Review checkpoint specs and tests to identify tests that encode ambiguous interpretations rather than explicit requirements. Use when asked to check checkpoint_N.md against test_checkpoint_N.py, when auditing tests for ambiguity, or when reviewing snapshot eval failures for interpretive issues.
Install
npx skills add SprocketLab/slop-code-bench --skill checkpoint-ambiguity-reviewnpx skills add SprocketLab/slop-code-bench --skill checkpoint-ambiguity-review -a claude-code -gnpx skills add SprocketLab/slop-code-bench --skill checkpoint-ambiguity-review -a codex -ggemini skills install https://github.com/SprocketLab/slop-code-bench.git --path .codex/skills/checkpoint-ambiguity-reviewgh skill install SprocketLab/slop-code-bench checkpoint-ambiguity-reviewgit clone --depth 1 https://github.com/SprocketLab/slop-code-bench /tmp/SprocketLab__slop-code-bench
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/SprocketLab__slop-code-bench/.codex/skills/checkpoint-ambiguity-review ~/.claude/skills/checkpoint-ambiguity-review # Claude Code
cp -R /tmp/SprocketLab__slop-code-bench/.codex/skills/checkpoint-ambiguity-review ~/.agents/skills/checkpoint-ambiguity-review # Codex, Cursor, Gemini CLI, Copilot, OpenCode