Unofficial community toolkit for HackerRank Orchestrate: 8 agent skills (Claude Code, Codex, Cursor, Copilot) for the 24-hour AI agent hackathon, plus an auditor and estimated scorer. Not affiliated with HackerRank.
This repository also configures its own agents. See what hackerrank-orchestrate-skills tells them →
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Orchestrate phases 1 and 2 - turn the problem statement into a written design (DESIGN.md) and then build the agent so it runs end to end on the sample with validation, failure handling and secrets handled. Use after reading the problem statement and sample data, and until the pipeline writes a valid CSV for the whole…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Orchestrate's 30-minute AI judge interview (30% of the score). Build the constants provenance sheet, prepare answers to the nine probed topics using mechanisms and measured trade-offs, and rehearse honest limits. Use from mid-build onward, and again before submission.
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Orchestrate final packaging. Checks the repo against the exact submission rules in problemstatement.md (output.csv header, row coverage, allowed values, code, README, transcript, secrets) and only then builds the submission/ folder with output.csv, code.zip, README, transcript and usage report. Use in the final hours…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Reference library for Orchestrate - ready-to-paste Claude Code prompts (kickoff, iteration, audit, freeze), the engineering playbook principles with case studies, the AI judge preparation notes, the release checklist, the community kit CLI, past-winner patterns, and rubric history. Read on demand; do not read top to…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Estimate the Orchestrate score the way HackerRank weights it - four signals (Code ZIP 30%, Output CSV 30%, AI Interview 30%, Chat Transcript 10%) with the published sub-weights. Uses the kit's scoring module as a heuristic and clearly separates measured facts from estimates. Use before submission, after each…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Orchestrate phases 5 and 6 - self-score all four sections against the rubric, harden security and robustness, check cost numbers, then run the spec audit, consistency check and release gate before packaging the submission. Use once the output is stable, and in the final two hours before submitting.
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
Orchestrate phases 3 and 4 - find where the built agent is wrong or fragile (edge cases, overfitting, determinism, two-strategy comparison, one-input trace), then fix wrong rows one change at a time with a diff of the whole output. Use once the pipeline runs on the sample, and whenever output rows are wrong or weakly…
NITISH-R-G/hackerrank-orchestrate-skills
Skill Claude CodeCodex
START HERE for HackerRank Orchestrate. Master plan for the 24-hour challenge - scoring targets, the phase order, which orchestrate- skill to run next, what to do when a step fails, and the transcript discipline that applies all day. Use at the start of the challenge, whenever you are unsure what to do next, or when…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: