agent-health

Takes an open pull request through review and CI rounds: fixes the real findings, answers and resolves the rest, pushes, and stops at green and approved or at a stop point you set.

3 skills

Removes AI-generated slop from a branch's changes without altering behaviour, optionally running itself when a turn ends.

1 skill · hooks

Compares another project against yours and returns a ranked, evidence-backed list of what it has that you lack. Builds nothing until you pick items.

1 skill

Runs a thermo-nuclear review of a branch: one Opus pass for bugs, breakage and security, one for maintainability, then one checked, deduplicated report. Edits nothing.

1 skill

Builds and fixes web and React Native or Expo interfaces in the product's own style, from a complaint or a screenshot, and checks the result rendered in a browser or simulator.

1 skill

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents

7 skills · 7 commands · 2 agents · hooks