Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkills › Authors › Amey-Thakur › Page 10

Amey-Thakur

@Amey-Thakur on GitHub →

733 Claude Code skills authored by Amey-Thakur.

updated 2026-11-15 · showing 541–600 of 733 by quality score

Average Pro QualityScore: 64.1/100

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

Run a team of growth agents that designs an experiment, builds the variant, analyzes the result, and passes an ethics gate before anything ships.
Share one physical GPU across several small workloads using MIG, MPS, or time slicing, and pick the mode whose isolation matches the risk.
Understand how files, directories, and durability actually work, so data written is data that survives a crash.
NVIDIA TensorRT model optimization and deployment. Convert models to TensorRT engines, configure optimization profiles and precision modes, apply INT8 calibration, analyze kernel…
Back-of-envelope calculations for system design. Use when estimating QPS, storage, bandwidth, or latency for capacity planning.
Run an org-level board that grades incident postmortems against a quality bar, promotes cross-cutting fixes to owned work, and reads across incidents for trends.
Place a QA agent as the last blocking node before output ships, checking acceptance criteria against executed test evidence with the power to veto.
Reach customers before they contact you, when telemetry or a known issue means they are about to have a problem.
Process only new and changed data with watermarks, merge strategies, and a full-refresh escape hatch.
Configure rules that stop unreviewed or broken code reaching the default branch, without making routine work impossible.
Retire API surface with sunset headers, usage tracking, migration guides, and enforced timelines. Use when removing an endpoint, field, or version that consumers depend on.
Run a team of support agents that triages each ticket, reproduces the problem, drafts a reply, and hands clean escalations to a human.
Write role cards that pin each agent to one charter with declared inputs, outputs, refusal rules, and non-overlapping scope.
Write Makefiles with honest dependencies, phony discipline, and self-documenting help, and know when make is the wrong tool.
Interpret what a user meant before matching, through normalisation, intent detection, and entity extraction.
Maintain a living register of business risks with agents that surface new ones, track mitigations, and force stale entries back to a decision.
Handle plurals, grammatical gender, and agreement using locale plural categories rather than an if-else on count.
Match people and capacity to project needs over time, accounting for partial allocation, ramp-up, and the cost of splitting attention.
Set, measure, and honour response and resolution commitments that reflect real capacity rather than aspiration. Use when promising response times to customers or in contracts.
Plan GPU spend by comparing owned hardware, reserved cloud, and on-demand against real utilization and lead time, so you commit at the right break-even.
Join data between sheets reliably using modern lookup functions, handling missing matches and duplicates explicitly. Use when combining data from more than one table.
Prepare for a penetration test by fixing scope, rules, and access up front, then turn its findings into tracked, verified remediation.
Put confirmation gates, blast-radius limits, audit trails, and kill switches around automation that can destroy things. Use when building scripts or bots with destructive power.
Design builds that are fast, reproducible, and cacheable, so developers wait less and CI costs less. Use when builds are slow, flaky, or produce different results locally and in…
Design each handoff between two agents as an explicit artifact contract with a context budget and a rule for what must survive the crossing.
Build input systems with action mapping, buffering, dead zones, and rebinding that feel responsive and fair.
Configure Kubernetes workloads with correct requests, probes, disruption budgets, and workload types.
Prepare a raise with agents that assemble the narrative, stress-test it as an investor would, and organise diligence material, while the founder owns every conversation.
Choose a loss that matches the task and the metric you care about, and understand what each penalises. Use when a model optimises well and performs badly on the thing that matters.
Python testing with pytest using uv package manager. Use when: (1) Running Python tests, (2) Writing test files or test functions, (3) Setting up fixtures, (4) Parametrizing…
Find and remove duplicate rows deterministically, keeping the record you meant to keep. Use when a table has accumulated duplicates or an import needs a clean unique set.
Frame work as falsifiable hypotheses, test the cheapest first, and update on evidence rather than defending the plan.
Instrument LLM applications with request tracing, token accounting, quality signals, and feedback loops.
Run the same task several times independently and combine the results by agreement, to damp variance on judgement calls.
Understand the layers between a request and its response, so latency, connection failures, and timeouts can be attributed to the right layer.
Shape pull requests a reviewer can actually hold in their head, through small size, a why-first description, and a self-review pass.
Run a team of postmortem agents that builds the timeline, analyzes causes, drafts corrective actions, and reviews for blamelessness and completeness.
Cap flaky tests with a measured budget, quarantine them off the merge gate, and burn them down under named owners and deadlines.
Design experiments with controls, randomization, confound awareness, and pre-registered analysis. Use when testing a hypothesis empirically and needing the result to actually mean…
Combine diverse models through averaging, blending, and stacking to beat any single model. Use when squeezing maximum accuracy from a competition or high-stakes prediction, after…
Use leases with fencing tokens for mutual exclusion across machines, or restructure to need no lock at all.
Universal links and deep linking skill for implementing iOS Universal Links, Android App Links, custom URL schemes, and deferred deep linking across mobile platforms.
Write openings that earn the next sentence: hook the reader, promise value, and get to the point fast. Use when a piece's beginning is slow, generic, or buries what matters.
Reason correctly about probability, base rates, conditional probability, and expected value, avoiding the common intuition traps.
Build repeatable data transformations that refresh on demand, replacing manual cleaning steps with a recorded pipeline.
Define what gets escalated, to whom, and how fast, so problems reach a decision maker at the right moment rather than too early or too late.
Scale databases by partitioning and sharding with a good key, handling resharding and cross-shard queries, and knowing when to avoid it.
Track every commitment from assignment to completion, chasing what is late and escalating what is stuck, so work finishes rather than fading.
Operate as a solutions architect who turns a customer's constraints into a defensible reference design and a path to production.
Store, scope, and rotate integration credentials so a leak is survivable and rotation does not cause an outage. Use when managing keys for external services.
Operate as a QA engineer who owns test strategy, automation coverage, and the release quality signal.
Reshape rows into columns and back, and know when the reshape belongs in SQL rather than in the reporting layer.
Split a large task across parallel agents that each handle one slice, then merge their outputs deliberately.
Keep agent usage within budget through context discipline, model selection, and caching, without degrading results. Use when agent costs are rising or long sessions are expensive.
Redistribute work across desks and workers as load shifts, so one bottleneck does not stall the company while others idle.
Ship reusable prompt templates from an MCP server so users invoke tested workflows rather than improvising.
Build forms with associated labels, identified errors, clear instructions, and autocomplete attributes. Use when creating or auditing forms for accessibility.
Convene agents to model pricing options, argue them from customer, competitor, and margin angles, and hand a human a decision pack.
Schedule GPU jobs on a shared cluster so distributed jobs get all their GPUs at once, fragmentation stays low, and preemption is predictable.
Produce campaigns with agents that research the audience, draft variants against a brief, check claims and brand voice, and leave publishing to a human.
Search all 733 skills by Amey-Thakur →