Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkills › Authors › Amey-Thakur › Page 2

Amey-Thakur

@Amey-Thakur on GitHub →

733 Claude Code skills authored by Amey-Thakur.

updated 2026-11-15 · showing 61–120 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.

Use cryptography by calling vetted libraries with authenticated defaults and storing keys in a KMS, never by designing a scheme.
Write bash that fails loudly, quotes correctly, cleans up after itself, and passes shellcheck. Use when writing shell scripts that automation or other people will depend on.
Keep a project alive without burning out its maintainers, through scope limits, shared load, and honest signals about capacity.
Run a game day that injects a real failure on purpose under safety rails, then captures what monitoring, runbooks, and responders actually did.
Accept user file uploads without letting them become code execution, storage exhaustion, or a path into other users' data.
Improve ranking with a judged evaluation set and measured changes rather than intuition. Use when search feels wrong and every proposed fix is someone's opinion.
Reach developers through docs, honest content, and community trust instead of ads they ignore. Use when marketing developer tools or building a devrel content engine.
Write a code style guide people actually follow by deciding once, automating enforcement, and logging exceptions.
Operate as a developer relations (DevRel) engineer who closes the loop between external developers and the product team.
Ship code behind flags without accumulating flag rot, through disciplined naming, expiry, and cleanup sweeps.
Write status updates with progress, risk, and asks calibrated to the audience, honoring the no-surprises rule.
Decide when repeated code should be unified and when a duplicate is the cheaper choice. Use when tempted to extract a shared helper or facing copy-pasted code.
Match storage class to access pattern so rarely read media costs less without becoming unavailable. Use when media storage cost grows faster than usage.
Checkpoint multi-node training runs so a save costs seconds instead of minutes and a resume reproduces the run exactly.
Let large uploads survive network interruption by chunking and resuming from the last confirmed part.
Choose stubs, fakes, and mocks deliberately and default to verifying state over interaction so tests survive refactors.
Recover revenue from failed recurring charges with retries, clear notice, and a graceful path back, without harassing customers.
Operate as a support engineer who triages by impact, reproduces before escalating, and turns recurring tickets into product fixes.
Run a team of documentation agents that finds the gaps, drafts the pages, gets them reviewed against the code, and sweeps for staleness on a schedule.
Give feedback that improves performance, timed and framed so it is used rather than defended against. Use when coaching, reviewing work, or mentoring.
Change prices or plan structure without breaking trust or billing, deciding who moves, when, and with what notice.
Suggest queries as the user types, fast enough to feel instant and relevant enough to be worth reading.
Size worker pools, queue depths, and batch widths against the real bottleneck so parallelism adds throughput instead of contention.
Understand what attention computes and why its cost grows quadratically with sequence length, to reason about context limits and efficiency work.
Structure async code so the event loop stays free, slow producers apply backpressure, and blocking calls never stall unrelated work.
Use an agent to write tests that check behaviour rather than restate the implementation, and verify they can actually fail. Use when adding coverage to existing code.
Build 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.
Tune LLM serving to hold latency SLOs while raising GPU throughput, working the batch scheduler, KV cache, and paged attention together.
Handle new requests mid-project by making the trade-off visible rather than absorbing them silently. Use when a project is accumulating additions and the date is not moving.
Run a production readiness review that checks SLOs, runbooks, capacity, and dependencies before an on-call team agrees to own a service.
Drive a real debugger with breakpoints, watch expressions, and conditional stops to read live program state at the moment of failure.
Design a text search feature with the right analyzer, fields, and matching model so results are relevant rather than merely returned.
Run write-first collaboration with the right document types, response-time norms, and meetings reserved for what writing cannot do.
Pursue a high-level goal to completion autonomously: lock the done-condition, decompose, execute with verification, adapt, and know when to stop.
Operate as a product designer who designs the whole flow, specs every state, defends the work in critique, and hands off at build fidelity.
Virtualize long lists so only visible rows mount, with correct handling of dynamic heights and scroll anchoring.
Operate as a data engineer who ships pipelines to a freshness SLA, enforces schema contracts at the source, and owns data quality end to end.
Make absence explicit in the type and resolve it at the edges so the interior never dereferences a surprise null.
Build an internal model of how a system works so you can predict its behaviour rather than recalling procedures.
Work with an agent on a bug by supplying evidence and letting it form hypotheses, rather than asking it to guess from a description. Use when debugging with an agent's help.
Serve media efficiently with caching, range requests, and access control, so playback starts fast and private files stay private.
Use low- and high-fidelity wireframes and prototypes to test ideas cheaply before building. Use when exploring a design, aligning stakeholders, or validating a flow before…
Choose names that carry meaning so readers grasp intent without chasing definitions. Use when naming variables, functions, types, or files, or when a name reads as vague.
Choose a compression codec and level by weighing size reduction against CPU cost, and place compression where the bytes are actually scarce.
Keep a long training job alive across GPU failures, node evictions, and stragglers so one bad host costs minutes, not the whole run.
Keep the suite fast enough to run on every change by measuring the slow tests, shaping the pyramid, cutting IO from the fast tier, and sharding.
Sort and compare text using locale collation rather than byte order, so lists read correctly in every language.
Keep pull requests small through vertical slicing and stacking, because review quality and latency both collapse with size. Use when PRs are too big to review well or sit for days.
Tag releases with semantic versions and signed tags, generate changelogs, and trigger builds from tags.
Transfer a ticket between agents, shifts, or teams without the customer repeating themselves. Use when work crosses people and context is being lost.
Design MCP tools an agent can select correctly, with names, descriptions, and schemas that make the right call obvious and the wrong one impossible.
Store passwords with a slow, salted, memory-hard hash and a plan to raise the cost over time. Use when building signup or login, migrating off a weak hash, or reviewing how a…
Approach a Kaggle (or any ML competition) systematically: trustworthy validation, strong baseline, then disciplined iteration.
Force the thread interleavings that expose races by using barriers, stress loops, and linearizability checks instead of hoping the scheduler hits them.
Run red-green-refactor honestly with the smallest failing test first, refusing test-after backfill dressed up as TDD.
Aggregate desk-level state into an honest company view where problems stay visible instead of averaging away.
Evaluate vendors with agents that build a comparable requirement matrix, research each option, check security and data terms, and prepare a recommendation for human sign-off.
Write an Amazon PR-FAQ that starts from a launch-day press release and hard customer questions so an idea is tested on the customer before it is built.
Assemble an investor or board update from source metrics with agents that draft, fact-check every number, and surface bad news rather than bury it.
Manage every resource through RAII with the rule of zero, correct smart-pointer selection, and move semantics.
Search all 733 skills by Amey-Thakur →