote approvals (Telegram/Feishu/web), live web terminal, and session monitoring for Claude Code / Codex. Use for configuring or diagnosing tlive, connecting IM platforms, printing session links, or explaining approval behavior. Triggers "tlive", "IM bridge", "phone approvals", "remote terminal", "Telegram/Feishu notifications". | Stars: 215 | Updated | Claude CodeCodex | Verified | Install |
| tlivey49/tlivetlive — remote approvals (Telegram/Feishu/web), live web terminal, and session monitoring for Claude Code / Codex. Use for configuring or diagnosing tlive, connecting IM platforms, printing session links, or explaining approval behavior. Triggers "tlive", "IM bridge", "phone approvals", "remote terminal", "Telegram/Feishu notifications". | Stars: 215 | Updated | Claude CodeCodex | Verified | Install |
| wjs-evaling-voicedrop-promptsjianshuo/claude-skillsUse when 王建硕 wants to evaluate whether a change to VoiceDrop's 挖矿 system prompt is actually better than the live version — runs the local eval harness (golden fixtures × champion-vs-candidate, same input), dispatches blind pairwise judge subagents, aggregates a win-rate verdict, and on approval promotes the candidate into agent/src/prompts/mine.js. Triggers — "评估 prompt"、"挖矿 prompt 改好了吗"、"eval prompt"、"比一比两版 prompt"、"/wjs-evaling-voicedrop-prompts". | Stars: 142 | Updated | Claude CodeCodex | Verified | Install |
| vibe-cherry-pick-integrationash1794/vibe-engineeringSafely integrates commits from parallel agent branches using sequential cherry-pick. Use after parallel work completes in isolated branches or worktrees. | Stars: 163 | Updated | Claude CodeCodex | Verified | Install |
| skillsdgiot/dgiot | Stars: 4.8k | Updated | Claude CodeCodex | Verified | Install |
| skill.check_against_rulesgpsaggese/helpersCheck a file against applicable convention rules and list violations | Stars: 158 | Updated | Claude CodeCodex | Verified | Install |