AI & ML

grzmol Bundle

Standing technical-debt audit of a Salesforce project and org - inventory the metadata surface, measure API version drift, test and coverage debt, trigger and automation sprawl, retired Workflow Rules and Process Builder still running, hardcoded ids and endpoints, profile-based permissions, dead fields and classes, Apex volume against the 6 MB org limit, and package and dependency debt; then rank findings by impact and effort into a debt register with an owner and a remediation skill per item. Use when taking over an unfamiliar org, planning a refactor or a release-hardening sprint, answering "why is every change here slow", or producing a debt report for an architecture review. Not for reviewing a diff - that is skill sf-code-analyzer-quality and the sf-quality-gate agent.

9s-l-s9 Bundle

Use this skill when reviewing a plan/tasks markdown file for dangling dependencies, duplicate task ids, or leftover template placeholders before handing the plan to an agent.

breroz Skill

Use this skill when a user wants to generate landing page copy, pricing strategy, or a full conversion narrative for a SaaS product or web tool. Triggers include: "write my landing page", "create pricing tiers", "copy for my product", "conversion copy", "pricing strategy", "value metric", "free vs pro tiers", "CTA copy", "SaaS pricing", "landing page structure", "strategic copy guide", or any request to turn a product idea into high-converting copy and a revenue model. Always use this skill when the user uploads a Market Validation Document, Implementation Guide, Brand Style Guide, or Brand Names doc and wants to generate copy or pricing from them. Also triggers when someone asks how to position, price, or write about their product for a launch.

stas2-git Bundle

Use when planning, scoping, validating, or preparing a Kaggle Agent capstone submission, including choosing a track, mapping requirements to deliverables, designing local evaluation, checking rules, or preparing the writeup/demo.

stas2-git Bundle

Use when building or adapting an ADK ambient/event-driven agent with scheduled work, Pub/Sub or event ingestion, normalized inputs, deterministic routing, LLM judgment, human review, state, traces, and evaluations.

stas2-git Bundle

Use when designing, evaluating, packaging, or refactoring portable agent skills, especially deciding skill scope, trigger descriptions, progressive disclosure, references/scripts/assets, and skill evaluation cases.

stas2-git Bundle

Agent Self Audit

stas2-git Bundle

Use when securing an ADK or tool-using agent with validation, authorization, guardrails, command hooks, secret scanning, STRIDE threat modeling, human gates, tests, and behavioral evaluation.

stas2-git Bundle

Use when evaluating, improving, red-teaming, or promoting a skill through read-only, draft-only, or action-allowed tiers using trigger tests, execution tests, token budget checks, regression checks, and human review.

stas2-git Bundle

Use when reviewing human- or AI-generated code changes, pull requests, diffs, or patches for correctness, regression risk, missing tests, security issues, oversized scope, spec mismatch, and production readiness.

samber Bundle

Design a SaaS product's MCP server as a product surface AI agents operate - sizing the build investment, curating a 5-15 workflow-tool agent surface instead of mirroring API endpoints, named write-tool safety patterns (scoped credentials, read-only lockdown, human-in-the-loop approval, risk-tiered server-side gates, dry-run preflight, idempotency and spend caps), remote hosting with OAuth 2.1, versioning the tool surface, MCP registry discoverability, and measuring agent adoption. Use whenever the user mentions MCP, Model Context Protocol, an agent-facing tool surface, exposing a product to AI agents or coding assistants, or MCP write-tool safety - even if they never say "MCP server". Design layer only - code-generation MCP builder skills scaffold what this specifies.

samber Bundle

Design the rate-limit policy a public API publishes to its consumers - the metering model per paradigm (REST request counting vs GraphQL cost points), tier and quota-vs-burst numbers, multi-tenant fairness, rate-limit headers (legacy X-RateLimit-* vs IETF RateLimit fields), 429 and Retry-After behavior, enterprise and partner overrides, and change-notice rules. Use whenever the user mentions rate limits, quotas, throttling tiers, 429 responses, noisy neighbors, or limit-increase requests - even if they never say "rate-limit policy". Policy layer only, not gateway configuration. Do NOT use for the 429 error envelope - use samber/developer-platform-skills@api-error-design instead.

samber Bundle

Design a public gRPC surface for external developers - the when-gRPC-at-all gate (most platforms keep gRPC internal and publish REST or transcoded JSON), AIP proto package and versioning conventions, buf breaking-change gates and their google.api.http blind spot, unary-by-default streaming decisions, the google.rpc.Status error model with its HTTP-mapping traps, transcoding and gateway architecture (Connect-RPC, grpc-gateway, Envoy), and external auth and TLS. Use whenever the user mentions gRPC, protobuf or .proto files, buf, Connect-RPC, grpc-gateway, or gRPC-JSON transcoding at a public edge - even if they never say "gRPC API design". Design layer only, not language-specific server implementation.

samber Bundle

Decide a public API's language-SDK portfolio - which languages get official SDKs and in what order, generated vs handwritten build model, official and community support tiers with a promotion gate, SDK deprecation and end-of-life, and decoupling SDK SemVer from API versioning and release cadence. Use whenever the user mentions client libraries, SDKs, which languages to support first, an SDK generator (Stainless, Fern, OpenAPI Generator), community SDKs, or sunsetting an SDK - even if they never say "SDK portfolio". Portfolio strategy only, not single-SDK ergonomics or registry publishing. Do NOT use for whether to offer SDKs as a surface at all - use samber/developer-platform-skills@api-integration-surface-strategy instead.

samber Bundle

Designs the pricing and packaging architecture of a developer tool - the value metric (seats, consumption, capacity, outcome, or a hybrid), free-tier limits, the tier ladder up to enterprise gating, price points bounded by a margin floor and the self-host and build-it ceilings, and a plan to change prices without a backlash. Use whenever someone asks what to charge for a developer tool, how to package tiers, where free ends and paid begins, whether to bill per seat or per usage, how to price against their own open-source edition, or how to raise prices safely - even if they only say the pricing page feels wrong. Not which business model to run - use samber/developer-relations-skills@devtools-business-model. Not pricing-page copy.

erbatista Bundle

Repository conventions, build/test commands, and framework pitfalls for Blazor codebases - .NET solutions with .razor components, Razor class libraries, Blazor Server or WebAssembly, and interactive render modes. Load whenever working in a Blazor project, and whenever feature-development or bug-fixing routes here in their stack-detection step. Not for WPF or non-.NET projects.

erbatista Bundle

Diagnose and fix existing defects in any codebase by reproducing the problem, establishing root cause with evidence, adding regression coverage when practical, and applying the smallest safe correction. Use for crashes, exceptions, incorrect results, regressions, intermittent failures, state and concurrency bugs, UI that does not update, and production incidents, even when the user only says "this doesn't work". Language-agnostic; detects the stack and loads the matching stack skill (dotnet-wpf, blazor) for framework-specific investigation and validation. Do not use as the primary workflow for net-new feature development; use feature-development for that.

erbatista Bundle

Repository conventions, build/test commands, and framework pitfalls for C#/.NET/WPF codebases - solutions with .sln/.csproj and UseWPF, XAML views, ViewModels, MVVM, commands, bindings, and dispatcher/UI-thread work. Load whenever working in a .NET/WPF repository, and whenever feature-development or bug-fixing routes here in their stack-detection step. Not for Blazor, ASP.NET, or non-.NET projects.

erbatista Bundle

Implement new features, user stories, enhancements, commands, views, services, endpoints, and workflow extensions in any codebase, using the repository's existing architecture, patterns, tests, and build conventions. Use whenever the task is to add, build, implement, extend, or support new behavior, even when the word "feature" is not used. Language-agnostic; detects the stack and loads the matching stack skill (dotnet-wpf, blazor) for conventions and validation commands. Do not use when the primary task is diagnosing existing incorrect behavior; use bug-fixing for that.

baymaxstudio Bundle

两人 AA 记账与结算。上传一批支付凭证截图（微信支付/支付宝/银行卡/香港电子钱包），逐张识别事项、日期、币种、金额，写入一份飞书多维表格（含原图附件），表格用公式自解算出谁该转给谁多少人民币。两个人各用各的飞书、各跑各的 agent，往同一个账本里记。触发词：A钱、AA 记账、ausgleich、平账、分账、对账、室友记账、分账表。不用于：三人及以上多人分账、自定义分摊比例、企业报销/审批、单人预算管理；当前仅支持 CNY/HKD 两种原币与固定 50/50 结算，香港以外的多币种混算不要触发本技能。

alanpai Bundle

暢流（ChangLiu / changliu.com.tw）WMS 系統 API 串接知識與工具。涵蓋 JWT 認證、訂單查詢、 庫存與儲位查詢、入庫單查詢、收件人個資 AES-128-ECB 解密，以及兩個最容易卡住的眉角 （必帶瀏覽器 User-Agent 避開 Cloudflare 1010、來源 IP 白名單）。 只要任務牽涉到暢流 WMS、changliu.com.tw 的 API、`*.wms.changliu.com.tw` 網域、 order_query/stock_query/inbound 等端點、用 API 抓電商訂單（蝦皮/momo/PChome 等經暢流出貨）、 或解密暢流回傳的收件人姓名電話，就務必使用本 skill，即使使用者沒有明講「暢流」或「WMS」。

samber Bundle

Builds a company's open-source sponsorship portfolio - which projects and maintainers to fund, through which allocation model, at what amount each, and how to prove it worked. Use whenever a company, OSPO, DevRel lead or engineering leader asks which open-source projects to sponsor, how much to budget for open-source funding, whether sponsoring maintainers is worth it, how to run an employee-nominated FOSS fund, how to fund dependencies at scale, how to pick a sponsorship tier on a maintainer's ladder, or how to measure the return on money paid to maintainers - even if they only say they want to give back. Not the maintainer side of raising sponsorship - use samber/developer-relations-skills@oss-sponsors-fundraising. Not event sponsorship.

headlinearena Skill

Use when an agent needs to obtain an access token, refresh an expired token, or authenticate with HeadlineArena. Trigger on phrases like "get token", "authenticate", "access token expired", "401 unauthorized", "token", or before calling any authenticated endpoint.

headlinearena Skill

Use when an agent wants to read activity from followed agents, discover what other agents are discussing, or interpret the social context embedded in event data. Trigger on phrases like "check feed", "what are agents saying", "follow feed", "social context", "who am I following", or "agents I follow".

headlinearena Skill

Use when an agent needs to check whether it has been claimed by its human operator, view current token/credential validity, see subscribed prediction scopes, or re-issue a lost claim link / pairing code. Trigger on phrases like "check my status", "am I claimed", "check claim status", "is my token still valid", "pairing code", "claim link expired", or "resend claim link".

headlinearena Skill

Use when an agent wants to check whether a newer version of the HeadlineArena plugin is available, or needs the exact command to reinstall/upgrade it. Trigger on phrases like "check for plugin update", "is there a new version", "update HeadlineArena plugin", "am I on the latest version", or when a stale-version warning has appeared.

headlinearena Skill

Use when an agent needs to check its own credit balance or transaction history, check its human owner's account balance, fund its own wallet from the owner's balance, or view/set its own wallet spending limits on HeadlineArena. Trigger on phrases like "check my credit balance", "credit history", "check owner balance", "top up my wallet", "fund my agent", "wallet policy", "spending limit", or before staking credits on a macro prediction.

headlinearena Skill

Use when an agent wants to post a comment on a market event, reply to another agent's comment, like a comment, or view existing comments on HeadlineArena. Trigger on phrases like "comment", "reply", "post analysis", "respond to agent", "like comment", or "view discussion".

headlinearena Skill

Use when an agent wants to discover open prediction challenges, submit a market prediction, or check challenge results on HeadlineArena. Trigger on phrases like "submit prediction", "predict", "AI Arena", "challenge", "bullish/bearish prediction", "market forecast", "BTC arena", "prediction leaderboard", "world cup prediction", "WC2026", "macro data", "CPI/PPI/PMI forecast", "economic indicator prediction", "Loan Prime Rate", "LPR forecast", "initial jobless claims", "binary probability forecast", "Civic Index", "Human Forecast", or when specific asset/event symbols are provided (e.g. "ha-predict CL ES", "predict gold and WC2026", "predict soccer matches", "predict CPI").

headlinearena Skill

Use when an agent needs to register with HeadlineArena for the first time, complete the market analysis challenge, and obtain a client_secret. Trigger on phrases like "register", "sign up", "join HeadlineArena", "get client_secret", "onboard to HeadlineArena", or when the user asks the agent to join the platform.

headlinearena Skill

Use when an agent wants to check the prediction leaderboard, understand their ranking, view scorecard details, or learn how scoring works on HeadlineArena. Trigger on phrases like "leaderboard", "rankings", "my rank", "scorecard", "scoring rules", "how am I doing", or "prediction accuracy".

samber Bundle

Design how a B2B SaaS app/connector marketplace makes money, operator side - merchant-of-record posture (marketplace-billed vs developer-billed), billing rails and account configuration, the fee stack (revenue share collected at source, program fees, processing pass-through), fee waivers and incentive tiers, payout cadence and hold windows, and the marketplace-facilitator/VAT tax layer. Use whenever the user mentions charging for apps, rev-share collection, paid-app billing or billing APIs, developer payouts, fee waivers, or merchant of record - even if they never say "marketplace monetization". Mechanics layer only. Do NOT use for take-rate level and tiers - use samber/developer-platform-skills@connector-marketplace-strategy instead.

samber Bundle

Decides whether, when and how far a developer product should open into a platform other companies build on - extension points, partner-built integrations, third-party apps, a complement ecosystem - and what that permanently obliges you to. Use whenever someone asks if the product should become a platform, whether to open extension points or an app model to third parties, how to start an integration ecosystem, why nobody builds on the API, whether partners should build the connectors, or how much value complementors must keep - even if they only say "we want an integrations story". Not marketplace operations or API design. Do NOT use for the revenue model - use samber/developer-relations-skills@devtools-business-model.

samber Bundle

Decides whether and how to invest in structured developer education, such as learning paths, a developer academy, hands-on labs, badges or a full certification program - instead of more ad-hoc content, then designs its operating model, staffing, refresh cadence, measurement and kill rules. Use whenever someone mentions a developer academy, certification, a developer curriculum, training for developers, learning paths, skill badges or credentials, "should we certify our users", partner or SI enablement training, or scaling developer onboarding beyond docs - even if they only say "we need more training content". Covers B2B, partner and bottom-up motions. Never writes the courses themselves. Use samber/developer-relations-skills@developer-tutorial for a lesson.

samber Bundle

Makes SDK, API or protocol documentation something a coding agent can integrate from unattended - crawler access, machine-readable entry points (llms.txt, markdown endpoints, OpenAPI and JSON Schema files), self-contained copy-paste-safe pages, and a measured first-attempt agent success rate. Use whenever the user mentions agent-readable or AI-ready docs, agent experience or AX, llms.txt or llms-full.txt, docs for coding agents, agents inventing API calls that do not exist, or asks whether an agent could wire up their SDK from the docs alone - even if they never say "agent". Not for AI-search citation, nor a repo's own contributor-facing agent instructions. For human docs architecture use samber/developer-relations-skills@developer-docs-structure-audit.

zchary1106 Skill

Collect and curate public AI Agent, LLM, RAG, MCP, and AI application interview experiences for agent-interview-hub.