Skip to content

Explore skills

Search every indexed skill by name, description, repository or instructions, then narrow the results.

Showing 50281–50310 of 52787 skills

renderersBdM-15/capture-insightsOffice-document renderers for pursuit deliverables — Markdown to DOCX (Pandoc/OpenXML) and JSON envelopes to styled XLSX (openpyxl). USE WHEN the user asks to export a Studio markdown file to Word, convert compliance matrix JSON to Excel, render proposal outline as DOCX, or run a one-off format conversion on files under pursuits/. Consumer skills (proposal-generator, subcontractor-sow-builder, compliance-auditor) call these scripts internally; users can also run renderers directly from Agent Skills or chat. DO NOT USE FOR drafting content (use proposal-generator), visual decks/PDF/PPTX (use huashu-design), or domain analysis.Stars: 0Updated Claude CodeCodexUnverifiedInstall
rfp-reverse-engineerBdM-15/capture-insightsReverse-engineers a federal RFP we received — given the SOW/PWS and evaluation criteria already in the Theseus KG, reconstructs the CO's hidden decision tree (upstream `sow-pws-builder` 6 scope blocks + 3 intake answers), surfaces hot buttons, ghost language, discriminator hooks, missing-section signals, and CPFF-form / Section-5 / QASP / Key-Personnel traps. USE WHEN the user asks "what scope decisions did the CO already make?", "reverse engineer this RFP", "what hot buttons are hiding in this PWS?", "where are the discriminator hooks?", "did they pick CPFF completion or term form?", "anything suspiciously missing?", or any variant of decoding CO intent. Pulls `requirement`, `deliverable`, `proposal_instruction`, `evaluation_factor`, `clause`, `performance_standard` from the active workspace KG and emits a JSON envelope feeding `proposal-generator`. DO NOT USE FOR proposal prose (`proposal-generator`), pricing (`price-to-win`), clause audit (`compliance-auditor`), or sub SOW (`subcontractor-sow-builder`).Stars: 0Updated Claude CodeCodexUnverifiedInstall
sam-monitor-builderBdM-15/capture-insightsCreate a SAM.gov search monitor from a pursuit or expiring row — persists to Pipeline and writes sam_monitor.md in the pursuit folder. Primary admin rote task for capture managers watching recompetes.Stars: 0Updated Claude CodeCodexUnverifiedInstall
sam-scanBdM-15/capture-insightsSearch SAM.gov for live notices matching a pursuit row (agency, incumbent, NAICS keywords) and save results to sam_scan.md. Use for admin monitor setup, presolicitation watch, or when user asks what is live on SAM for an expiring contract.Stars: 0Updated Claude CodeCodexUnverifiedInstall
subcontractor-sow-builderBdM-15/capture-insightsDrafts a federally-defensible SOW or PWS the prime issues to a subcontractor / teaming partner — same FAR 37.102(d) / 37.602 / 16.601(c)(2) / 16.306(d) discipline a contracting officer applies, opposite seat. USE WHEN the user asks to "write a SOW for our sub", "draft a PWS for [Partner]", "build the teaming-partner statement of work", "convert this SOO into a sub SOW", "we need a SOW the sub will sign", or any variant of authoring a downstream work statement. Walks the upstream 3-phase tree (acquisition intake → 6 scope blocks → 14-section assembly), pulls scope from the active Theseus KG (requirements, deliverables, work_scope_items, performance_standards), enforces FAR 37.102(d) "no FTEs in body", emits a chat-only staffing handoff for the prime's cost build, writes Markdown for `renderers` → .docx. DO NOT USE FOR prime proposal prose (`proposal-generator`), reverse-engineering an RFP (`rfp-reverse-engineer`), pricing the sub (`price-to-win`), or clause audit (`compliance-auditor`).Stars: 0Updated Claude CodeCodexUnverifiedInstall
teaming-finderBdM-15/capture-insightsFind adjacent vendors and subs (not top market primes) who fill a capability gap against a displacement target using USASpending flows and SAM entity signals. Use when user defines a teaming gap and wants vault-ready partner shortlist with citations.Stars: 0Updated Claude CodeCodexUnverifiedInstall
value-propositionsBdM-15/capture-insightsDraft outcome-led value proposition hooks for a target agency or pursuit using vault context and mission alignment. Use when user asks for messaging angles for capture — catalog skill from coreyhaines marketingskills pattern.Stars: 0Updated Claude CodeCodexUnverifiedInstall
vault-index-rebuildBdM-15/capture-insightsRebuild Knowledge Vault index.md from disk truth per capture-llm-wiki schema. Use when vault structure drifted or after bulk ingest of pursuit folders. Karpathy LLM wiki maintenance skill.Stars: 0Updated Claude CodeCodexUnverifiedInstall
vault-lintBdM-15/capture-insightsLint native Knowledge Vault markdown against capture-llm-wiki schema — frontmatter, wikilinks, citation hygiene. Use when user asks to health-check the vault or before bulk LLM synthesis. Karpathy LLM wiki maintenance skill.Stars: 0Updated Claude CodeCodexUnverifiedInstall
vault-synthesizeBdM-15/capture-insightsSynthesize or append structured wiki notes from dashboard signals into brain/ or global/ per capture-llm-wiki schema with citations. Use when user wants LLM to compound vault knowledge from USASpending context — human review recommended.Stars: 0Updated Claude CodeCodexUnverifiedInstall
compare-result-analyzerAscend/msagent分析 msProbe compare 精度比对结果文件(CSV/XLSX),定位整网精度问题与数值差异。支持统计量模式,输出分析报告。支持辅助信息协助定位:辅助信息(历史结论/已知根因/已排除算子/嫌疑区域等)建议在请求中附带(不依赖交互工具)。若请求中未附带且运行环境无 AskUserQuestion,则跳过辅助信息收集、照常完成分析,报告中省略辅助信息章节并注明原因。Stars: 0Updated Claude CodeCodexUnverifiedInstall
deterministic-calculation-analysisAscend/msagent执行msProbe数据比对并分析比对结果,定位确定性计算问题首个输入一致输出不一致的API。Stars: 0Updated Claude CodeCodexUnverifiedInstall
nan-overflow-detectionAscend/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: 0Updated Claude CodeCodexUnverifiedInstall
precision-debuggerAscend/msagent在遇到模型精度问题,需要分析定位时使用。典型的精度问题包括回复输出中有乱码或重复、精度测评不达标等。Stars: 0Updated Claude CodeCodexUnverifiedInstall
rl-consistency-analysisAscend/msagent训练与推理数据不一致的端到端根因分析。当模块映射/值比较不足以定位问题时使用,可追踪首个可信的分歧边界,过滤融合或结构性误报,遵循生产者-消费者链,并生成包含具体假设和证据的根因报告。Stars: 0Updated Claude CodeCodexUnverifiedInstall
spike-root-cause-analysisAscend/msagent分布式训练梯度尖刺 (Gradient Spike) 根因定位。基于梯度监控数据 (trend.db/CSV)、 msprobe dump 统计数据,三阶段渐进式从异常坐标定位逐层深入到算子级根因。 当用户明确指明分析梯度尖刺问题时使用此 skill。 即便用户提供以上数据,但未指明分析梯度尖刺问题时,不可使用此skill。Stars: 0Updated Claude CodeCodexUnverifiedInstall
train-infer-op-diff-scannerAscend/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: 0Updated Claude CodeCodexUnverifiedInstall
verl-omni-msprobe-dumpAscend/msagent为 verl-omni 接入或修复 MSProbe 训推一致性采集,生成打点代码、样本关联日志和诊断启动脚本。 用于 diffusion/omni 的 rollout 与 actor 数据采集、dump 缺失或配对失败;不负责精度根因分析。Stars: 0Updated Claude CodeCodexUnverifiedInstall
github-raw-fetchAscend/msagent当用户提供 GitHub 文件页面链接,或希望读取某个仓库中的源码、配置、README、Markdown、docs 内容时,使用此技能。技能支持将 `github.com/<owner>/<repo>/blob/<ref>/...` 转换为 `raw.githubusercontent.com` 链接并获取内容;读取仓库 docs 时先列出仓库根目录、按真实结构定位 `docs/` 目录(语言子目录、索引),不要假设所有仓库都有固定目录或 `agent_router.md`(该文件仅当根目录确实存在时才可选参考)。Stars: 0Updated Claude CodeCodexUnverifiedInstall
aisbench-dataset-compression-herdingAscend/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: 0Updated Claude CodeCodexUnverifiedInstall
run-aisbench-evaluationAscend/msagent解析中文自然语言中的 AISBench 测评需求,检查 Python 与 AISBench 运行环境,通过分轮追问确认关键配置,将基准名称映射为仓库内的数据集任务,在用户最终确认后生成并执行 AISBench CLI,并返回精度指标和产物路径。适用于用户要求使用 AISBench 评测模型或运行数据集;不适用于实现新数据集或仅解释基准概念。Stars: 0Updated Claude CodeCodexUnverifiedInstall
document-ux-reviewAscend/msagent当用户希望你像第一次接触项目的人一样,真实按仓库的 README、安装文档或 quick start 跑一遍,并判断“新人能不能走通”“文档是否可用”“哪里会卡住”“安装/启动说明是否对新手友好”时,使用这个 skill。它适用于 repo onboarding audit、documentation UX review、quickstart validation、README walkthrough、按文档验证安装与运行并输出问题报告的场景;即使用户只是说“按 README 试一下”“帮我检查这个仓库文档能不能跑通”“看看 quick start 为什么带不动新人”,也应触发。不要用于纯翻译、润色、摘要、风格对比、治理项检查,或只想直接修环境/修单个报错而不做完整文档体验审查的请求。Stars: 0Updated Claude CodeCodexUnverifiedInstall
msmodeling-device-configAscend/msagent在需要根据自然语言规格为未支持硬件新增或更新 DeviceProfile 设备画像条目时使用Stars: 0Updated Claude CodeCodexUnverifiedInstall
msmodeling-env-installerAscend/msagentInstall and verify the msmodeling development environment. Use when the user explicitly asks to install msmodeling dependencies, set up this repository, create `myenv` with `uv`, install this repository's `requirements.txt`, set project `PYTHONPATH`, or configure `HF_ENDPOINT`; if the user only says to install an environment, ask whether they mean msmodeling dependencies before proceeding.Stars: 0Updated Claude CodeCodexUnverifiedInstall
msmodeling-optix-deployAscend/msagent当用户需要部署 msmodeling optix 服务化自动寻优工具时使用。负责安装与验证。Stars: 0Updated Claude CodeCodexUnverifiedInstall
msmodeling-optix-param-recommendAscend/msagent当首次使用 msmodeling optix 的用户需要根据硬件、模型、负载和优化目标推荐 MindIE/vLLM 寻优参数、搜索范围、benchmark 侧字段或 config.toml 片段时使用。Stars: 0Updated Claude CodeCodexUnverifiedInstall
msmodeling-text-generate-executorAscend/msagentInteractively gather parameters for `python -m cli.inference.text_generate`, generate a concrete text generation simulation command, explain assumptions, ask for execution confirmation, then run the command and summarize performance metrics. Use when the user wants to validate a specific model, hardware profile, batch/query size, prefill or decode scenario, TP/DP/EP/MOE parallel strategy, profiling database, chrome trace, empirical metrics export, or a best row produced by throughput_optimizer.Stars: 0Updated Claude CodeCodexUnverifiedInstall
msmodeling-throughput-optimizer-executorAscend/msagentInteractively gather parameters for `python -m cli.inference.throughput_optimizer`, generate a deployment simulation command, explain assumptions, ask for execution confirmation, then run the simulation and summarize the best parallel strategy. Use when the user wants to evaluate a model on one or more hardware profiles, compare hardware targets, compare aggregation versus disaggregation versus PD ratio optimization, choose TP/EP/MOE-DP search ranges, or obtain recommended concurrency, throughput, TTFT, and TPOT results from throughput modeling.Stars: 0Updated Claude CodeCodexUnverifiedInstall
msdebug-basic-usageAscend/msagent昇腾AscendC算子调试工具(msDebug)技能,含两大流程:①上板调试——算子加 -g -O0 编译后由 msdebug 拉起,支持断点、单步、变量/内存打印、核切换、寄存器读取;②coredump解析——用户指定 core 文件路径后,msdebug 加载解析挂掉代码行/异常调用栈/现场变量。触发关键词:msdebug、算子调试、上板调试、断点、单步调试、打印变量、读内存、核切换、寄存器、coredump、core文件、调用栈、崩溃解析Stars: 0Updated Claude CodeCodexUnverifiedInstall
msot-msopprof-operator-profilerAscend/msagent当用户希望使用 msOpProf(`msprof op` / `msprof op simulator`)对昇腾 AI 算子做上板或仿真性能调优、解释 `aic-metrics`/`trace.json`/`visualize_data.bin`、选择 device vs simulator 路径、排查 `--soc-version`/`--export`/`signal 6`/`Bad address`/热点图或流水图相关问题,或要求生成固定分析报告模板(算子基本信息 / 关键数据 TOP5 / 核心瓶颈 TOP5 / 优化建议 TOP5)时,使用本技能。它负责先判定模式、输入形态与芯片/能力边界,再给出正确命令、结果解读、固定报告输出与高频踩坑规避;不要把经验案例当成通用规则。Stars: 0Updated Claude CodeCodexUnverifiedInstall