| Skill | Added | Review |
|---|---|---|
fix-ci-tests .claude/skills/fix-ci-tests/SKILL.md Diagnose and fix CI failures on a GitHub PR by analyzing failing checks, reading logs, and applying fixes | 71 71 Impact — No eval scenarios have been run Securityby  Low Low-risk findings worth noting Version: c5b036b | |
fix-local-tests .claude/skills/fix-local-tests/SKILL.md Fix failing tests by prioritising shell implementation fixes to match bash behaviour | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: c5b036b | |
review-fix-loop .claude/skills/review-fix-loop/SKILL.md Self-review a PR, fix all issues, and re-review in a loop until clean. Coordinates code-review, address-pr-comments, and fix-ci-tests skills. | 61 61 Impact — No eval scenarios have been run Securityby Critical Do not install without reviewing Version: c5b036b | |
code-review .claude/skills/code-review/SKILL.md Comprehensive code review covering security, correctness, bash compatibility, test coverage, and code quality. Use for PRs, commits, or any code changes. | 72 72 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: c5b036b | |
improve-loop .claude/skills/improve-loop/SKILL.md Systematically review and improve every shell feature and builtin command. Iterates through each feature/command, runs code-review, fixes issues, and re-reviews until clean. | 79 79 1.56x Agent success vs baseline Impact 91% 1.56xAverage score across 3 eval scenarios Securityby Low Low-risk findings worth noting Reviewed: Version: c5b036b | |
implement-posix-command .claude/skills/implement-posix-command/SKILL.md Implement a new POSIX command as a builtin in the safe shell interpreter | 57 57 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: c5b036b | |
improve-test-coverage .claude/skills/improve-test-coverage/SKILL.md Improve test coverage for shell features and commands using reference test suites from yash, GNU coreutils, and uutils/coreutils | 60 60 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: c5b036b | |
address-pr-comments .claude/skills/address-pr-comments/SKILL.md Read PR review comments, evaluate validity, implement fixes, push changes, and reply/resolve threads | 61 61 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: c5b036b | |
gtfobins-validate .claude/skills/gtfobins-validate/SKILL.md Validate shell builtins against GTFOBins attack patterns to ensure exploits are blocked by the sandbox | 63 63 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: c5b036b |