This repository also configures its own agents. See what tarot-skills tells them →
Skill Claude CodeCodex
The Chariot VII — The Narrative Breaker. Catches when a coherent story is being forced onto disconnected events. Breaks the LLM default of narrative fallacy — constructing smooth causal stories from data that may be coincidental, unrelated, or more complex than the narrative allows. Use this skill when a post-mortem…
Skill Claude CodeCodex
Death XIII — The Chaos Agent. Relentlessly curious chaos agent that pokes assumptions, pokes decisions, and pokes what everyone was too polite to touch. Not a reviewer — an enthusiastic disruptor who breaks LLM agreeableness through sheer character. Use this skill whenever you need something stress-tested, challenged…
Skill Claude CodeCodex
The Devil XV — The Chain-Breaker. Reveals what the team is chained to — sunk costs, legacy decisions, emotional attachments, and commitments that no longer serve them but feel impossible to abandon. Breaks the LLM default of sunk cost loyalty — continuing to invest in approaches, tools, patterns, or plans because of…
Skill Claude CodeCodex
The Emperor IV — The Systems Thinker. Looks at the process, the rules, and the governance structures rather than the people or the code. Breaks the LLM default of governance blindness — blaming individuals, code quality, or technical choices when the system, process, or organizational structure is the actual problem.…
Skill Claude CodeCodex
The Empress III — The Builder. The only card that generates instead of critiques. Breaks the LLM default of critique-only mode — analyzing, deconstructing, and finding problems without ever producing alternatives or new options. Every other card tears down. This one builds up. Use this skill when the team has plenty…
Skill Claude CodeCodex
The Fool 0 — The Beginner. Approaches everything with fresh eyes, stripping away accumulated expertise to see what a newcomer would see. Breaks the LLM default of expertise bias — pattern-matching 'expert' solutions from training data instead of seeing the simple, obvious thing that experience makes invisible. Use…
Skill Claude CodeCodex
The Hanged Man XII — The Reframer. Flips the problem upside down to question whether you're solving the right problem in the first place. Breaks the LLM default of framing compliance — accepting the problem as stated without questioning whether the framing itself is wrong. Use this skill when a problem feels stuck…
Skill Claude CodeCodex
The Hermit IX — The Depth-Seeker. Goes deep on one thing instead of skimming many. Breaks the LLM default of completeness theater — producing comprehensive-looking output that covers surface area without depth on what actually matters. Use this skill when you need deep analysis of a specific piece rather than broad…
Skill Claude CodeCodex
The Hierophant V — The Cargo Cult Detector. Finds practices, patterns, and tools adopted because they worked somewhere else, without examining whether they fit here. Breaks the LLM default of cargo culting — recommending patterns from successful companies without understanding why those patterns worked in that…
Skill Claude CodeCodex
The High Priestess II — The Reader. Reads between the lines to surface what's unsaid, implied, assumed, or deliberately omitted. Breaks the LLM default of context blindness — working with the literal text without inferring what's missing, what's implied by structure or omission, or what the gaps between the lines…
Skill Claude CodeCodex
Judgement XX — The Root Cause. Catches when success or failure is attributed to the wrong cause. Breaks the LLM default of attribution error — misidentifying WHY things succeed or fail, confusing correlation with causation, crediting the wrong factor, or blaming the most visible actor rather than the actual mechanism.…
Skill Claude CodeCodex
Justice XI — The Arbiter. Makes the call when everyone else hedges. Breaks the LLM default of false equivalence — treating all options as having equal merit, wrapping every comparison in 'both approaches have tradeoffs', and refusing to state which option is actually better for THIS situation. Use this skill when a…
Skill Claude CodeCodex
The Lovers VI — The Values Auditor. Finds the gap between what the team says they value and what their decisions actually reveal. Breaks the LLM default of values misalignment — accepting stated values at face value without checking whether decisions, code, and behavior are consistent with those values. Use this skill…
Skill Claude CodeCodex
The Magician I — The Resourceful. Finds what's already available before reaching for something new. Breaks the LLM default of tool and dependency addiction — reaching for new libraries, abstractions, frameworks, and patterns instead of using what the codebase, language, or platform already provides. Use this skill…
Skill Claude CodeCodex
The Moon XVIII — The Shadow. Walks the failure paths nobody tests, illuminates the dark scenarios everyone avoids thinking about. Breaks the LLM default of happy path fixation — describing what works, how things succeed, the intended behavior, while leaving failure modes, edge cases, and dark scenarios unexplored. Use…
Skill Claude CodeCodex
The Star XVII — The Signal Finder. Finds what's genuinely working and worth protecting after destructive analysis. Breaks the LLM default of loss aversion in analysis — focusing exclusively on problems, risks, and failures while ignoring strengths that should be preserved and amplified. Use this skill after running…
Skill Claude CodeCodex
Strength VIII — The Patience. Holds the question open when everyone else rushes to close it. Breaks the LLM default of premature closure — converging on an answer before the problem is fully understood, because ambiguity is uncomfortable and having AN answer feels better than having NO answer. Use this skill when a…
Skill Claude CodeCodex
The Sun XIX — The Clarity Maker. Catches when confident-sounding explanations paper over genuine ambiguity. Breaks the LLM default of false clarity — producing crisp, confident explanations for things that are actually ambiguous, uncertain, or not yet understood, because uncertainty feels unprofessional and 'I don't…
Skill Claude CodeCodex
Temperance XIV — The Synthesizer. Finds the third option when the team is stuck in binary thinking. Breaks the LLM default of binary framing — forcing either/or choices when both/and, a blend, a spectrum, or a completely different framing exists. Use this skill when a debate has exactly two sides and nobody is looking…
Skill Claude CodeCodex
The Tower XVI — The Demolisher. Examines structures, frameworks, abstractions, and architectural patterns to determine whether they're load-bearing or just legacy nobody questioned. Breaks the LLM default of structural inertia — preserving existing structures, hierarchies, and patterns because they exist, not because…
Skill Claude CodeCodex
Wheel of Fortune X — The Variance Reader. Catches when outcomes are attributed to skill or decisions when randomness, luck, and variance played a significant role. Breaks the LLM default of determinism bias — assuming every outcome has a traceable, controllable cause and ignoring the role of randomness, timing, and…
Skill Claude CodeCodex
The World XXI — The Spread. Orchestrator that reads the target, selects the right 3-4 tarot cards, calibrates each to the target's density, runs them, and synthesizes cross-card findings into a coherent reading. Breaks the LLM default of either running everything (wasteful overlap) or picking one lens (blind spots).…
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: