{"id":"devallibus-shiplog","name":"shiplog","af_score":45.0,"security_score":43.8,"reliability_score":21.2,"what_it_does":"shiplog is an AI development “skill” that uses Git and GitHub to persist engineering context across sessions by capturing brainstorms as issues, creating isolated work sessions (branches/worktrees), logging commit context, and writing PR “journey” timelines. It also supports cross-model review/provenance/signing conventions, evidence-linked closure, and artifact metadata for later search.","best_when":"You want long-term, queryable traceability of “why” behind changes created with AI assistants (Claude Code/Codex/Cursor) and you already use GitHub+gh in a normal repo workflow.","avoid_when":"You require an offline-only system with no GitHub writes, or you need fine-grained, auditable permission scoping without using a user’s gh authentication context.","last_evaluated":"2026-03-30T15:24:10.210890+00:00","has_mcp":false,"has_api":false,"auth_methods":["GitHub CLI (gh) authenticated session"],"has_free_tier":false,"known_gotchas":["Relies on `gh` CLI and git state (worktrees/branches). Agent use may fail if repo/branch conventions diverge from expectations.","Because it writes to GitHub issues/PR bodies and may use a separate `--log` branch, users should ensure appropriate permissions and privacy controls before enabling in sensitive repos."],"error_quality":0.0}