NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Designing the agent itself for an Orchestrate-style challenge — real agent loops versus hardcoded workflows, tool boundaries, prompt structure, and the design decisions a judge can actually see in your code. Use when starting to build an AI agent for a hackathon or evaluation, when deciding between a scripted pipeline…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Working with an AI coding assistant in a way that produces a strong, scorable chat transcript — visible planning, explicit constraints, real debugging dialogue, deliberate iteration. Use continuously throughout any session where the transcript itself will be evaluated (HackerRank Orchestrate's AI chat transcript…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Build checkpoint-and-resume capability into a HackerRank Orchestrate agent's batch processing run, so an API rate limit or crash partway through a full-dataset run doesn't force reprocessing everything from scratch. Use when writing the main loop that processes the full ticket/claim dataset, or after a rate limit or…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Set and defend the confidence column. Use when choosing confidence values, and before any recalibration. The counter-intuitive rule: calibrate to the labeling policy, not to correctness.
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Track and report operational metrics — model calls, token usage, cost estimates, runtime, and rate-limit (TPM/RPM) considerations — for a HackerRank Orchestrate submission, a graded requirement in the multi-modal-review challenge. Use when instrumenting an agent's LLM calls, when preparing final approach…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Find every place a solution accidentally depends on an incidental property of the sample data — id format, timestamp format, row order, filenames, exact wording. Use before submission, because the graded set differs from your sample in every way the spec does not explicitly fix.
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Prove output is reproducible, and state precisely where that guarantee stops. Use before submission and whenever output changes between identical runs. Unqualified determinism claims are almost always false.
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Test a HackerRank Orchestrate agent against its failures and inconsistencies, not just its successes — deliberately inspecting where similar cases get different treatment. Use before submission when the only testing done so far was "run it and see if the output.csv looks reasonable," when comparing how the agent…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Design escalation and uncertainty-marking as a first-class, calibrated decision in a HackerRank Orchestrate agent — not a fallback bolted on after the main logic. Directly addresses the published finding that both escalate-everything and respond-to-everything fail. Use when designing the decision boundary between…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Score a whole Orchestrate repository across specification, evidence, generalization, determinism, security, and release readiness — and decide whether it is moving toward the top of the leaderboard. Use at each phase gate and before submission.
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Design and defend the evidence column. Use when building retrieval or considering a ranker change. Covers the ceiling analysis that tells you whether a gain is possible at all, and why the fashionable option often loses.
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Design failure handling for a HackerRank Orchestrate agent so failures degrade safely instead of silently — logging failed rows, continuing processing when safe, and explicitly marking uncertainty rather than guessing. Use whenever writing the main processing loop that iterates over tickets/claims, when deciding what…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Trace a single input through every stage of a HackerRank Orchestrate agent pipeline (input loading, context building, model invocation, response parsing, validation, fallback) to verify each stage does what you assume it does. Use as a design self-check right after scaffolding a pipeline, when debugging a specific…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Validate inputs before they reach a model call (not just outputs after), and use deterministic rule-based overrides for cases where model discretion shouldn't apply — for HackerRank Orchestrate agents or any LLM pipeline handling untrusted structured input. Use when writing the ingestion/input-loading stage of an…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Prepare for the AI judge interview: know your constants, state boundaries, and never claim what the repository cannot support. Use in the hours before the interview and when writing any defensive documentation.
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Preparing for an AI-conducted technical interview scored by evidence-anchored rubrics (HackerRank Chakra-style, or similar) — rehearsing specific, concrete answers instead of general ones, and practicing honest disclosure of your system's limitations. Use before any voice or chat interview where an AI judge scores…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Writing agent decision justifications that are scored well — evidence-anchored, specific, calibrated, and honest about uncertainty. Use whenever an agent must explain or justify a decision it made (an escalation, a classification, a refusal), when producing an output file that includes reasoning alongside verdicts, or…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Evaluate a change BEFORE you make it: expected gain, risk, blast radius, what to measure, and whether it was already tried and rejected. Use whenever you are about to optimise something in the final hours.
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Compare at least two distinct strategies, prompts, or configurations against HackerRank Orchestrate's sample dataset, and document the reasoning behind the final choice — a graded requirement in the multi-modal-review challenge and strong practice for any Orchestrate challenge. Use when deciding between two…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Prove that image and audio content actually changes routing decisions, rather than merely being loaded. Use whenever a submission claims multimodal reasoning. The test is the counterfactual: disable the modality and show the decision changes.
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Ground claim-verification decisions in specific, cited visual evidence for HackerRank Orchestrate's multi-modal-review challenge (or any future multi-modal Orchestrate challenge) — mapping each claim verdict back to specific image IDs, classifying severity/risk explicitly, and distinguishing "contradicted" from "not…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Structure a HackerRank Orchestrate codebase with clear separation of concerns and descriptive naming — the specific pattern HackerRank's own advice calls out as scored. Use when scaffolding a new Orchestrate project, when a codebase has accumulated files named "helper.py" or "utils.js", or before submission when…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
The master sequencing skill for HackerRank Orchestrate (or any timeboxed agent-building hackathon) — enforces an ordered set of quality gates from planning through submission, and names which companion skill owns each gate. Use this at the START of any Orchestrate-style challenge, whenever the user mentions HackerRank…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Write prompts for a HackerRank Orchestrate agent with the same engineering rigor as code — explicit allowed-output specifications, required-evidence framing, and format requirements, treating the prompt as a reviewable artifact rather than throwaway text. Use whenever writing or revising a system/task prompt for the…