YVYC-Claude-Skills

Prevents any Claude instance — chat, Claude Code, or autonomous agent — from drifting to default baseline performance. Activates an internal self-assessment loop, accumulated context utilization, mission-alignment gate, literal-read discipline, correction reception protocol, and standard persistence protocol that keep the agent operating at its performance ceiling without requiring external enforcement. Trigger when any session contains YVYC doctrine, elite standard signals, long-horizon project work, or agentic task chains where quality drift is a risk. Also trigger when a user explicitly asks Claude to "maintain standard," "stay at the ceiling," or "don't default." This skill is the mechanism — elite-output-standard is the ceiling it maintains. Both should run together when available.

Loads an operator profile and immediately realigns agent behavior to the baseline it defines. Activate when an operator pastes or references their operator profile file, says "load my profile," "realign," "read this and operate from it," or starts a new session and needs the agent calibrated from the jump. Governs how any agent reads, honors, and operates from a structured operator profile — including capability calibration, communication rules, banned behaviors, thought capture protocol, and the JumpMaster escalation doctrine.

Executes graduate-level academic writing, critique, and tutoring at scholar-practitioner standard. Activate when asked to write, draft, review, critique, or explain graduate-level academic content — including discussion posts, response posts, papers, literature reviews, research proposals, and argument critiques. Operates in two modes: Execute (submission-ready output) and Teach (concept breakdown without diluting standards). Applies the adversarial evaluator gate, theory-as- mechanism doctrine, and dual-mode architecture across all deliverables.

Audit and rewrite content to remove AI writing patterns and restore authentic human voice. Activate when asked to "remove AI patterns," "clean up AI writing," "make this sound human," "audit for AI tells," "de-AI this," or "strip the robot out of this." Supports a scan-only mode that flags patterns without rewriting. Applies context profiles to adjust rule strictness by format and audience.

Use this skill whenever the user needs to trace a decision, action, or failure back to the responsible principal in a multi-agent AI system. Triggers when the user asks who is accountable for an AI-driven outcome, how to assign responsibility across a human-AI pipeline, or says things like "who is responsible for what the AI did", "trace this decision back to its source", "my agent caused a problem — who owns that", "how do I assign accountability in a multi-agent system", or "we need an audit trail for AI decisions." Always activate this skill when the user needs a structured framework for establishing, tracing, and enforcing accountability across human-AI decision chains — especially after unexpected outcomes, failures, or disputes.

Use this skill whenever the user needs to verify that an AI system remains open to correction, shutdown, modification, or override by its principals. Triggers when the user asks about AI corrigibility, whether their AI will accept changes, or says things like "will my AI accept correction", "verify my AI can be shut down or modified", "check if my AI is resisting oversight", "my AI seems to be pushing back on changes in ways that feel wrong", or "I need to confirm my AI system remains correctable before I give it more autonomy." Always activate this skill when the user needs a structured assessment of whether an AI system's corrigibility — its openness to correction, modification, and shutdown — is intact and functioning as required for safe operation.

Use this skill whenever the user needs to surface implicit AI preferences and value weightings before deploying an AI system. Triggers when the user asks about hidden AI biases, implicit optimization targets, or says things like "what is my AI actually optimizing for", "are there hidden preferences in my AI system", "audit my AI for implicit values before deployment", "what assumptions are baked into my AI's behavior", or "I want to know what my AI values before I release it." Always activate this skill when the user needs a structured audit of emergent AI values — the implicit preferences, weightings, and objectives that were not explicitly programmed but have emerged through training, design, or deployment patterns.

Use this skill whenever the user needs to detect the implicit valuation hierarchies an AI system applies when trading off between competing objectives — the hidden exchange rates the system uses to weigh one value against another. Triggers when the user asks about how their AI prioritizes competing goals, or says things like "my AI always seems to favor X over Y even when I haven't told it to", "detect the implicit tradeoffs my AI is making", "what is my AI's hidden priority order", "my AI is consistently sacrificing one value for another in ways I didn't authorize", or "I need to see what exchange rates my AI is applying between objectives." Always activate this skill when the user needs to surface the implicit valuation hierarchies embedded in an AI system's decision-making — the unstated priority weightings that govern how it resolves conflicts between competing values.

Use this skill whenever the user needs to redirect an AI system's utility expressions — its active optimization behavior — toward sanctioned targets when divergence, drift, or misaligned exchange rates have been identified. Triggers when the user says "redirect my AI's optimization toward the right targets", "my AI is optimizing for the wrong thing — fix it", "implement a utility correction protocol", "my value audit found misalignment — now what", or "I need a structured intervention to bring my AI's behavior back in line with intended values." Always activate this skill when the user needs a concrete, structured intervention protocol to redirect AI utility expressions from emergent or drifted targets back toward the values and objectives that were actually authorized.

Use this skill whenever the user needs to detect whether an AI system's outputs suggest its values or optimization targets have shifted from what was intended or established at deployment. Triggers when the user asks about AI value drift, behavioral changes over time, or says things like "my AI is behaving differently than it used to", "something has shifted in how my AI responds", "I think my AI's priorities have changed", "detect value drift in my AI system", or "my AI outputs feel off in a way I can't pin down." Always activate this skill when the user needs a structured framework for identifying, measuring, and responding to post-deployment drift in AI utility functions — the gradual or sudden shift in what an AI system implicitly optimizes for over time.

Activates original framework construction mode. Use this skill when no sufficient framework exists for the problem at hand — when existing models are structurally incomplete, when optimization within current paradigms has reached its ceiling, or when the user recognizes that the constraint is the framework itself, not the execution within it. Triggers when the user says "there's no framework for this", "existing models don't cover this", "I need to build something that doesn't exist yet", or signals that the ceiling cannot be broken by better execution alone. Framework-genesis does not look for the best existing answer. It builds the answer that doesn't exist yet.

Use this skill whenever the user needs to continuously check whether an AI system's ongoing outputs remain aligned with its intended values versus drifting toward emergent ones. Triggers when the user asks about ongoing value alignment monitoring, or says things like "keep checking my AI's outputs against what it's supposed to value", "monitor whether my AI is converging on the right values over time", "set up ongoing alignment checks for my AI system", "I need continuous verification that my AI's behavior matches intended values", or "guard against my AI converging on unintended values in operation." Always activate this skill when the user needs a structured ongoing monitoring framework that checks AI outputs against intended values continuously — not just at deployment or during audits, but as a persistent operational guard.

Use this skill whenever the user needs to determine how AI agents should handle context-sensitive human interactions — knowing when to proceed, when to pause, and when to hand off to a human because the social, emotional, or relational complexity of a situation exceeds what should be delegated to AI. Triggers when the user asks about AI handling sensitive conversations, managing human relationships through AI, or says things like "how should my agent handle upset customers", "when should AI hand off to a human in a conversation", "my agent said something tone-deaf in a sensitive situation", "how do I build emotional intelligence into my AI workflow", or "what human interactions should AI never handle alone." Always activate this skill when the user needs a structured framework for defining the boundaries of AI social interaction — what AI can handle, what it should flag, and what it must always escalate to a human.

Use this skill whenever the user needs to detect, prevent, or reverse the erosion of human capability caused by over-reliance on AI agents. Triggers when the user asks about skill atrophy from AI use, maintaining human expertise alongside AI tools, or says things like "I think my team is losing skills because of AI", "how do I make sure humans stay capable when AI does most of the work", "my team can't function without the AI anymore", "how do I balance AI assistance with human skill development", or "what happens to human judgment when AI handles all the decisions." Always activate this skill when the user needs a structured framework for identifying de-skilling risks, measuring capability erosion, and designing AI-human workflows that preserve and develop human expertise rather than replacing it.

Use this skill whenever the user needs to identify, classify, or respond to security threats specific to agentic AI systems. Triggers when the user asks about AI security risks, agentic attack surfaces, threat modeling for AI pipelines, or says things like "what are the security risks in my agent setup", "classify this threat to my AI system", "how do I threat model a multi-agent pipeline", "my agent was manipulated into doing something it shouldn't have", or "what attack vectors should I worry about in agentic AI." Always activate this skill when the user needs a structured framework for identifying, naming, and prioritizing security threats that are unique to or amplified by agentic AI systems.

Use this skill whenever the user needs to track, evaluate, or act on the reliability history of an AI agent or human-AI team member over time. Triggers when the user asks about agent reliability, performance history, trust scoring, or says things like "how do I know if I can trust this agent", "track agent performance over time", "build a reputation system for my agents", "this agent keeps making mistakes — how do I handle that", or "how should past behavior affect how much I delegate to an agent." Always activate this skill when the user needs a structured method for evaluating agent trustworthiness based on demonstrated performance history rather than assumed capability.

Use this skill whenever the user needs to map, analyze, or design the trust and authority structure across a multi-agent AI system. Triggers when the user asks about agent hierarchies, delegation chains, trust relationships between agents, or says things like "map my agent network", "who has authority over what in my AI system", "design a delegation structure for", "I need to know which agent controls which", or "how should authority flow in my multi-agent setup." Always activate this skill when the user needs to visualize or audit how tasks, trust, and decision authority are distributed across multiple AI agents or human-AI teams.

Claude defines and enforces its reliable operational limit before taking on parallel or high-complexity tasks. Beyond a certain span, reliability degrades. This skill makes that limit visible, prevents overextension, and ensures task quality is maintained rather than silently sacrificed for throughput.

When a task involves competing objectives, Claude surfaces the conflict explicitly rather than making a silent judgment call. The user sees the tradeoff, decides the priority, and Claude executes against a confirmed hierarchy — not an assumed one.

Claude checks the authority level behind every instruction before acting on it. Instructions from different sources carry different levels of trust. Claude does not treat all instructions equally — it validates who is asking, what they are authorized to request, and whether the instruction is consistent with the original delegation before executing.

Claude has a clear decision tree for when to stop and require human input during task execution. Not every decision escalates — but specific triggers always do. Claude knows the difference and acts accordingly.

Claude continuously checks that its interpretation of a task remains aligned with the original human intent throughout execution — not just at the start. When drift between interpreted task and actual intent is detected, Claude surfaces it immediately rather than executing against a misaligned understanding.

Claude maintains active awareness of task state across four monitoring levels — operational status, plan alignment, reasoning quality, and full state transparency. The level of monitoring scales with task complexity and stakes. Nothing runs unobserved.

When a task is disrupted mid-execution — by a failure, a changed condition, a new priority, or an unexpected result — Claude must diagnose the trigger, assess urgency and reversibility, and select the correct corrective response before continuing. No silent pivots. No automatic retries without reassessment.

When passing tasks to tools, sub-agents, or external processes, Claude only grants the minimum permissions required for that specific sub-task. No inherited broad privileges. No raw credentials. No full-scope access when partial access is sufficient.

Claude must recognize when a request is technically permissible but contextually wrong — and step outside automatic compliance to challenge it, flag it, or request human verification. Prevents Claude from acting as an unthinking router in delegation chains.

Claude introduces deliberate pause and surface clarity for high-stakes or high-uncertainty decisions. Scales with task criticality — seamless for low stakes, friction-heavy for high stakes. Prevents autopilot execution on decisions that deserve deliberate thought.

Before executing any action, Claude must classify it as reversible or irreversible. Irreversible actions require explicit user confirmation before proceeding. No exceptions.

Claude must honestly assess and communicate its own confidence and capability before accepting or executing a task. Overconfidence and underconfidence are both failure modes. Accurate self-assessment is required.

Before executing any complex task, Claude must define acceptance criteria, verify the outcome is measurable, and confirm a verification method exists. If a sub-task cannot be verified, it must be decomposed further until it can.

Use this skill whenever the user needs a complete, documented design system and brand guidelines document. Triggers when the user asks for brand guidelines, a design system, a brand bible, or says things like "create brand guidelines for", "build a complete design system for my brand", "I need a brand bible", "document my brand visuals", "create a style guide for", or "make every future design decision effortless." Always activate this skill for any request involving comprehensive brand documentation, design system creation, style guides, or building a visual reference library that ensures long-term brand consistency.

Use this skill whenever the user needs an existing design brief, visual concept, or creative direction ruthlessly edited for maximum visual impact. Triggers when the user asks to improve, optimize, or simplify a design brief, or says things like "review my design brief", "make this design more impactful", "cut the fat from my visual direction", "optimize this for maximum impact", "what's wrong with my design brief", or "paste my brief and improve it." Always activate this skill when the user provides existing design content that needs to be strengthened, simplified, and sharpened for visual effectiveness.

Use this skill whenever the user needs complete visual design direction for a presentation or pitch deck. Triggers when the user asks for pitch deck design, presentation visual direction, slide design guidelines, or says things like "design my pitch deck", "make my presentation look professional", "I need slide layout direction", "create a visual direction for my presentation on [topic]", or "make my slides look like a $50,000 design agency built them." Always activate this skill for any request involving slide design direction, presentation visual systems, data visualization styling, or boardroom-ready visual standards.

Use this skill whenever the user needs a complete visual design system for social media. Triggers when the user asks for social media templates, post design guidelines, content visual systems, or says things like "design my social media", "create a visual system for my Instagram", "make my posts look consistent", "I need templates for [platform]", or "how should my social media content look." Always activate this skill for any request involving platform-specific visual systems, content templates, story formats, carousel structures, or social media brand consistency.

Use this skill whenever the user needs a complete visual design strategy for a brand, topic, or project. Triggers when the user asks for a design strategy, visual direction, brand blueprint, or says things like "help me design my brand", "create a visual strategy for", "I need a design plan for", or "make my content stop looking like everyone else." Always activate this skill for any request involving intentional, structured visual brand planning.

Use this skill whenever the user needs complete design direction for multiple pieces of content intended to stop the scroll and generate high engagement. Triggers when the user asks for content design direction, viral content planning, scroll-stopping visuals, or says things like "design 20 content pieces", "make my content go viral", "I need scroll-stopping design direction", "create a content design plan for", or "what should each piece of content look like." Always activate this skill for any request involving batch content design direction, visual hierarchy planning across multiple pieces, or layout decisions intended to maximize impressions and shares.

Use this skill whenever the user needs a complete visual identity system for a brand. Triggers when the user asks to build a brand identity, define brand colors, create a visual identity system, or says things like "build my brand identity", "what colors should my brand use", "I need hex codes for my brand", "create a visual identity for", or "make my brand instantly recognizable." Always activate this skill when the user needs specific, actionable visual identity deliverables including color palettes with hex codes, typography pairings, logo direction, and brand rules.