Claude Skills by Popschlock

Starts creating a new Claude Code environment for any project -- interviews the user, generates CLAUDE.md + rules + agents + skills + settings, and validates the result. Supports both single-project environments and multi-area hubs (several related work areas sharing a parent configuration layer). Auto-detects when run inside an existing hub and offers to add a new area. Use when user says "create environment", "set up my project", "generate environment", "I need a Claude setup", "make me an ...

Updates the Harness Generator's own knowledge base (Docs/AgentGuidelines/Topics/, AgentPlaybooks/, tool-registry) -- ingests pending ProvideKnowledge/ docs, then web-researches Anthropic docs and changelogs, incorporates validated findings with source attribution, and prunes superseded or deprecated entries (90-day tool-registry cadence). Supports a local-only mode that ingests ProvideKnowledge/ without web search. Use when the user says "update knowledge", "refresh best practices", "check fo...

Audits an existing Claude Code environment against current best practices, interviews the user about pain points, and implements approved improvements -- including shape conversions (single <-> multi-area hub <-> undeclared siblings). Recommendations are tiered quick wins / medium / large so the user picks what to implement. Use when user says "upgrade environment", "improve my environment", "optimize my setup", "audit my environment for best practices", "make my environment better", "convert...

Validates an existing Claude Code environment against structural correctness and quality standards (file references resolve, frontmatter is valid, size limits hold, routing is complete, hub registry matches disk). Use when user says "validate environment", "check my environment", "is my setup correct", "validate my config", "audit my environment", "run the validator", or "/validate-environment". Do NOT use for creating new environments or for best-practice upgrade recommendations (use /upgrad...

<!-- TEMPLATE ANNOTATION This template defines the /health-check skill that validates environment integrity using a two-layer approach: deterministic script (structural checks) and LLM-based analysis (semantic checks). QUALITY CRITERIA: - Skill description includes 3+ trigger phrases - SKILL.md body under 500 lines - Two-layer validation (deterministic + semantic) - scripts/validate.sh reference for structural checks - PASS/WARN/FAIL output format - Progressive disclosure structure - Specific...

<!-- TEMPLATE ANNOTATION This template defines the /state-load skill that restores session state from a previous /state-save. It follows a 5-step session startup protocol, detects drift between saved and current state, and produces a context restoration briefing. QUALITY CRITERIA: - Skill description includes 3+ trigger phrases - SKILL.md body under 500 lines - Session startup protocol (5 steps) - Drift detection (compare saved vs current) - Context restoration briefing format - Read-only (no...

<!-- TEMPLATE ANNOTATION This template defines the /state-save skill that captures session state across 6 universal categories. It writes JSON for programmatic state and Markdown for human-readable context. QUALITY CRITERIA: - Skill description includes 3+ trigger phrases - SKILL.md body under 500 lines - Progressive disclosure (SKILL.md + scripts/ + references/) - 6-category taxonomy fully specified - JSON output format for programmatic state - Markdown output for human context - Composabili...

<!-- TEMPLATE ANNOTATION This template defines the /update skill that reviews friction logs and proposes environment improvements. It is split into two phases: Analysis (always runs) and Implementation (requires user approval per proposal). QUALITY CRITERIA: - Skill description includes 3+ trigger phrases - SKILL.md body under 500 lines - Analysis phase clearly separated from implementation - Evaluation-driven methodology - Proposal format with evidence, change, classification - Guardrails (m...