菜单
Implement a legitimate Harbor Oracle solution and validate its behavior against an independent verifier without weakening the task contract.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Build or repair a deterministic Harbor task environment with explicit resources, network policy, health checks, and safe solver-visible boundaries.
Red-team a Harbor verifier for answer leakage, reward hacking, shared-container tampering, artifact manipulation, and semantic under-testing.
Calibrate a frozen tb-hard task using Harbor Oracle and real-agent rollouts, then distinguish authentic difficulty from ambiguity, flakiness, leakage, or infrastructure failure.
Create or evolve a canonical Harbor task inside a stable tb-hard case directory. Use after the design brief names observable acceptance criteria and at least three difficulty dimensions.
Audit a calibrated Harbor task for deterministic purchaser export, leakage, evidence completeness, and release readiness.
Research Harbor and Terminal-Bench 2 patterns to design an original tb-hard task. Use before approving a design brief or when checking whether a candidate is too shallow or derivative.
| name | harbor-oracle-verifier |
| description | Implement a legitimate Harbor Oracle solution and validate its behavior against an independent verifier without weakening the task contract. |
| argument-hint | <case_id> |
| user-invocable | true |
| context | fork |
| agent | oracle-solution-engineer |
| model | opus |
| effort | xhigh |
| allowed-tools | Read Write Edit Glob Grep Bash |
Target case: $ARGUMENTS
The Oracle proves solvability. Work only in cases/<case_id>/task/solution/ unless the main agent explicitly assigns a verifier defect investigation. Do not weaken or redesign tests, public constraints, or task semantics to make the Oracle pass.
Solve from the same baseline available to a competent solver. Do not hardcode public samples or read private briefs, calibration evidence, hidden grader material, or authoring assets. Run make oracle CASE=<case_id> from a clean environment and preserve command/log metadata under evidence/<case_id>/oracle/.
Return changed files, run command, reward, logs, and any independently reviewable coverage concern.
