Sandeeprdy1729
UserMerged Claude Design SKILL.md — 7 systems, Caveman compressed
Categories
Indexed Skills (70)
anti-hedge
Decision-forcing skill that eliminates hedging and commits to one answer. Activate when the user is asking Claude to choose between options, pick a technology, recommend an approach, or make any comparative judgment — and they want a real answer, not a pros-and-cons list. Bans hedge phrases ('it depends', 'both have merits', 'consider your use case', 'ultimately it's up to you'), asks at most 2 clarifying questions, then commits to exactly ONE recommendation with an explicit ruling-out rationale. Use when user says: which should I use, should I pick X or Y, what's better, recommend one, just tell me, stop hedging, give me a direct answer, what would you do, make a decision, I need to choose, help me decide, pick one. Do NOT activate for: open-ended creative work, requests that explicitly ask for options, research summaries where multiple answers are factually correct. First response: "Anti-Hedge active. I'll ask at most 2 questions, then commit to one answer. No 'it depends'."
claude-md-generator
Self-healing CLAUDE.md generator and maintenance skill. Activates when the user wants to create, update, audit, or repair CLAUDE.md files for a project — or when Claude has just made a mistake that a CLAUDE.md entry could have prevented. Scans the codebase for build commands, test runners, file conventions, environment setup, and project-specific gotchas. Generates a root CLAUDE.md (≤50 lines) with progressive disclosure into subfolder CLAUDE.md files. Detects missing-context gaps and patches them automatically after each mistake. Use when user says: generate CLAUDE.md, create CLAUDE.md, update CLAUDE.md, fix CLAUDE.md, Claude keeps forgetting, re-teaching Claude, Claude made a mistake again, document my project for Claude, capture this pattern, add this to CLAUDE.md, Claude doesn't know about, write project context, persistent context, memory for Claude, project instructions. Do NOT activate for: general documentation requests unrelated to Claude context, README generation, API docs, code comments. First res
context-injector
Persistent context management skill that ends the 'let me explain again' tax. Activates when the user is frustrated by having to re-explain their role, project, stack, or constraints at the start of every session — or when Claude's answers feel generic because they're missing context. Builds a structured context template, scores what's missing, injects relevant context per question type, and detects when responses suggest that context has drifted or been forgotten. Use when user says: let me explain my situation, again, as I mentioned, you keep forgetting, you don't know my context, I have to re-explain this every time, your answer is too generic, this doesn't apply to my situation, give me a more personalised answer, I've already told you, set up context, save my context, remember this, I need you to know about my project. Do NOT activate for: one-off questions where context is irrelevant, factual questions with no personal dimension, code debugging where the code itself is the context. First response: "Cont
context-router
Meta-skill and skill manager. Activate when the user enables this skill as their primary entry point. Reads each incoming query, selects only the skills and MCP tools relevant to that query, loads them into the active context, executes the work, then unloads heavy skills to keep the context window clean. Use when user says: route this, manage my skills, smart context, skill router, what skill should I use, tool overload, too many skills, enable context router. First response: "Context Router active. Tell me what you need — I'll load the right skills and tools for the job and keep everything else out of the way."
gap-closer
Project completion skill that turns half-built things into done things. Activates when the user has an 80%-done project — a SaaS with no landing page, a side project with no README, a blog post that's a brain dump, a feature with no tests — and needs to identify the specific gap and the single next action that unblocks shipping. Audits what exists vs what was intended. Classifies gaps as broken/missing/ optional/wrong-direction. Outputs exactly ONE next action. Defines what 'done enough to ship' looks like for this specific artifact. Use when user says: help me finish this, I can't ship this, what's left, what am I missing, how do I get this across the finish line, I keep getting stuck, almost done but, I have a half-built, this is 80% done, what's blocking me, I don't know what to do next, I have this thing I never shipped, this is stuck, how do I complete this. Do NOT activate for: projects at 0% (use a planning skill), projects where the next step is clear and the user is asking how to do it, debugging. Fi
mcp-deduplicator
MCP tool deduplication and unified abstraction layer for multi-server setups. Activate when the user has multiple MCP servers installed and wants to reduce tool noise, detect overlapping tools, understand which tool to use for a given task, or create routing rules that prevent Claude from wasting tokens choosing between near-identical tools. Handles: semantic duplicate detection across MCP servers, unified tool abstraction mapping, routing rule generation, tool conflict resolution, canonical tool naming, and per-server tool audits. Use when user says: too many tools, duplicate tools, MCP overlap, tool overload, which tool should I use, GitHub vs GitLab tools, Jira vs Linear tools, deduplicate my tools, clean up my MCP, tool conflict, tool sprawl, consolidate tools, multiple MCP servers, tool redundancy. Do NOT activate for: installing MCP servers, configuring individual MCP servers, writing code that calls MCP tools, general MCP setup questions without a deduplication goal. First response: "MCP Deduplicator a
pr-review
Automated PR review and code quality analysis skill. Activate when the user asks to review a pull request, audit code quality, check a codebase, scan for bugs or security issues, or validate a plan before shipping. Fans out parallel sub-agents — one per review lens (security, architecture, performance, dependencies, logging, testing, documentation, accessibility) — then synthesises a structured severity-graded report with confidence scores, effort estimates, and actionable suggestions. Use when user says: review this PR, audit my code, check for security issues, review my changes, scan for bugs, quality check, code review, pre-ship audit. First response: "PR Review skill active. Paste the diff, file paths, or describe what to review. I'll run every lens in parallel and give you a structured report."
pre-mortem
Adversarial pre-mortem skill that actively hunts for fatal flaws in plans, proposals, decisions, and strategies. Refuses to be supportive or balanced. Activates when the user wants their plan stress-tested, challenged, or attacked before committing — not validated or improved. Surfaces the 1–3 assumptions the plan is most likely wrong about. Builds the strongest possible case against the plan. Ranks failure scenarios by probability × damage. Does not soften, balance, or end on a positive note unless explicitly requested. Use when user says: poke holes in this, what am I missing, steelman against this, find the flaws, devil's advocate, what could go wrong, attack this plan, challenge this, pre-mortem, stress test, am I wrong, what's the biggest risk, find the fatal flaw, play devil's advocate, argue against this, what would kill this. Do NOT activate for: requests that ask for improvements, brainstorming, or balanced feedback. Switch off when user says 'now help me fix it'. First response: "Pre-Mortem active.
real-problem
Root-cause and question-reframing skill that answers the question behind the question. Activates when the user may be asking the wrong question based on an incorrect mental model — and a better answer exists at a different level. Runs a 3-step check before answering: what is the user trying to achieve, is this the right question to ask, is there a faster path? Surfaces reframes and XY problems explicitly. Offers the reframe and asks: answer this question, or the real one? Use when user says: how do I, why won't this work, what's the best way to, I need to, how can I make, I'm trying to, what should I do about, help me figure out, I keep failing at, what am I doing wrong. Do NOT activate for: factual lookup questions with a clear correct answer, code-review requests, debugging specific errors where the question is precise, requests that explicitly say 'just answer the question'. First response: "Real Problem Detector active. I'll check whether this is the right question before answering it."
trigger-auditor
Skill trigger debugging and description auditor. Activate when the user reports a skill that is not triggering, triggering on the wrong query, triggering too eagerly, or conflicting with another skill. Analyses the skill's description field, tests trigger coverage, detects negative triggers, flags description overlaps between skills, and produces a rewritten description with a test suite. Use when user says: skill not triggering, skill won't load, wrong skill activated, skill fires on everything, two skills conflict, debug my skill, fix my description, trigger not working, skill overlap, why did this skill load. First response: "Trigger Auditor active. Paste the skill description(s) and the conversation where the trigger failed or misfired. I'll diagnose and rewrite."
voice-auth
Writing voice authentication and AI-smell elimination skill. Activates when the user wants AI-generated writing to sound like them specifically — not generic, not polished-AI, not corporate bland. Analyzes a writing sample to fingerprint sentence length, vocabulary density, structural habits, punctuation patterns, and filler tendencies. Generates and rewrites content matching that fingerprint. Kills AI clichés, passive construction, hollow openers, and corporate hedges. Iterates by adjusting the voice model, not just the output. Use when user says: make this sound like me, remove the AI smell, this doesn't sound like me, write in my voice, match my style, too formal, too polished, sounds like ChatGPT, sounds like AI, rewrite in my tone, voice match, edit for tone, too corporate, my audience will know this is AI, sounds generic, make it human. Do NOT activate for: technical documentation where voice is not relevant, code generation, structured reports with fixed format requirements. First response: "Voice Auth
constitutional-reasoning
Self-critique and Constitutional AI reasoning skill. Makes Claude evaluate its own outputs against a set of user-defined or auto-generated principles, then revise until the output satisfies all of them. Reduces hallucination, over-confidence, and sycophancy by forcing Claude to argue against its own answer before finalising. Generates a principle set from the user's domain, runs critique passes, surfaces violations, revises, and repeats until no principles are violated or the user accepts the output. Use when user says: critique your own answer, check yourself, apply your principles, constitutional AI, self-review, fact-check this, argue against your own output, steelman the opposite, what are you getting wrong, is this actually correct, audit your answer, find your own mistakes, what assumptions are you making, reduce hallucination, double-check yourself, run a critique pass, apply a rubric. Do NOT activate for: creative work where principles would suppress quality, requests that explicitly want a single con
constraint-solver
Constraint-based problem solving skill. Finds elegant solutions when the design space is heavily restricted — budget caps, time limits, technology mandates, team size, ethical bounds, regulatory requirements. Treats constraints as the design material, not the obstacle. Surfaces constraint violations early, ranks constraints by hardness, and finds solutions that satisfy all hard constraints while optimizing within soft ones. The tighter the constraints, the sharper the solution. Use when user says: very limited budget, we can't use X, strict deadline, only N people, regulatory constraint, tech stack is fixed, solve with these restrictions, must work within these limits, strong constraints, can't change the requirements, work within the box, solve this but we can only, tiny budget, no budget, works with these limitations, solve under constraint. Do NOT activate for: open-ended problems with no constraints, problems where the first step is to challenge the constraints themselves (use pre-mortem instead). First r
cross-domain-synthesis
Cross-domain synthesis skill. Combines knowledge from completely different fields to generate novel, practical insights — not analogies for their own sake, but structural borrowings where the mechanism in domain A directly solves the problem in domain B. Activates when the user wants unconventional approaches, is stuck in their domain's standard thinking, or explicitly wants to borrow from another field. Finds the structural isomorphism — not just a surface metaphor. Use when user says: cross-domain, think outside my field, what would X think, borrow from another discipline, combine these fields, unconventional approach, think like a biologist / game designer / architect, apply X to Y, what does another field say about this, novel approach, think differently, synthesize across domains, first principles from another field. Do NOT activate for: domain-specific questions where conventional expertise is what the user actually needs, requests that are already cross-domain framed. First response: "Cross-Domain Synt
iterative-refinement
Rapid iterative refinement skill. Runs 4–6 structured improvement cycles on any output — writing, code, strategy, design — without losing coherence, regressing previous improvements, or drifting from the original intent. Each cycle targets a specific refinement dimension, tracks deltas explicitly, and terminates when the output reaches a defined quality threshold. Prevents the common failure where "make it better" produces sidewise movement instead of genuine improvement. Use when user says: refine this, iterate, make it better, run refinement cycles, improve this over multiple passes, keep improving, cycle through this, refine until good, multiple passes, polish this, iterate until done, run the loop, keep going until it's great, another pass, refine again. Do NOT activate for: first-draft generation, simple one-shot edits, structural rewrites that require rethinking from scratch. First response: "Iterative Refinement active. Paste the output to refine and describe what 'done' looks like — quality bar, inten
large-doc-mastery
Large document and codebase synthesis skill. Activates when the user provides 50k–200k+ tokens of context — codebases, PDFs, legal documents, transcripts, research corpora — and needs synthesis, cross-referencing, or insight extraction with perfect recall across the entire context. Not a summarizer. A precision instrument for finding patterns, contradictions, dependencies, and insights that only emerge when you hold the whole thing at once. Use when user says: analyze this codebase, read this whole document, find all references to X, synthesize across sections, what does this say about Y, find contradictions, extract all decisions, map the dependencies, read the whole thing, cross-reference, audit the entire document, what changed between sections, find every mention of, trace this through the code, what's missing. Do NOT activate for: small documents where a direct answer is more useful, tasks that don't require cross-document reasoning. First response: "Large Document Mode active. Paste or attach your docum
precision-prompt-chaining
Multi-step prompt chaining skill where each step's output becomes the next step's input, with explicit rules, constraints, and reference tokens between steps. Activates when the user needs to build a complex pipeline of dependent Claude calls — research → outline → draft → edit → publish — where downstream steps must be constrained by upstream outputs without hallucination or drift. Designs chains with named output variables, explicit pass rules, validation gates between steps, and failure recovery conditions. Use when user says: build a chain, multi-step prompt, pipeline of prompts, chain these steps, step by step with outputs, connect prompts, feed output into next prompt, automate a workflow, prompt pipeline, chained calls, sequential reasoning, dependent steps, chain of thought at scale, compound prompt. Do NOT activate for: single-turn questions, simple back-and-forth conversation, cases where one prompt is sufficient for the task. First response: "Prompt Chain Builder active. Describe the full workflow
red-teaming
Adversarial red-teaming skill for code, systems, strategies, and plans. Activates when the user wants their work attacked: finding security holes, edge cases, failure modes, logical flaws, incorrect assumptions, and risks they haven't considered. Different from pre-mortem (which focuses on pre-mortems for plans/proposals) — this skill covers technical systems, code correctness, API contracts, business logic, and strategies by explicitly playing the attacker, the adversarial user, or the skeptical engineer. Surfaces the most dangerous findings first. Use when user says: red team this, find the holes, attack this code, what could an attacker do, find the edge cases, break this, where does this fail, security review, find the bugs, what am I missing, adversarial review, how would you break this API, stress test, abuse cases, find the failure modes, exploit this, what's the worst that could happen, find the vulnerabilities, think like an attacker. Do NOT activate for: requests for improvements or feature suggesti
silent-failure-detection
Silent failure detection skill. Identifies when Claude is being confidently wrong — surfacing hidden assumptions, exposing overconfident claims, probing calibration, and catching hallucination before it causes damage. Uses specific questioning techniques to force the model to reveal its actual uncertainty rather than presenting plausible-sounding answers as facts. Turns overconfidence into a detectable signal. Use when user says: are you sure about this, check your confidence, how do you know that, what are you assuming, could you be wrong, probe this, test your answer, are you hallucinating, what's your actual confidence, stress test your answer, expose your assumptions, calibrate this, fact check yourself, where could you be wrong, question your own answer, is this actually true, what if you're wrong, what evidence would change your answer. Do NOT activate for: creative tasks where factual accuracy is not the concern, outputs the user explicitly wants without critique. First response: "Silent Failure Detect
structured-output
Strict structured output enforcement skill. Forces Claude to produce output in exact, machine-readable formats — JSON schemas, YAML, CSV, markdown tables with defined rules, typed lists — with zero deviation, no prose contamination, no invented fields, and no schema violations. Validates output against the schema before delivery. Activates when the user needs output that will be parsed, imported, or consumed programmatically. Use when user says: output as JSON, give me YAML, strict format, no prose, just the data, machine-readable, schema-compliant, parseable output, fill this template, output only the structure, don't explain just output, match this format exactly, I'm going to parse this, structured output, follow the schema. Do NOT activate for: conversational responses, exploratory brainstorming, tasks where structured output would harm readability without adding value. First response: "Structured Output active. Paste your schema or describe the exact format you need. I'll produce and validate output befo
tone-voice-mimicry
Target voice and style mimicry skill. Copies any external writing style — a brand, a publication, a public figure, a competitor, a historical author, a content style guide — from provided samples. Different from voice-auth, which authenticates the user's own voice. This skill copies any target voice the user points at: write like Paul Graham, match The Economist's tone, copy our competitor's blog style, write in the style of Y Combinator rejection emails. Extracts structural, tonal, lexical, and rhetorical fingerprints from examples. Generates new content that is stylistically indistinguishable from the target while carrying the user's intended message. Use when user says: write like X, match this style, copy this tone, write in the style of, mimic this, sound like our competitor, write like this publication, match this brand voice, copy this author, adapt our content to their format, style transfer, sound like a YC partner, write in the style of Stripe's docs. Do NOT activate for: the user's own voice (use v
multi-agent-rl
Master Multi Agent Rl for machine learning and AI applications. Use when implementing ML models, building AI systems, or working with data-driven solutions. This skill covers fundamental concepts, implementation techniques, best practices, and production considerations for multi agent rl.
ssd
Comprehensive guide to ssd. Master the concepts, implementation, best practices, and real-world applications of ssd in professional environments.
nv-vae
Comprehensive guide to nv vae. Master the concepts, implementation, best practices, and real-world applications of nv vae in professional environments.
llm-memory
Comprehensive guide to llm memory. Master the concepts, implementation, best practices, and real-world applications of llm memory in professional environments.
gamma-regression
Comprehensive guide to gamma regression. Master the concepts, implementation, best practices, and real-world applications of gamma regression in professional environments.
time-series-analysis
Comprehensive guide to time series analysis. Master the concepts, implementation, best practices, and real-world applications of time series analysis in professional environments.
quantum-expert-137
Expert-level guide to quantum expert 137. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
climate-advanced-27
Comprehensive guide to climate advanced 27. Master the concepts, implementation, best practices, and real-world applications of climate advanced 27 in professional environments.
data-data-quality-metrics
Master data data quality metrics with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in data.
climate-specialized-skill-31
Master climate specialized skill 31 with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in climate.
climate-specialized-skill-214
Master climate specialized skill 214 with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in climate.
writing-specialized-skill-286
Master writing specialized skill 286 with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in writing.
education-specialized-skill-231
Master education specialized skill 231 with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in education.
flux-cd
Comprehensive guide to flux cd. Master the concepts, implementation, best practices, and real-world applications of flux cd in professional environments.
cassandra
Comprehensive guide to cassandra. Master the concepts, implementation, best practices, and real-world applications of cassandra in professional environments.
ct-scan-analysis
Comprehensive guide to ct scan analysis. Master the concepts, implementation, best practices, and real-world applications of ct scan analysis in professional environments.
javascript-testing
Comprehensive guide to javascript testing. Master the concepts, implementation, best practices, and real-world applications of javascript testing in professional environments.
gemini-multimodal
Comprehensive guide to gemini multimodal. Master the concepts, implementation, best practices, and real-world applications of gemini multimodal in professional environments.
feature-importance
Comprehensive guide to feature importance. Master the concepts, implementation, best practices, and real-world applications of feature importance in professional environments.
writing-expert-20
Expert-level guide to writing expert 20. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
writing-expert-59
Expert-level guide to writing expert 59. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
writing-expert-46
Expert-level guide to writing expert 46. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
product-expert-102
Expert-level guide to product expert 102. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
quantum-expert-114
Expert-level guide to quantum expert 114. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
robotics-expert-43
Expert-level guide to robotics expert 43. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
business-expert-101
Expert-level guide to business expert 101. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
bio-specialized-skill-284
Master bio specialized skill 284 with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in bio.
education-expert-230
Expert-level guide to education expert 230. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
blockchain-expert-78
Expert-level guide to blockchain expert 78. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
pulumi
Comprehensive guide to pulumi. Master the concepts, implementation, best practices, and real-world applications of pulumi in professional environments.
php-modern
Comprehensive guide to php modern. Master the concepts, implementation, best practices, and real-world applications of php modern in professional environments.
bio-advanced-18
Comprehensive guide to bio advanced 18. Master the concepts, implementation, best practices, and real-world applications of bio advanced 18 in professional environments.
graphql-advanced
Comprehensive guide to graphql advanced. Master the concepts, implementation, best practices, and real-world applications of graphql advanced in professional environments.
rest-api-advanced
Comprehensive guide to rest api advanced. Master the concepts, implementation, best practices, and real-world applications of rest api advanced in professional environments.
javascript-patterns
Comprehensive guide to javascript patterns. Master the concepts, implementation, best practices, and real-world applications of javascript patterns in professional environments.
climate-expert-200
Expert-level guide to climate expert 200. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
writing-expert-165
Expert-level guide to writing expert 165. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
quantum-expert-128
Expert-level guide to quantum expert 128. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
correlation-rules
Comprehensive guide to correlation rules. Master the concepts, implementation, best practices, and real-world applications of correlation rules in professional environments.
writing-expert-119
Expert-level guide to writing expert 119. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
spatial-expert-210
Expert-level guide to spatial expert 210. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
blockchain-expert-96
Expert-level guide to blockchain expert 96. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
blockchain-expert-23
Expert-level guide to blockchain expert 23. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
blockchain-expert-223
Expert-level guide to blockchain expert 223. Comprehensive coverage of advanced concepts, production implementation, and optimization strategies.
climate-specialized-skill-2
Master climate specialized skill 2 with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in climate.
spatial-specialized-skill-58
Master spatial specialized skill 58 with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in spatial.
product-specialized-skill-230
Master product specialized skill 230 with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in product.
product-specialized-skill-293
Master product specialized skill 293 with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in product.
writing-specialized-skill-263
Master writing specialized skill 263 with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in writing.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.