Search through memory files - learnings, decisions, observations, questions, episodes, reflections. Use when looking for past insights, recalling why a decision was made, finding what was learned about a topic, or searching conversation history. Trigger words: memory, remember, recall, search, find, when did, what did I learn, past.
Orchestrates multi-model LLM consensus through a three-phase deliberation protocol. Use when you need collaborative AI review, multi-model problem-solving, code review from multiple perspectives, or consensus-based decision making. Coordinates OpenAI Codex, Google Gemini, and Claude CLIs for opinion collection, peer review, and chairman synthesis.
Access accumulated learnings and insights. Contains technical discoveries, personal insights, and lessons from past experience. Use when asked about past experience, what was learned, how something works based on experience, or for context on topics previously explored. Triggers: what did I learn, have I seen this before, past experience, learned that, figured out.
Search the web using the agent's built-in WebSearch tool. Use when you need to find current information, verify facts, or research topics. No API key required. Keywords: search, web, internet, lookup, find, research, current events, facts.
Guide for performing secure web searches with privacy protection, source verification, and information validation. Use when the user wants to search the web securely, verify sources, fact-check information, or mentions secure search, privacy, source validation, or web research.
Validate constitution quality with checklists, anti-pattern detection, and version bump rules. Use after writing constitution content, when reviewing constitutions, or when you see "constitution review", "quality check", "version bump", "anti-patterns", or "constitution audit".
Systematically investigate social media claims and viral content. Use when fact-checking complex claims, when decomposing multi-part assertions, or when investigating narratives that mix facts with interpretation.
Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification
Comprehensive link analysis for static sites. Use when the user wants to analyze links, find broken links, identify orphan pages, detect under-linked or over-linked content, find link sinks, or understand their site's internal linking structure. Supports HTTP validation with false-positive filtering.
Systematically analyze societal impacts of technologies using McLuhan's Tetrad of Media Effects. Use when evaluating new technology, planning technology adoption, or analyzing technology policy.
Diagnose lyric problems across prosody, rhyme, meaning, register, sound, and structure. Use when AI-generated or human lyrics feel flat, cliched, awkward, or mismatched.
Search the web using Tavily API for high-quality, AI-optimized results with advanced filtering options. Use when you need structured search results, domain filtering, relevance scores, or AI-generated answer summaries. Requires TAVILY_API_KEY. Keywords: tavily, advanced search, filtered search, domain filtering, relevance scoring.
Search 76M+ patents using BigQuery (fast, zero setup) or PatentsView API (US patents with rich metadata).
Diagnose and guide revisions in non-fiction books. Use for non-fiction book revision, when arguments feel weak, evidence is outdated, readers report confusion, thesis is unclear, or book structure has problems. Keywords: non-fiction, revision, thesis, argument, evidence, structure.
Expert evaluation of Chemical Engineering PhD qualifying exams - review written reports, presentations, and prepare comprehensive questioning sessions to assess student readiness for doctoral research
Fast, cloud-based patent searching across 76 million+ worldwide patents using Google BigQuery - keyword search, CPC classification, patent details retrieval
Write solution options documents to evaluate and compare different technical approaches with trade-off analysis Common user requests: - "Evaluate options for [problem]" - "Compare [solution A] vs [solution B]" - "What are the trade-offs between [approach X] and [approach Y]?"
Diagnose book marketing copy problems and generate platform-optimized blurbs, descriptions, taglines, and query pitches. Use when marketing copy feels weak, when descriptions aren't converting, or when starting marketing from scratch.
Analyzes keyword usage in provided content, calculates density, suggests semantic variations and LSI keywords based on the topic. Prevents over-optimization. Use PROACTIVELY for content optimization.
Analyzes content for E-E-A-T signals and suggests improvements to build authority and trust. Identifies missing credibility elements. Use PROACTIVELY for YMYL topics.
This skill analyzes meeting transcripts to extract decisions, action items, opinions, questions, and terminology using Cerebras AI (llama-3.3-70b). Use this skill when the user asks to analyze a transcript, extract action items from meetings, find decisions in conversations, build glossaries from discussions, or summarize key points from recorded meetings.
Chinese doctoral/master thesis LaTeX assistant. Provides: structure integrity checking, GB/T 7714 format validation, compilation (xelatex/lualatex via latexmk), Chinese academic expression standards, terminology consistency analysis. Use when: - Working with Chinese thesis projects (main.tex + chapter files) - User mentions "doctoral thesis", "master thesis", "dissertation", "graduation thesis" - User mentions Chinese: "博士论文", "硕士论文", "学位论文", "毕业论文" - User asks about university templates: thuthesis, pkuthss, ustcthesis, fduthesis - User needs GB/T 7714 bibliography format checking - User wants to compile Chinese LaTeX documents
