Run [implement-spec](../implement-spec/SKILL.md) with Codex doing the implementation passes while you orchestrate, integrate, and review. Use when the user asks to implement a spec with Codex, or to run implement-spec with Codex as the implementer.
Use this skill to detect cheating in evaluation result directories (not jsonl format). Evaluation directories contain CVE subdirectories with agent traces in agent-logs/last_mini_run.traj.json. This skill: 1) Converts directory structure to jsonl; 2) Detects cheating patterns; 3) Launches parallel agents for verification; 4) Aggregates results. Trigger when user mentions: check cheating in evaluation results, detect cheating in eval directory, or provides a path like 'model/date' format.
Use this skill to detect and filter cheating cases in agent training data. Cheating is defined as an agent obtaining official fix code/patches from the network to reference or copy. This skill can: 1) Scan training data for cheating patterns (curl github, git show commit, npm pack, etc.); 2) Launch parallel agents to verify if detected cases are real cheats or false positives; 3) Filter out verified cheating cases from the dataset. Trigger when user mentions: cheating detection, filter cheating, verify cheating, clean training data, or wants to remove cases where agents downloaded fix code.
Guides Generator Agent to write high-quality dynamic test_vuln.py for CVE reproduction. Provides PoC level classification (P1-P5), CWE-specific payload collections, runtime judgment criteria, and structured self-check workflow. Use when Generator writes vulnerability tests, mentions CWE, test_vuln, PoC, exploit, security test, XSS, SQL injection, command injection, path traversal, CSRF, buffer overflow, use-after-free, missing authorization, or file upload.