Multi-platform AI assistant skills and workflows. Serious engineering. Also fun.
This repository also configures its own agents. See what spellbook tells them →
Command Claude Code
Systematically address PR review comments. Fetches all threads, categorizes by status (acknowledged, silently fixed, unaddressed), and guides user through posting replies and implementing fixes with explicit approval.
Command Claude Code
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.
Command Claude Code
Advanced Code Review Phase 1: Strategic Planning - scope analysis, risk categorization, priority ordering.
Command Claude Code
Advanced Code Review Phase 5: Report Generation - produce final deliverables including Markdown report and JSON summary.
Command Claude Code
Advanced Code Review Phase 3: Deep Review - multi-pass code analysis, finding generation with severity classification.
Command Claude Code
Advanced Code Review Phase 4: Verification - fact-check findings against codebase, remove false positives.
Command Claude Code
Audit test suites for Green Mirage anti-patterns: tests that pass but don't verify behavior.
Command Claude Code
Phases 2-3 and 7 of auditing-green-mirage: systematic line-by-line audit, the Green Mirage Patterns, named assertion shapes, and the fix-verification Test Adversary prompt.
Command Claude Code
Phase 4 of auditing-green-mirage: Cross-test suite-level analysis.
Command Claude Code
Phase 5-6 of auditing-green-mirage: Findings report generation and output.
Command Claude Code
Audit mode for code-review: multi-pass deep-dive with zero-tolerance posture, API hallucination detection, and risk assessment.
Command Claude Code
Feedback mode for code-review: Process received review feedback with categorization, decision rationale, and response templates.
Command Claude Code
Give mode for code-review: Review someone else's code with multi-pass analysis and structured recommendations.
Command Claude Code
Tarot integration for code-review: Roundtable dialogue with archetype personas for all review modes.
Command Claude Code
Create a GitHub issue with proper template discovery and population.
Command Claude Code
Create a pull request with proper template discovery and population.
Command Claude Code
Operator-invoked rule bookkeeping for canonical ## Rules sections produced by /crystallize. Use when accumulated rules need consolidation (overlap merge, redundancy collapse, deprecated-tool retirement). Triggers: '/crystallize-consolidate ', 'consolidate the rules section', 'merge overlapping rules in this file'. NOT…
Command Claude Code
Adversarial review of a crystallized document against its original. Use when crystallize.md invokes pre-delivery verification. Receives original + crystallized documents; returns PASS or FAIL with findings.
Command Claude Code
Transform verbose SOPs into high-performance agentic prompts via principled compression. Use when user says "/crystallize", "compress this prompt", "make this more agentic".
Command Claude Code
Extract, triage, and verify code items for dead code. Part of dead-code- family. Run after /dead-code-setup.
Command Claude Code
Implement dead code deletions with user approval. Part of dead-code- family.
Command Claude Code
Generate dead code findings report with implementation plan. Part of dead-code- family.
Command Claude Code
Git safety and scope selection for dead code analysis. Part of dead-code- family.
Command Claude Code
Decompose text into atomic, independently verifiable claims using FActScore-style analysis. For text and documentation claims only; code claims use inline verification.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: