Product & Planning

paulasilvatech Skill

Generate production-ready Product Requirements Documents for software systems and AI-powered features. Use when starting a product or feature cycle, translating a vague idea into requirements, defining AI system requirements, planning a feature, or creating a stakeholder source of truth.

paulasilvatech Bundle

Work with Aspire distributed applications, AppHost orchestration, CLI commands, service discovery, integrations, MCP docs, dashboard, testing, and deployment. Use this skill when the user asks to create, run, debug, configure, deploy, or troubleshoot an Aspire polyglot app.

paulasilvatech Bundle

Azure CLI operations run az commands for cloud resource discovery, subscription context, identity, AKS, ACR, Key Vault, RBAC, managed identity, and federated credential workflows. Use this skill when working with az login, az account, az aks, az acr, az keyvault, resource group checks, or Azure day-2 operations.

adu2021 Skill

Replace expensive test-based execution loops with learned prediction models that forecast agent action outcomes before commitment. Framework uses internalized execution priors and structured analysis reports to achieve 6x faster convergence and 6% higher performance compared to execute-first baselines. Applicable to scientific discovery, optimization, and hypothesis testing where verification is computationally or financially expensive.

adu2021 Skill

Route queries across frontier models using two-stage system: graph-based task discovery identifies ~332 latent task types via semantic similarity + preference patterns; MoE with task-specific adapters estimates quality for candidate models. Achieves <50% inference cost of strongest single model while exceeding its performance; applies when managing pools of frontier models with narrow capability gaps.

undermybelt Skill

Discover and evaluate Laravel packages via LaraPlugins.io MCP. Use when the user wants to find plugins, check package health, or assess Laravel/PHP compatibility.

undermybelt Bundle

Triage a batch of raw security findings. Verify each is real, collapse duplicates, re-rank by derived exploitability, and tag with an owner. Takes a directory or file of scanner output and writes TRIAGE.json + TRIAGE.md sorted by what actually needs engineering attention. Use when asked to "triage findings", "validate scanner output", "prioritize vulns", or "review the backlog". Runs interactively by default; pass --auto to skip the interview.

undermybelt Skill

Anthropic Defending Code Reference Harness safety wrapper. Use for questions or operating plans around the vuln-pipeline autonomous vulnerability-discovery harness, sandbox setup, C/C++ ASAN targets, recon/find/grade/report/patch flow, or adapting the reference harness. Reference-only until the user explicitly asks to bring up the Python/Docker runtime.

undermybelt Bundle

This skill covers performing vulnerability assessments in OT environments using the Claroty xDome platform for comprehensive asset discovery, risk scoring, vulnerability correlation, and remediation prioritization. It addresses passive vulnerability identification through traffic analysis, active safe querying of OT devices, integration with CVE databases and ICS-CERT advisories, and risk-based prioritization that accounts for operational impact and compensating controls.

undermybelt Bundle

Perform comprehensive ICS/OT asset discovery using Claroty xDome platform, leveraging passive monitoring, Claroty Edge active queries, and integration ecosystem to gain full visibility into industrial control system assets including PLCs, RTUs, HMIs, and network infrastructure across Purdue Model levels.

adu2021 Skill

Balance LLM flexibility with domain rigor in scientific agents through dual-layer architecture. Enforce role-based access control and artifact-centric state management to prevent hallucinations, while preserving free-form reasoning for lower-risk tasks.

adu2021 Skill

Train reasoning models to discover diverse solution strategies through two-player RL that jointly optimizes abstraction generation and solution derivation. Use when exploring multiple reasoning approaches is preferable to single-strategy depth.

nota-america Skill

QA an analysis before sharing -- methodology, accuracy, and bias checks. Use when reviewing an analysis before a stakeholder presentation, spot-checking calculations and aggregation logic, verifying a SQL query's results look right, or assessing whether conclusions are actually supported by the data.

nota-america Skill

Process call notes or a transcript — extract action items, draft follow-up email, generate internal summary. Use when pasting rough notes or a transcript after a discovery, demo, or negotiation call, drafting a customer follow-up, logging the activity for your CRM, or capturing objections and next steps for your team.

nota-america Skill

Generate a status report with KPIs, risks, and action items. Use when writing a weekly or monthly update for leadership, summarizing project health with green/yellow/red status, surfacing risks and decisions that need stakeholder attention, or turning a pile of project tracker activity into a readable narrative.

nota-america Skill

Create a change management request with impact analysis and rollback plan. Use when proposing a system or process change that needs approval, preparing a change record for CAB review, documenting risk and rollback steps before a deployment, or planning stakeholder communications for a rollout.

nota-america Skill

Identify, categorize, and prioritize technical debt. Trigger with "tech debt", "technical debt audit", "what should we refactor", "code health", or when the user asks about code quality, refactoring priorities, or maintenance backlog.

nota-america Skill

Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request into a structured document, scoping a feature with goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into a phased spec.

findscripter Skill

当需要把报错日志、截图、语音口述、零散吐槽等非结构化 bug 输入整理成开发者可直接处理的 GitHub Issue 时使用；做的事是抽取结构化信息并产出含复现步骤、预期/实际、影响等级、证据引用的标准 Issue Markdown；不适用于代码评审、需求/PRD 撰写或环境实测验证；触发词：github issue、提 issue、写 issue、bug 报告、缺陷单、复现步骤、issue 编写、报错整理

findscripter Skill

当需要系统盘点技术债、决定"先重构什么"、评估代码健康度或排维护 backlog 时使用；做按六类（代码/架构/测试/依赖/文档/基础设施）盘点技术债并用 影响×风险×工作量 打分，产出带优先级、工作量估算、业务理由的清单和可与功能开发并行的分阶段偿还计划；不适用于具体某段代码的逐行 bug 审查、单条重构的实现、或全新功能设计；触发词：技术债、tech debt、重构什么、该重构哪里、代码健康度、维护 backlog、技术债审计

findscripter Skill

当需要规划内容选题、主题集群与编辑路线图（以获取自然流量、建立权威、获取线索）时使用；做：盘点业务/客户/竞品上下文，识别 3-5 个内容支柱与集群，按买家旅程做关键词分级，按四维权重打分排优先级，产出支柱方案+优先选题清单+集群地图；不适用于单篇文案写作或纯技术 SEO 审计；触发词：内容策略、content strategy、主题集群、topic cluster、内容支柱、content pillar、编辑路线图、editorial roadmap、选题规划、内容矩阵

adu2021 Skill

Implement techniques from DSGym: A Holistic Framework for Evaluating and Training Data Science Agents. Data science agents promise to accelerate discovery and insight-generation by turning data into executable analyses and findings

nota-america Skill

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

nota-america Skill

Generate a professional PDF report from a GEO audit using pandoc + Chrome headless. Converts GEO-AUDIT-REPORT.md into a styled, client-ready PDF with a cover page, color-coded score tables, severity-tagged findings, and a 90-day roadmap.

findscripter Skill

当需要做特性优先级排序、用户访谈综合或撰写 PRD 时使用；用 RICE 打分脚本与访谈分析脚本产出优先级清单/季度路线图/洞察报告，并套用 PRD 模板与发现框架；不适用于纯工程实现、UI 视觉设计或营销投放执行。触发词：RICE、优先级、PRD、用户访谈、路线图

findscripter Skill

当为领导/干系人撰写周报、月报或季度更新，需把项目活动汇成红黄绿健康度叙事并暴露风险与待决策时使用；产出含执行摘要、KPI 指标表、进展/风险/待决策表与下期优先级的精炼状态报告；不适用于排程、纯纪要摘要或深度风险矩阵分析。触发词：状态报告、项目周报、月报、领导汇报、健康度、红黄绿、风险与待决策、status report、KPI、stakeholder update

findscripter Skill

当 PM/业务在 Slack 抛来「这算问题吗/能不能做 X/要走法务评审吗/帮我把把关」类即时小问题、需一分钟内给出可以或需看或打住的判定时使用；做按风险校准表模式匹配并检查常见陷阱、产出三态结论加一句理由及下一步；不适用于多议题/新领域的复杂分析、PRD 评审或自己拿不准的情形（应转评审或如实说不确定）。触发词：这算问题吗、能不能做、要走法务评审吗、帮我把把关

findscripter Skill

当搭建公司运营机制、选型管理框架、设计会议节奏、建立权责体系或落地 OKR 时使用；产出含责权图、记分卡、会议节奏、IDS 议题解决、90 天 Rocks 的运营系统设计与 30 天落地清单；不适用于具体业务执行或单个职能的深度方案。触发词：EOS、Scaling Up、OKR、L10 会议、Rocks、记分卡、责权图、IDS、季度规划。

findscripter Skill

当需要对一次产品/功能上线（PRD、上线工单、Drive 文档）做逐类目法律审查、判定能否发布时使用；做按团队审查框架走查（合同/隐私/安全/IP/第三方/监管/营销/AI 治理）+ 行业叠加 + 风险校准，产出「特权审查备忘录 + 可贴工单的脱敏结论」双输出；不适用于替代律师批准发布、撰写营销创意、出具正式法律意见。触发词：审查这次上线、上线法律审查、这个能发吗、功能法律风险、PRD 法务过一遍、launch review、can we ship this

findscripter Skill

当你要在投入交付资源前验证产品机会、识别假设并测试问题-方案匹配时使用；用机会方案树(OST)+假设映射+问题/方案验证产出可决策的探索冲刺结论（继续/转向/停止）；不适用于已决定要做、只需排期或写需求文档的场景，那用 RICE 优先级或 PRD 技能。触发词：产品探索、机会验证、假设映射、问题验证、探索冲刺

findscripter Skill

当需按受众与节奏撰写干系人更新（高管周报/月报、发布公告、风险升级，或把同一进展改写成高管简报/工程明细/对客版本）时使用；产出含状态灯（绿/黄/红）、TL;DR、进展、风险与诉求的分受众结构化更新草稿；不适用于对外客服回复、营销文案或纯财务建模；触发词：干系人更新、状态汇报、周报、月报、发布公告、风险升级、stakeholder update

findscripter Skill

当需要为团队批量制作、改版、治理 Jira/Confluence 标准化模板（会议纪要、PRD、Bug 报告、Epic 等）并经 Atlassian MCP 发布时使用；做的是设计含宏与占位符的可复用模板/蓝图并验证发布产出标准化页面；不适用于单篇内容写作、非 Atlassian 平台或纯 Markdown 文档。触发词：Atlassian 模板、Confluence 模板、Jira 模板、blueprint 蓝图、storage format、会议纪要模板、PRD 模板、Bug 报告模板

cslawyer1985 Bundle

印度《2023 年数字个人数据保护法》（DPDPA）合规顾问专家。当用户询问 DPDPA、DPDP 法案、DPDP 规则 2025、印度数据隐私法、数据受托人义务、数据主体权利、重要数据受托人、印度数据保护委员会、DPDPA 下的同意、通知要求、印度违规通知、印度儿童数据、印度跨境数据传输、印度隐私合规、DPDPA 差距分析、DPDPA 与 GDPR 对比，或印度个人数据保护框架下的任何义务时，使用本技能。以下情况同样触发："Section 6 consent"、"Section 7 legitimate uses"、"Section 9 children's data"、"Section 10 SDF"、"Section 16 cross-border"、"Rule 6 breach notification"、"Rule 13 SDF obligations"、"Data Protection Board complaint"、"verifiable parental consent India"、"DPDPA compliance roadmap" 或 "India privacy law global company"。

cslawyer1985 Bundle

Use for law firm and legal practice operations — case management, document drafting, client communication, billing, court deadlines, discovery workflows, compliance tracking, and matter lifecycle management.

cslawyer1985 Bundle

Use this skill when a litigation attorney, e-discovery counsel, or paralegal needs to prepare for an FRCP Rule 26(f) meet-and-confer or draft an ESI Protocol for federal civil litigation. Produces a meet-and-confer-ready ESI Protocol, Rule 26(f) discovery-plan section, gap audit, and pre-conference Q&A worksheet.

findscripter Skill

当团队各自为政、OKR 互不衔接、部门局部最优损害公司目标时使用；做战略级联映射与失配诊断（孤儿目标/冲突/覆盖缺口/筒仓）并产出对齐评分与重对齐方案；不适用于个人绩效考核或战略本身的制定。触发词：战略对齐、OKR级联、孤儿OKR、部门筒仓