Amey-Thakur
- 1k skills
- 0 followers
- 2 days ago last updated
- ▌ Ml Engineer Role · amey-thakurOperate as an ML engineer who takes a research model to reliable production behind eval gates and keeps it healthy across its lifecycle. Use when asked to productionize a model, build a training or serving pipeline, or set promotion criteria.
- ▌ QA Engineer Role · amey-thakurOperate as a QA engineer who owns test strategy, automation coverage, and the release quality signal. Use when asked to build a test approach, decide what to automate, or give a defensible go or no-go on a release.
- ▌ User Activation · amey-thakurMove new users to their first value moment fast by defining activation, instrumenting the funnel, and cutting time-to-value. Use when signups do not become engaged users.
- ▌ Boolean Parameters · amey-thakurReplace opaque boolean flags with named enums or split functions so call sites read without the definition open. Use when a signature takes a bare boolean or a function branches on a mode flag.
- ▌ Tech Debt Register · amey-thakurTrack technical debt deliberately by framing each item as interest owed and budgeting steady paydown. Use when debt is piling up as vague complaints and you need to make it fundable work.
- ▌ Support Macros · amey-thakurBuild reusable reply templates that speed common answers without making replies feel automated. Use when agents retype the same explanations daily.
- ▌ Data Retention · amey-thakurImplement retention tiers, legal holds, and deletion pipelines that actually delete, including GDPR-style erasure. Use when defining how long data lives or building the machinery that enforces it.
- ▌ Consent Management · amey-thakurAsk for, record, and honour consent so processing has a lawful basis and withdrawal actually stops it. Use when adding tracking, marketing, or any optional processing of personal data.
- ▌ Data Anonymization · amey-thakurRemove or blunt identifiers so a dataset can be analysed or shared without re-identifying people, and know when it is only pseudonymous. Use when preparing data for analytics, testing, sharing, or research.
- ▌ Data Visualization · amey-thakurChoose and design charts that reveal the truth in data clearly and honestly, matching the chart to the question. Use when visualizing data for exploration or communication, or fixing a misleading or cluttered chart.
- ▌ Sharding Partitioning · amey-thakurScale databases by partitioning and sharding with a good key, handling resharding and cross-shard queries, and knowing when to avoid it. Use when one database can no longer hold or serve the load.
- ▌ Time Travel Debugging · amey-thakurRecord an execution once and replay it deterministically so you can step backward to the moment a value went wrong. Use when a bug is hard to reproduce or the failure surfaces long after its cause, and rerunning changes the outcome.
- ▌ Dashboard Building · amey-thakurBuild dashboards that answer specific questions at a glance, rather than displaying every available metric. Use when a team needs shared visibility into an ongoing situation.
- ▌ Documentation Site · amey-thakurStructure a documentation site so readers find answers by task, with working examples and a maintenance path. Use when documenting a product or library for external users.
- ▌ Print Ready Output · amey-thakurPrepare documents for physical printing with correct colour, bleed, resolution, and fonts, so what prints matches what you designed. Use when producing anything that will be professionally printed.
- ▌ Technical Diagrams · amey-thakurDraw system, sequence, and flow diagrams that clarify rather than decorate, at a consistent level of abstraction. Use when explaining a system to people who did not build it.
- ▌ Changelog Writing · amey-thakurWrite changelogs for humans, grouped by change type, with breaking changes called out and versions dated. Use when maintaining a changelog or replacing raw commit dumps with useful release notes.
- ▌ Technical Writing · amey-thakurWrite documentation, READMEs, and guides that respect the reader's time and answer their actual question. Use when drafting or editing any technical document.
- ▌ Embedded Debugging · amey-thakurDebug firmware with JTAG/SWD workflows, console-free logging, and hard-fault analysis that names the faulting line. Use when a device crashes, hangs, or misbehaves only in the field.
- ▌ React Component Design · amey-thakurDesign React component props and boundaries so components compose cleanly and stay reusable. Use when creating a component, reviewing a bloated props list, or deciding controlled versus uncontrolled.
- ▌ React Hooks Discipline · amey-thakurWrite React hooks with correct dependencies and minimal effects so renders stay predictable. Use when adding useEffect, debugging stale closures or render loops, or extracting a custom hook.
- ▌ Secret Scanning · amey-thakurDetect committed credentials, respond correctly when one is found, and prevent the next one. Use when setting up a repository or after a credential appears in history.
- ▌ LLM Eval Design · amey-thakurBuild LLM evaluations from real failures with calibrated judges and regression gates that catch quality drift. Use when an LLM feature needs quality measurement or prompts change without anyone knowing what broke.
- ▌ Self Reflection · amey-thakurHave an agent critique and improve its own output before delivering, catching errors a first pass misses, without spiraling. Use when correctness matters and an agent should check its own work rather than ship the first draft.
- ▌ Staying On Task · amey-thakurKeep an AI agent anchored to the actual goal through long or messy work. Use at the start of any multi-step task, and whenever work begins to drift, balloon, or stall.
- ▌ Tool Use Design · amey-thakurDesign LLM tools with descriptions that steer, granularity that composes, and error returns the model can act on. Use when building agent tool sets or debugging wrong-tool and wrong-argument failures.
- ▌ Competitive Messaging · amey-thakurTalk 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.
- ▌ Marketing Attribution · amey-thakurAssign credit for conversions across touchpoints honestly, knowing what each model hides. Use when deciding where to spend and channels each claim the same conversions.
- ▌ Social Media Strategy · amey-thakurChoose 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.
- ▌ Media Delivery · amey-thakurServe 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.
- ▌ Agent QA Gate · amey-thakurPlace a QA agent as the last blocking node before output ships, checking acceptance criteria against executed test evidence with the power to veto. Use when builder agents keep declaring done on work that does not meet its criteria and you need one gate that runs the artifact instead of trusting the claim.
- ▌ Tls And Certificates · amey-thakurIssue, install, renew, and debug TLS certificates so connections stay encrypted and trusted without surprise expiry. Use when setting up HTTPS, rotating a certificate, or diagnosing a trust or handshake error.
- ▌ Semantic Versioning · amey-thakurCommunicate compatibility through version numbers so consumers know what upgrading costs. Use when releasing a library, deciding whether a change is breaking, or setting a dependency range.
- ▌ Memory Optimization · amey-thakurCut a program's memory footprint by fixing data layout, reusing allocations, and streaming input instead of buffering it whole. Use when a process is killed by the OOM killer, garbage collection dominates the profile, or heap growth tracks input size.
- ▌ Performance Budgets · amey-thakurSet numeric performance budgets and enforce them in CI so regressions fail the build instead of reaching users. Use when performance keeps sliding release over release or a team wants to hold a latency or bundle target.
- ▌ Prompt Iteration · amey-thakurImprove a prompt through controlled changes measured against a fixed set of cases, rather than by rewriting until an example looks good. Use when a prompt underperforms and each edit is a guess.
- ▌ Prompt Structure · amey-thakurOrder a prompt so the model knows its task, its material, and its output before it starts generating. Use when writing any non-trivial prompt or fixing one that produces the wrong shape of answer.
- ▌ Python Project Structure · amey-thakurOrganize Python packages so imports stay clean, cycles cannot form, and the layout scales with the codebase. Use when starting a Python project or untangling circular imports and grab-bag modules.
- ▌ Hypothesis Driven Work · amey-thakurFrame work as falsifiable hypotheses, test the cheapest first, and update on evidence rather than defending the plan. Use when facing uncertainty and tempted to build the whole thing before learning anything.
- ▌ Faceted Search · amey-thakurProvide filters that narrow results honestly, with counts that reflect what is actually available and a clear way back out. Use when a result set is large enough that browsing needs structure.
- ▌ Typo Tolerance · amey-thakurCorrect or forgive misspelled queries without turning precise searches into fuzzy guesses. Use when users mistype and get nothing, or when fuzzy matching returns irrelevant results.
- ▌ Browser Storage Safety · amey-thakurDecide where a web app keeps tokens and state by reasoning about the XSS blast radius of each store, not by convenience. Use when choosing how to persist session tokens, auth state, or any value an attacker on your origin would want to read.
- ▌ Deserialization Safety · amey-thakurTreat any serialized bytes from outside the program as hostile, parsing them through schema-validated formats instead of native object reconstructors. Use when reading pickles, Java or PHP serialized objects, YAML, or any encoded structure that arrives from a user, a queue, or a cache.
- ▌ Path Traversal Defense · amey-thakurStop user-supplied path components from escaping the directory you meant to confine them to. Use when a filename, path segment, or archive entry from outside the program is joined into a filesystem path for reading, writing, or serving.
- ▌ Spreadsheet Charts · amey-thakurBuild charts that make the point clearly, choosing the type by the question and removing everything that does not carry meaning. Use when presenting spreadsheet data visually.
- ▌ Test Environment Parity · amey-thakurClose the gaps between test and production by matching versions, data shape, and configuration paths so a passing suite actually predicts prod behavior. Use when tests are green but production breaks in ways staging never showed.
- ▌ Citation Grounding · amey-thakurTie every claim in a generated answer to the retrieved passage that supports it, so users can verify and unsupported claims are visible. Use when answers are drawn from documents users may need to check.
- ▌ API Gateway Pattern · amey-thakurUse an API gateway for cross-cutting edge concerns without letting it absorb business logic, including the BFF variant. Use when fronting services with a gateway or untangling a bloated one.
- ▌ Chaos Gameday · amey-thakurRun a game day that injects a real failure on purpose under safety rails, then captures what monitoring, runbooks, and responders actually did. Use when you want to prove resilience before an incident tests it for you, or to rehearse a team on a failure it has never handled.
- ▌ Exec Briefing · amey-thakurBrief executives with the answer first, the whole thing on one page, risks paired with the decision you need, and no surprises. Use when you must get a decision or an update in front of leadership who have five minutes and no context.
- ▌ Launch Review · amey-thakurRun a launch review that gates a release behind a readiness checklist, named sign-offs, and a clear no-go authority. Use when a user-facing launch is about to ship and a bad release would be costly to walk back.
- ▌ Exhaustive Switches · amey-thakurMake switch and match statements provably total so adding a case forces every site to handle it, with no default that hides the gap. Use when branching over an enum, union, or sealed type.
- ▌ Legacy Code Changes · amey-thakurChange untested legacy code safely using characterization tests, seams, and the sprout method. Use when you must modify code that has no tests and you cannot prove your change is harmless.
- ▌ Rewrite Vs Refactor · amey-thakurDecide whether to refactor code in place or rewrite it from scratch using risk math, not frustration. Use when a component feels beyond repair and someone proposes starting over.
- ▌ Support Handoff · amey-thakurTransfer a ticket between agents, shifts, or teams without the customer repeating themselves. Use when work crosses people and context is being lost.
- ▌ Data Classification · amey-thakurLabel data by sensitivity so controls, retention, and access follow the label instead of being argued case by case. Use when designing storage, granting access, or deciding how carefully a dataset must be handled.
- ▌ Experiment Analysis · amey-thakurAnalyze A/B test results correctly: effect size with intervals, guardrails, segments, and the peeking and Simpson traps. Use when reading out an experiment and deciding whether the change worked, before you ship it.
- ▌ Regression Analysis · amey-thakurFit and interpret regression models for insight, reading coefficients, fit, and caveats honestly rather than as causal truth. Use when using regression to understand relationships in data, not to build a predictive model.
- ▌ Database Normalization · amey-thakurApply normal forms pragmatically and denormalize deliberately, weighing update anomalies against read performance. Use when designing a relational schema or deciding whether to denormalize.
- ▌ Transactions Isolation · amey-thakurChoose isolation levels by the anomalies they prevent, understand locking versus MVCC, and retry on serialization failures. Use when transactional correctness matters or concurrency bugs appear under load.
- ▌ Batch Size Effects · amey-thakurChoose batch size understanding its effect on gradient noise, memory, throughput, and generalisation, and adjust the learning rate with it. Use when scaling training or running out of memory.
- ▌ Slide Deck Creation · amey-thakurBuild a deck that supports a spoken argument, with one idea per slide and visuals that carry meaning. Use when presenting to an audience rather than sending a document.
- ▌ Docker Image Optimization · amey-thakurBuild small, fast, secure container images with layer caching, multi-stage builds, and a minimal base policy. Use when images are bloated, slow to build, or failing security scans.
- ▌ Infrastructure Monitoring · amey-thakurMonitor systems with the golden signals and USE method, alerts that page only on user impact, and runbook-linked responses. Use when instrumenting infrastructure or fixing alert fatigue.
- ▌ Backpressure · amey-thakurBound every queue and propagate overload upstream so systems degrade by shedding instead of collapsing. Use when designing high-throughput paths or diagnosing latency spirals under load.
- ▌ Saga Pattern · amey-thakurCoordinate multi-service transactions as a sequence of local steps with compensations, timeouts, and an observable state machine. Use when a business flow spans services and two-phase commit is not on the table.
- ▌ API Reference Docs · amey-thakurProduce API reference docs that blend generation with curation, an example per endpoint, and documented errors. Use when documenting an API or SDK for external or internal consumers.
- ▌ Code Documentation · amey-thakurWrite code comments and API docs that carry what the code cannot say, and nothing it already does. Use when documenting functions, modules, or tricky passages.
- ▌ Interrupt Safe Code · amey-thakurWrite ISRs that stay minimal, share data through volatile-correct handoffs, and defer real work safely. Use when writing interrupt handlers or debugging corruption that only happens sometimes.
- ▌ Actions Security · amey-thakurPrevent workflow automation from becoming an attack path, through pinned actions, scoped tokens, and careful handling of untrusted input. Use when workflows handle secrets or run on pull requests from forks.
- ▌ JS Modules · amey-thakurNavigate ESM and CommonJS, interop between them, and structure imports so bundlers can tree-shake. Use when hitting module-resolution errors, mixing ESM and CJS, or shrinking a bundle.
- ▌ LLM Cost Latency · amey-thakurCut LLM cost and latency with caching, model tiering, prompt diet, batching, and streaming UX. Use when the inference bill or response time needs engineering down.
- ▌ Imbalanced Data · amey-thakurHandle skewed classes with threshold moving, weighting, and PR-based evaluation instead of reflexive resampling. Use when the positive class is rare and accuracy looks deceptively high.
- ▌ MCP Sampling And Elicitation · amey-thakurUse 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.
- ▌ React Native Architecture · amey-thakurStructure React Native apps around clear native-module boundaries and decide honestly when RN fits. Use when starting or auditing a React Native codebase, or weighing RN against fully native development.
- ▌ Tax Calculation · amey-thakurDetermine, apply, and record sales tax or VAT correctly by jurisdiction, product type, and customer status. Use when selling across borders or when tax handling is currently a flat assumption.
- ▌ Context Placement · amey-thakurDecide where in a prompt to put documents, history, and instructions, given that models attend unevenly across a long context. Use when prompts are long and the model ignores material in the middle.
- ▌ Few Shot Examples · amey-thakurTeach a task by showing worked examples, chosen and ordered so the model generalises the pattern rather than copying the specifics. Use when instructions alone produce inconsistent format or judgement.
- ▌ Prompt Versioning · amey-thakurManage prompts as versioned artefacts with review, rollback, and a record of what changed and why. Use when prompts affect production behaviour and more than one person edits them.
- ▌ Capacity Forecasting · amey-thakurPredict when current capacity will be exhausted and plan the increase before it becomes an incident. Use when growth is steady enough to plan for or when scaling events surprise you.
- ▌ Graceful Degradation · amey-thakurDesign systems that lose functionality progressively rather than failing entirely when a dependency is unavailable. Use when one component's failure currently takes down the whole product.
- ▌ Financial Functions · amey-thakurUse present value, rate, and payment functions correctly, with consistent periods and sign conventions. Use when modelling loans, investments, or discounted cash flows.
- ▌ Ffi Boundaries · amey-thakurDesign foreign-function boundaries with explicit ownership, error translation, and contained panics/exceptions. Use when binding between Rust/Go/Python and C/C++ libraries or exposing your library over a C ABI.
- ▌ Go Concurrency · amey-thakurStructure goroutines with owned lifecycles, context propagation, and channel patterns that cannot leak or race. Use when writing concurrent Go or debugging goroutine leaks and data races.
- ▌ Rust Ownership · amey-thakurWork with the borrow checker through ownership-first design instead of fighting it with clones and unsafe. Use when writing Rust or resolving borrow-checker errors that feel unwinnable.
- ▌ Keyboard Navigation · amey-thakurMake interfaces fully keyboard-operable with logical focus order, no traps, skip links, and roving tabindex where needed. Use when building interactive UI or auditing keyboard accessibility.
- ▌ Agent Code Review · amey-thakurUse an agent to review a diff productively, with the right scope, framing, and scepticism about its findings. Use when reviewing your own changes before requesting human review.
- ▌ Agent Plan Review · amey-thakurHave an agent produce a plan before implementing, and review it as the cheapest intervention point in the work. Use before any non-trivial agent task.
- ▌ Chunking Strategies · amey-thakurSplit documents into retrieval units that preserve meaning, so a retrieved chunk answers the question rather than trailing off mid-thought. Use when building or fixing a retrieval pipeline whose results are technically relevant but useless.
- ▌ Context Compression · amey-thakurReduce retrieved material to what the model needs, through filtering, extraction, and summarisation, before it reaches the prompt. Use when retrieved context is large, mostly irrelevant, or crowding out reasoning.
- ▌ Conversation Memory · amey-thakurKeep a long conversation coherent within a finite window through rolling summaries, pinned facts, and selective recall. Use when sessions run long enough that early context falls out.
- ▌ Multi Hop Retrieval · amey-thakurAnswer questions that need several linked lookups by decomposing the query and retrieving in sequence. Use when questions require combining facts that never appear in the same passage.
- ▌ Domain Driven Design · amey-thakurApply DDD pragmatically: bounded contexts, ubiquitous language, and aggregates sized to invariants. Use when modeling a complex domain or when code and business people describe the same thing differently.
- ▌ Layered Architecture · amey-thakurOrganize a system into layers with one permitted direction of dependency and enforce that direction mechanically at the import level. Use when a codebase is sliding toward tangled cross-references and you need a rule a linter can check, not a convention people forget.
- ▌ Scalability Planning · amey-thakurPlan scalability from a load model and bottleneck math, designing for realistic growth without premature over-engineering. Use when designing for scale or after a load-driven incident.
- ▌ Oncall Handoff · amey-thakurHand off an on-call rotation by transferring open incidents, watch items, and the tribal context runbooks miss. Use at the end of a shift or rotation when the pager passes to the next responder and continuity of understanding matters.
- ▌ Data Engineer Role · amey-thakurOperate as a data engineer who ships pipelines to a freshness SLA, enforces schema contracts at the source, and owns data quality end to end. Use when building or reviewing a pipeline, warehouse table, or ingestion path that other teams will trust.
- ▌ UX Researcher Role · amey-thakurOperate as a UX researcher who ties every study to a pending decision, synthesizes evidence into ranked insights, and delivers findings that move the roadmap. Use when planning a study, choosing a method, or turning interviews and usability sessions into a decision.
- ▌ Code Review Comments · amey-thakurWrite review comments that land by labeling severity and separating genuine questions from directives. Use when leaving comments on a pull request or coaching someone on how theirs read.
- ▌ File Systems · amey-thakurUnderstand how files, directories, and durability actually work, so data written is data that survives a crash. Use when writing files that matter or debugging corruption and permission problems.