All authors
Claude Skills by Amey-Thakur
github.com/Amey-Thakur1,001 skills16 installs1,473 views
- Ml BaselinesEstablish heuristic and simple-model baselines that bound what complexity is worth. Use when starting any ML project or auditing whether a complex model earns its cost.Votes: 0GitHub stars: 7
- Ml Error AnalysisReview model errors by hand, discover failing slices, and decide whether data or model fixes pay more. Use when a model underperforms and you need to know why before spending compute.Votes: 0GitHub stars: 7
- Ml Problem FramingFrame ML problems around a decision, a measurable target, and honest error costs before touching models. Use when scoping an ML project or reviewing whether one should exist.Votes: 0GitHub stars: 7
- Model DeploymentShip models through batch, online, or edge patterns with shadow testing, gated rollouts, and rollback. Use when moving a model to production or designing the serving architecture.Votes: 0GitHub stars: 7
- Model EvaluationEvaluate models with cost-aligned metrics, slice analysis, calibration, and uncertainty, not a single accuracy number. Use when choosing evaluation metrics or judging whether a model is fit to ship.Votes: 0GitHub stars: 7
- Train Test DisciplineSplit data before looking at it, respect time and groups, and quarantine the test set so scores mean something. Use when setting up ML evaluation or auditing why offline metrics did not survive production.Votes: 0GitHub stars: 7
- Community Led GrowthGrow through a community that supports and advocates for itself, with genuine investment rather than extraction. Use when the product benefits from peer knowledge and users want to talk to each other.Votes: 0GitHub stars: 7
- Competitive MessagingTalk about competitors accurately and fairly in a way that helps buyers decide, without claims you cannot support. Use when buyers ask how you compare or a competitor is winning deals.Votes: 0GitHub stars: 7
- Content Marketing StrategyPlan content that reaches buyers at the moment they are looking, with a cadence you can sustain and a way to tell whether it worked. Use when publishing sporadically without knowing whether it helps.Votes: 0GitHub stars: 7
- Conversion Rate OptimizationImprove the proportion of visitors who take the desired action, through evidence about where they drop rather than opinions about design. Use when traffic is adequate and conversion is not.Votes: 0GitHub stars: 7
- Customer PersonasBuild audience profiles from evidence rather than imagination, capturing the job, the trigger, and the objection. Use when marketing targets everyone and converts nobody.Votes: 0GitHub stars: 7
- Email MarketingRun lifecycle and campaign email that people open, with segmentation, timing, and permission handled properly. Use when email is a channel you own and want to keep.Votes: 0GitHub stars: 7
- Launch MarketingCoordinate a launch so attention arrives when the product is ready and converts rather than dissipating. Use when releasing something significant enough to warrant a moment.Votes: 0GitHub stars: 7
- Marketing AttributionAssign credit for conversions across touchpoints honestly, knowing what each model hides. Use when deciding where to spend and channels each claim the same conversions.Votes: 0GitHub stars: 7
- Paid AcquisitionBuy traffic profitably by measuring against payback and lifetime value rather than cost per click. Use when considering paid channels or when spend is rising without profit.Votes: 0GitHub stars: 7
- Positioning And MessagingDecide what you are, who for, and against what alternative, then say it in words customers use. Use when nobody can explain the product in one sentence or the same product is described differently everywhere.Votes: 0GitHub stars: 7
- Retention MarketingKeep and re-engage existing customers, which is usually cheaper and more valuable than acquiring new ones. Use when churn is high or growth is entirely dependent on new acquisition.Votes: 0GitHub stars: 7
- Social Media StrategyChoose platforms and a cadence you can sustain, with content native to each rather than cross-posted. Use when social presence is scattered and producing nothing.Votes: 0GitHub stars: 7
- Mcp AuthenticationAuthenticate and authorise access to a remote MCP server so tools act as the right user with the least necessary privilege. Use when hosting an MCP server that more than one person or agent reaches.Votes: 0GitHub stars: 7
- Mcp Client IntegrationConnect MCP servers into an application with lifecycle management, capability negotiation, and graceful degradation when a server is unavailable. Use when building a client or embedding MCP into a product.Votes: 0GitHub stars: 7
- Mcp Context BudgetingKeep tool results small enough that an agent can hold what matters, through pagination, projection, and summarisation at the server. Use when tool output floods the context window.Votes: 0GitHub stars: 7
- Mcp Error HandlingReturn errors an agent can act on, distinguishing retryable failures from permanent ones and never leaking internals. Use when building MCP tools that will fail in production.Votes: 0GitHub stars: 7
- Mcp Multi Server OrchestrationRun an agent across several MCP servers without name collisions, tool overload, or ambiguity about which server owns an action. Use when one agent connects to more than a few servers.Votes: 0GitHub stars: 7
- Mcp Prompt TemplatesShip reusable prompt templates from an MCP server so users invoke tested workflows rather than improvising. Use when a server supports a workflow that benefits from a known-good prompt.Votes: 0GitHub stars: 7
- Mcp Resource DesignExpose data through MCP resources with stable URIs, useful listings, and sizes that fit a context window. Use when an agent needs to read data rather than perform an action.Votes: 0GitHub stars: 7
- Mcp Sampling And ElicitationUse server-initiated model calls and user prompts responsibly, so a server can ask for reasoning or input without seizing control. Use when a server needs the model's help or a decision from the user mid-operation.Votes: 0GitHub stars: 7
- Mcp Security BoundariesTreat tool output as untrusted data, confirm destructive actions, and keep an agent's reach inside what its user may do. Use when an MCP server touches real systems or reads content from outside your control.Votes: 0GitHub stars: 7
- Mcp Server TestingTest an MCP server for protocol conformance, tool selection accuracy, and behaviour under real model calls rather than only unit tests. Use before shipping a server others will connect agents to.Votes: 0GitHub stars: 7
- Mcp Tool DesignDesign MCP tools an agent can select correctly, with names, descriptions, and schemas that make the right call obvious and the wrong one impossible. Use when exposing capability to an agent through an MCP server.Votes: 0GitHub stars: 7
- Mcp Transport SelectionChoose between local stdio and remote HTTP transports for an MCP server based on trust, deployment, and who runs it. Use when deciding how a server will be hosted and reached.Votes: 0GitHub stars: 7
- Audio ProcessingNormalise, compress, and prepare audio for reliable playback and transcription, handling levels and formats consistently. Use when accepting recorded audio or producing spoken content.Votes: 0GitHub stars: 7
- Document ParsingExtract text and structure from PDFs, office documents, and scans reliably enough to search, index, or summarise. Use when users upload documents whose contents the product must understand.Votes: 0GitHub stars: 7
- Format SelectionChoose media formats and codecs by compatibility, quality, and licensing, with fallbacks for what the client cannot play. Use when deciding what to store and deliver.Votes: 0GitHub stars: 7
- Media DeliveryServe media efficiently with caching, range requests, and access control, so playback starts fast and private files stay private. Use when media is slow to load or must be restricted to authorised users.Votes: 0GitHub stars: 7
- Media Processing QueueRun transcoding, thumbnailing, and extraction as queued background work with progress, retries, and failure visibility. Use when media processing takes long enough that it cannot happen in the request.Votes: 0GitHub stars: 7
- Media Storage TieringMatch storage class to access pattern so rarely read media costs less without becoming unavailable. Use when media storage cost grows faster than usage.Votes: 0GitHub stars: 7
- Metadata StrippingRemove embedded metadata such as location, device, and author from user files before they are stored or shared. Use when users upload photographs or documents that others will see.Votes: 0GitHub stars: 7
- Resumable UploadsLet large uploads survive network interruption by chunking and resuming from the last confirmed part. Use when files are large enough that a failed upload is a real cost to the user.Votes: 0GitHub stars: 7
- Thumbnail GenerationProduce preview images for files of every type, consistently sized and generated without blocking the user. Use when a file list or gallery needs visual previews.Votes: 0GitHub stars: 7
- Upload Pipeline DesignMove a file from the user's device to durable storage and a processed state, with validation, progress, and recovery at every stage. Use when building any feature that accepts files.Votes: 0GitHub stars: 7
- Video TranscodingConvert uploaded video into the renditions needed for reliable playback across devices and bandwidths. Use when accepting user video or delivering video that must play everywhere.Votes: 0GitHub stars: 7
- App Store ReadinessPass App Store and Play review on the first attempt and recover fast from rejections. Use when preparing a mobile submission, writing store metadata, or responding to a review rejection.Votes: 0GitHub stars: 7
- Deep LinkingSet up universal and app links that open the right in-app screen from a URL, with deferred links surviving install and a routing layer that validates every parameter. Use when adding shareable links, wiring campaign or email links into the app, or debugging links that open the browser instead.Votes: 0GitHub stars: 7
- Mobile Input UxMake mobile forms and controls fast to use with correct keyboards, reachable touch targets, and restrained haptics. Use when building input-heavy mobile screens or fixing form abandonment on small screens.Votes: 0GitHub stars: 7
- Mobile NavigationStructure mobile navigation with a clear stack, tab, and modal hierarchy and a back stack that survives deep links and process death. Use when designing app navigation, adding a deep-link target, or fixing lost-state and wrong-back-button bugs.Votes: 0GitHub stars: 7
- Mobile ObservabilityInstrument mobile apps for crash-free rate, ANR and hang detection, and release health you can gate rollouts on. Use when setting up mobile monitoring or deciding whether a release is healthy enough to expand.Votes: 0GitHub stars: 7
- Mobile PerformanceMake a mobile app fast where users feel it by protecting startup time, keeping lists at frame rate, handling images at display size, and keeping work off the main thread. Use when the app is slow to open, scrolling janks, or the UI freezes during work.Votes: 0GitHub stars: 7
- Mobile Release StrategyShip mobile releases through phased rollouts with hotfix paths and a forced-upgrade policy that never strands users. Use when planning app releases, a rollout gate, or recovery from a bad build in the stores.Votes: 0GitHub stars: 7
- Offline First MobileBuild a mobile app where the local database is the source of truth, the UI reads and writes it directly, and a background sync engine reconciles with the server. Use when the app must work on flaky or no connectivity, or when network-coupled screens feel slow and fragile.Votes: 0GitHub stars: 7
- Push NotificationsDeliver mobile push that users keep enabled by asking permission at the right moment, managing token lifecycle, using categories and silent pushes correctly, and respecting quiet hours. Use when adding push, debugging non-delivery, or opt-in rates are low.Votes: 0GitHub stars: 7