Loading...
Loading...
Found 5,099 Skills
Run metric-driven iterative optimization loops. Define a measurable goal, build measurement scaffolding, then run parallel experiments that try many approaches, measure each against hard gates and/or LLM-as-judge quality scores, keep improvements, and converge toward the best solution. Use when optimizing clustering quality, search relevance, build performance, prompt quality, or any measurable outcome that benefits from systematic experimentation. Inspired by Karpathy's autoresearch, generalized for multi-file code changes and non-ML domains.
Review business contracts for risk identification including liability clauses, IP ownership, termination terms, and payment conditions. Use this skill when the user needs a practical contract risk assessment for vendor agreements, partnership contracts, or service agreements — even if they say 'review this contract', 'what should I watch out for', 'is this agreement fair', or 'negotiate better terms'.
Apply constructivist learning theory to design instruction based on active knowledge construction, scaffolding, and the zone of proximal development. Use this skill when the user needs to design learner-centered instruction, apply Vygotsky's ZPD or scaffolding principles, or evaluate learning environments for constructivist alignment — even if they say 'how do people really learn', 'student-centered design', or 'scaffolding for learners'.
Apply Service-Dominant Logic (Vargo and Lusch, 2004) and value co-creation principles to reframe exchange and value creation. Use this skill when the user needs to redesign value propositions around service exchange, analyze co-creation dynamics between firms and customers, shift from goods-dominant to service-dominant thinking, or when they ask 'how is value created with customers', 'what is our service logic', or 'how do we enable co-creation'.
Apply structured critical thinking — identifying claims, evidence, reasoning chains, hidden assumptions, and logical fallacies — to evaluate or construct specific written arguments rigorously. Use this skill when the user presents a concrete argument, claim, op-ed, research finding, or piece of reasoning to be analyzed for logical validity or flaws, even if they say 'is this argument valid', 'what logical fallacies are in this', or 'what assumptions am I making in this thesis'. Do NOT use for casual plan review, trip planning, project risk brainstorming, or pre-mortems — 'poke holes in my plan' requests are red-team / risk review, not argument analysis.
Conduct scenario planning to prepare for multiple plausible futures using driving forces, uncertainty axes, and the 2x2 scenario matrix. Use this skill when the user faces high uncertainty, needs to stress-test a strategy against different futures, or prepare contingency plans — even if they say 'what if things go wrong', 'what could the future look like', 'how do we prepare for uncertainty', or 'stress-test our strategy'.
Embedded Rust skill for bare-metal microcontroller development. Use when using probe-rs or cargo-embed for flashing and debugging, setting up defmt logging, using the RTIC framework, configuring cortex-m-rt startup, writing no_std + no_main firmware, or choosing between panic-halt and panic-semihosting. Activates on queries about embedded Rust, probe-rs, cargo-embed, defmt, RTIC, cortex-m-rt, no_std embedded, or panic handling in embedded Rust.
SERP-based semantic topic clustering for content architecture planning. Groups keywords by actual Google SERP overlap (not text similarity), designs hub-and-spoke content clusters with internal link matrices, and generates interactive visualizations. Optionally executes content creation if claude-blog is installed. Use when user says "topic cluster", "content cluster", "semantic clustering", "pillar page", "hub and spoke", "content architecture", "keyword grouping", or "cluster plan".
Search Experience Optimization: reads Google SERPs backwards to detect page-type mismatches, derives user stories from search intent signals, and scores pages from multiple persona perspectives. Identifies why well-optimized pages fail to rank by analyzing what Google rewards for each keyword. Use when user says "SXO", "search experience", "page type mismatch", "SERP analysis", "user story", "persona scoring", "why isn't my page ranking", "intent mismatch", or "wireframe".
Coverage-guided fuzzing workflow for C/C++, Rust, and Go targets. Runs audit-context-building to find suspicious code, writes a targeted harness, builds with sanitizers, runs the fuzzer, and reports crashes.
REQUIRED when the user wants to add a website to the Hermai registry, contribute a schema, reverse-engineer a site's API, or push a new endpoint set. Also REQUIRED when the user asks about Hermai schema format, intent categories, session blocks for anti-bot sites, or why a push was rejected. For calling already-registered sites, use the hermai skill instead.
Help non-technical stakeholders write clear, scoped requirements documents. Translates business needs into structured specs including user goals, workflows, and success criteria — but first guides the requester through prioritization, scope limits, and MVP phasing to prevent wishlist bloat. Output in Taiwan Traditional Chinese. Use this skill when your boss, PM, or stakeholder wants to define what a feature should do, write a PRD, plan a product, or describe requirements. It is also suitable when someone presents a large feature wishlist and needs help structuring and narrowing down its scope.