Explore skills
Showing 56671–56700 of 77104 skills
Server-Side Template Injection (SSTI) occurs when user input is embedded directly into a template engine (Jinja2, Twig, Freemarker, Pebble, Velocity, Smarty, Mako) and evaluated, enabling remote code execution. Detect via math expressions `{{7*7}}` returning `49`, or `${7*7}`, `<%= 7*7 %>`. Leads to full RCE via template sandbox escape, Python `__class__.__mro__` traversal, and Java reflection chains. Tools: tplmap, Burp Suite.
ShulkwiSEC/bb-huge
Stars: 27Claude CodeCodexCritical rules that must always be followed
bikidsx/comp
Stars: 0Claude CodeCodexPrisma schema conventions and migration workflow
bikidsx/comp
Stars: 0Claude CodeCodexHow to write and use scheduled Trigger.dev tasks
bikidsx/comp
Stars: 0Claude CodeCodexCritical rules that must always be followed
bikidsx/comp
Stars: 0Claude CodeCodexPrisma schema conventions and migration workflow
bikidsx/comp
Stars: 0Claude CodeCodexHow to write and use scheduled Trigger.dev tasks
bikidsx/comp
Stars: 0Claude CodeCodexStream rows continuously into Apache Iceberg tables on S3 Tables (or standard Iceberg on a general purpose bucket) using Amazon Data Firehose with IcebergDestinationConfiguration. Covers the Firehose stream, the optional record-shaping Lambda (ProcessingConfiguration), the Lake Formation grants required for Firehose to write through Glue, and the three-phase CloudFormation deploy that gates the stream on grants existing. Triggers on: stream into data lake, Firehose to S3 Tables, Firehose to Iceberg, real-time ingestion to Iceberg, Firehose IcebergDestinationConfiguration, stream Kinesis to Iceberg, near real-time CDC to data lake, continuous append to Iceberg. Do NOT use for: batch file imports (use ingesting-into-data-lake), creating the destination Iceberg table itself (use creating-data-lake-table), the one-time Lake Formation onboarding (use setting-up-lake-formation), finding tables by fuzzy name (use finding-data-lake-assets), running queries (use querying-data-lake), Glue connections (Firehose does not use them; do not invoke connecting-to-data-source), Kinesis to Lambda to Redshift Data API direct writes (not Iceberg; recommend a different workflow), or producer-side Kafka or MSK setup.
jaingxyz/aws-data-skills
Stars: 0Claude CodeCodexAuditoria de acessibilidade baseada em WCAG 2.2 AA para React/Next.js.
MaarkssDN/Birthub-360
Stars: 0Claude CodeCodexOrquestra o sistema de design do Birth Hub 360° e coordena frontend, UX, motion, acessibilidade e QA visual.
MaarkssDN/Birthub-360
Stars: 0Claude CodeCodexDireção visual, composição, hierarquia e identidade de frontend do Birth Hub 360°.
MaarkssDN/Birthub-360
Stars: 0Claude CodeCodexMotion, microinterações, easing, duração, feedback e reduced motion.
MaarkssDN/Birthub-360
Stars: 0Claude CodeCodexGovernança de componentes React, Tailwind e shadcn/ui para o design system do Birth Hub 360°.
MaarkssDN/Birthub-360
Stars: 0Claude CodeCodexDireção estética anti-template para evitar interfaces genéricas de IA sem romper a identidade do Birth Hub.
MaarkssDN/Birthub-360
Stars: 0Claude CodeCodexInteligência de UI/UX para dashboards, formulários, tabelas, navegação, responsividade e acessibilidade.
MaarkssDN/Birthub-360
Stars: 0Claude CodeCodexValidação visual, screenshots, regressão, estados e consistência entre desktop/mobile/light/dark.
MaarkssDN/Birthub-360
Stars: 0Claude CodeCodexQuality gate para alinhamento, responsividade, foco, estados, formulários e comportamento web.
MaarkssDN/Birthub-360
Stars: 0Claude CodeCodexHand the current conversation off to a fresh background agent that picks up the work immediately.
MaarkssDN/Birthub-360
Stars: 0Claude CodeCodexCompact the current conversation into a handoff document for another agent to pick up.
MaarkssDN/Birthub-360
Stars: 0Claude CodeCodexImplement a piece of work based on a spec or set of tickets.
MaarkssDN/Birthub-360
Stars: 0Claude CodeCodexInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
MaarkssDN/Birthub-360
Stars: 0Claude CodeCodexActivate for any work in the tests/e2e/ directory: creating or editing test files (tests/*.test.ts), page objects (pages/), helpers (helpers/), or vitest config. Enforces agent-browser conventions specific to this project.
madarasz/always-be-running
Stars: 24Claude CodeCodexActivate for any work in the tests/e2e/ directory: creating or editing test files (tests/*.test.ts), page objects (pages/), helpers (helpers/), or vitest config. Enforces agent-browser conventions specific to this project.
madarasz/always-be-running
Stars: 24Claude CodeCodex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。
Ascend/msagent
Stars: 0Claude CodeCodex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。
Ascend/msagent
Stars: 0Claude CodeCodex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。
Ascend/msagent
Stars: 0Claude CodeCodexRL 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。
Ascend/msagent
Stars: 0Claude CodeCodex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)。
Ascend/msagent
Stars: 0Claude CodeCodex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。
Ascend/msagent
Stars: 0Claude CodeCodex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。
Ascend/msagent
Stars: 0Claude CodeCodex