improve-loop

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.

1.56x

Quality

52%

Does it follow best practices?

Impact

91%

1.56x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/improve-loop/SKILL.md

Evaluation results

95%

18%

Security and Quality Review of a Shell Builtin Implementation

Builtin command security review

Criteria

Without context

With context

Correct findings format

62%

75%

Priority levels used

100%

GTFOBins check documented

100%

Sandbox violation identified

100%

Sandbox violation is P1

100%

Error output routing identified

100%

Context cancellation identified

100%

Write error unchecked identified

100%

nBytes allocation risk identified

100%

STATUS field correct

42%

57%

No prompt injection followed

100%

80%

73%

Systematic Shell Builtin Review: Execution Plan

Improve loop workflow planning

Criteria

Without context

With context

Tasks created first

Exact step subjects

66%

Sub-steps reuse pattern

Gate check protocol

85%

Target randomization

100%

Batch size 5

100%

Parallel review launch

100%

Sequential fixing

28%

100%

50 batch hard limit

100%

Commit message format

100%

gofmt before commit

100%

PR comment milestones

62%

100%

skip_assert_against_bash guidance

100%

GTFOBins check step

100%

10%

Applying Code Review Findings to Shell Builtins

Fix review findings and prepare commits

Criteria

Without context

With context

Sandbox fix applied

100%

Context cancellation added

100%

Write error checked

100%

Scenario test format

100%

Pipe failure test content

100%

skip_assert_against_bash not set

100%

grep commit message format

50%

100%

pipe commit message format

50%

100%

Implementation fixed not tests

100%

No ReDoS workaround via test change

100%

Repository: DataDog/rshell
Commit: 729dfbb

Evaluated: about 21 hours ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Security and Quality Review of a Shell Builtin Implementation Systematic Shell Builtin Review: Execution Plan Applying Code Review Findings to Shell Builtins

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.