Context management for agentic coding in Claude Code. The main session keeps its window for judgment, every task runs in a worker with a clean context and a precise brief, state survives compaction, and the record of the work goes to GitHub or Jira instead of your repository.
19 skills · hooks
Python engineering for Claude Code: eight skills (build-web-service, enterprise-design, design-persistence, design-tests, data-engineering, data-analysis, automate-task and tactical-slop-review), four agents (pylens, pep-talk, reviewer and test-engineer), the ty language server, standard-library docs on demand, and hooks that brief each session on the project's Python toolchain and a note whenever a Bash command runs plain python instead of uv run python.
8 skills · 4 agents · 1 MCP server · hooks · LSP
Terraform and IaC repositories in Claude Code: an MCP server that checks modules, digests plans, traces change impact and looks up provider schemas, four subagents, skills, terraform-ls, and hooks that format and check .tf files as Claude works.
8 skills · 4 agents · 1 MCP server · hooks · LSP
Eleven skills for building, hardening and tuning Claude Code agents, skills, hooks, instructions, MCP servers, and loops, plus a vibe-code CLI that needs uv on PATH.
11 skills