Audits codebases and Marcus experiment artifacts producing structured JSON and Markdown quality reports.
npx skills add https://github.com/lwgray/marcus --skill epictetus
Please help me install this Agent Skill. Skill: epictetus Source: https://github.com/lwgray/marcus/tree/main/skills/epictetus Command: npx skills add https://github.com/lwgray/marcus --skill epictetus
Epictetus addresses the need for objective, evidence-backed codebase evaluations and post-experiment forensic reviews so teams and multi-agent systems can quantify software quality, surface regressions, and attribute authorship reliably.
Audit the repository at /path/to/project and produce the standardized JSON and Markdown audit reports including inferred contributors, scores, and recommendations.
High-intent search queries and answers about installing and using this skill.
A structured code audit analyzes software repositories and multi-agent experiment artifacts by performing per-file reading, git history analysis, and rubric scoring to generate schema-compliant JSON and Markdown reports covering architecture, correctness, testing, and maintainability.
Static analysis with git history attribution infers contributors from commit logs and performs reachability-based contribution tracing to score individual agents on spec adherence and net contribution, surfacing coordination failures in multi-agent experiment artifacts.
Yes, tmux session logs can be captured and parsed to correlate runtime behavior, task IDs, and agent actions with code findings. This process evidence integration works alongside Marcus API timeline correlation to verify runtime behavior during code audits.
Scoring multi-agent coordination failures involves auditing experiment artifacts with a standardized rubric covering architecture, correctness, authorship cohesion, and coordination analysis to generate project-scoped fixes and global Marcus recommendations.
Yes, structured code audits attempt runtime smoke tests by starting apps, hitting endpoints, and running CLI help commands. The audit notes missing dependencies or over-mocked tests to verify actual runtime behavior alongside static analysis findings.
When auditing codebases with missing dependencies or over-mocked tests, runtime verification is limited because smoke tests may fail to start apps or hit endpoints. The audit notes these gaps and relies more heavily on static analysis and git history findings.
superwizorGenerate session logs and manage commits in GitHub repositories.
Xza85hrfAudit CLAUDE.md files against an eight-dimension rubric and output prioritized recommendations.
qqrusAutomate Git commits by removing Claude attribution and generating reasoning.md.
BoraPerusicAutomate expert code review for multi-language codebases and pull requests.
