$ show glittercowboy/taches-cc-resources
This is a Claude Code plugin and resource library, not a deployable application or data pipeline: 27 slash commands, 9+ autonomous skills, 3 auditor subagents, and extensive prompt-engineering documentation that extend the Claude Code CLI. In production, the system functions as configuration-as-code content consumed by the Claude Code runtime — teaching the assistant how to create executable plans (PLAN.md is the prompt itself), chain meta-prompts, build MCP servers, manage subagent orchestration, run autonomous coding loops (the 'Ralph' technique), and apply iOS/macOS development expertise. The only real executable code is a handful of self-contained scripts: a TypeScript CLI for The Pirate Bay API, Python/TypeScript MCP server templates, project scaffolding shell scripts, and autonomous loop iteration scripts. The dominant architectural pattern is the 'router skill': a SKILL.md entry point with essential principles, an intake gate, a routing table, and progressive disclosure into workflows, references, templates, and scripts — implemented consistently across all skills with pure XML prompt structure and checkpoint-based plan execution. Despite being classified as an application (there is no data-research character — no notebooks, datasets, or pipelines), its substance is largely authored content rather than software. The craft is strong: consistent XML schemas across files, a genuine QA layer (skill-auditor agents), secret hygiene practices, and a well-developed checkpoint/auth-gate protocol for safe automation. However, the repo carries real drift risks: duplicated reference files (research-pitfalls.md, cli-observability.md are copied across skills), dangling references to not-yet-created files, tight coupling to Claude Code's evolving plugin API, version-specific Apple platform guidance that will age, and the included The Pirate Bay skill which depends on a fragile third-party API and presents a content-policy concern. An engineer seeking to reuse this should extract the self-contained templates and scripts (MCP server scaffolding, loop automation) and treat the reference material as opinionated prompt guidance rather than canonical documentation.
The LLM identified 7 files worth highlighting for reuse:
Standalone TypeScript CLI wrapping the apibay.org JSON API. Self-contained (no internal imports), with search, category filtering, sorting, and quality/trust scoring of torrent results. Could be extracted into any project needing a typed CLI wrapper around a JSON web API with minimal modification — demonstrates clean argument parsing and structured output for machine consumption.
Complete, self-contained MCP server template with tool registration, error handling, and lazy initialization patterns. Extractable to bootstrap any new Python MCP server without modification — a genuine reusable scaffold rather than project-specific glue.
Full TypeScript MCP server template with typed tool definitions, response optimization, and error handling. Works standalone and can bootstrap any MCP server project — demonstrates the on-demand-discovery pattern for reducing context usage against large APIs.
Parameterized shell script that scaffolds a Python project using uv for dependency isolation — a recurring infrastructure problem solved idempotently. Extractable to any Python project bootstrap workflow; demonstrates the 'uv --directory' isolation pattern that prevents version conflicts in shared environments.
Shell-based TypeScript project scaffolding companion to the Python setup script. Self-contained and parameterized, solving the recurring problem of reproducible Node/TypeScript project initialization. Reusable across any TypeScript tooling project.
Autonomous coding loop script implementing the 'while :; do cat PROMPT.md | claude; done' technique with added stuck detection, iteration summaries, and remote backup. A robust automation loop abstraction that tolerates failures and self-corrects — easily extracted to drive any repetitive AI-agent execution cycle.
The canonical definition of the repo's router-skill architecture: SKILL.md with essential principles, intake gate, routing table, and references/workflows/templates indexes. Though markdown rather than code, it is the non-obvious architectural pattern that makes the whole library usable — progressive disclosure that keeps context small, an intake gate that prevents premature execution, and semantic XML structure. Directly transplantable to any agent-skill authoring effort.