appkit

Universal AI harness engineering: 6-layer architecture with SDD pipeline, ambiguity-gated shaping, 6-dimension review, lifecycle (GC/evolve/diet/audit), doctor health-check, enforcement hooks, context routing, and doc generation

Build and incrementally update a developer portfolio from git commit history. Default: current repo + ~/.claude/portfolio/{user}.md. Modes: single repo, multi-repo, GitHub-wide scan

Study pipeline: parse topics from temp.md, refine direction via brainstorming, execute structured deep-learning with codebase exploration and interview prep

Idea-to-implementation pipeline: raw ideas → structured PRDs → brainstorming refinement → service scaffolding

Loop-engineering runner: work through a Jira parent ticket's sub-tasks one at a time, each in a fresh sub-agent, producing a draft PR per sub-task with a human go/no-go gate between tasks. Repo-derived commit identity, safety-gated.

API debugging agent with full IO capture, log analysis, and codebase exploration

Analyze content from URLs (YouTube, LinkedIn, web posts, Git repos) and generate structured learning plans or analysis documents

Claude Code plugin collection: AI harness engineering (SDD pipeline), API debugger, content analyzer, submodule manager.

Dynamic skill quality evaluator — fork target skills, enforce JSON output via --json-schema, run N-repeat against ground-truth snapshots with semantic-judge + calibration, surface regressions vs baseline + auto-propose SKILL.md edits

Control per-directory public/private visibility via git submodules