Skill UI

This skill manages the secure transition of private internal projects to public open-source releases. It executes a three-stage pipeline: Forking (removing secrets), Sanitizing (verifying clean code), and Packaging (generating required documentation like README, setup.sh, and CLAUDE.md). It ensures code safety and readiness before public deployment.

A four-tier memory store for AI assistants that promotes recurring facts from transcripts to project context and persona via deterministic recurrence gates, avoiding CLAUDE.md bloat and repeated corrections. Suitable for projects where agents need durable memory that is only committed after human adoption.

Consent-gated editor for Caveman Learn. Reads ranked token sinks, proposes concrete reductions for heavy context files and repeated blocks, applies them after approval. Use to lower agent token costs, trim heavy CLAUDE.md, offload re-pasted context to cavemem, or distill repeated procedures into a skill.

Secure AI coding agents with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments. Covers Claude Code, Cursor, Copilot, and Codex security implementations including CLAUDE.md configuration, command allowlists, filesystem access controls, and pre-commit hooks for secret scanning.

Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models, reducing token usage while increasing compliance. Ideal for optimizing LLM system prompts and migrating rules between AI tools.

Deep expert in Claude Code - Anthropic's CLI. Maximizes productivity with shortcuts, hooks, MCPs, advanced configurations, workflows, CLAUDE.md, memory, sub-agents, permissions, and ecosystem integration.

Comprehensive guide for configuring and using Claude Code, including CLAUDE.md templates, advanced prompting keywords, debugging tips, and best practices for iterative AI-assisted development.

This skill helps developers create highly focused, folder-specific documentation (`CLAUDE.md` and `AGENTS.md`). It systematically analyzes all files in a target directory to extract project purpose, operational constraints, naming conventions, and critical decisions. This deep context ensures that future AI agents (like Claude or Codex) operate with localized knowledge, preventing them from relying on global, generalized instructions and improving their accuracy in that specific domain.

Reduces token costs by scoping context into directory-level CLAUDE.md files. Sets up hierarchical memory, tracks savings via dashboard, routes agents to sub-contexts, and provides audit and insights commands.

Maps, explains, and lints repository-scoped coding-agent instruction files such as AGENTS.md, CLAUDE.md, Copilot and Cursor rules. Run local read-only scans to inventory instructions, audit recursive imports, and export JSON or SARIF diagnostics before changing code.

Detects which APIs of a Python project's pinned dependencies changed after a coding model's training cutoff, locates the code using them, and writes short evidence-tagged notes into AGENTS.md or CLAUDE.md.

This skill humanizes natural-language memory files like CLAUDE.md, AGENTS.md, and docs by removing AI-isms and adding burstiness. It offers deterministic and LLM modes, preserves code blocks, URLs, paths, and headings, and creates backups. Ideal for cleaning up AI-generated content in configuration files and documentation.