学术
学术写作、研究与引用
critique
Zpankz
Multi-perspective dialectical reasoning with cross-evaluative synthesis. Spawns parallel evaluative lenses (STRUCTURAL, EVIDENTIAL, SCOPE, ADVERSARIAL, PRAGMATIC) that critique thesis AND critique each other's critiques, producing N-squared evaluation matrix before recursive aggregation. Triggers on /critique, /dialectic, /crosseval, requests for thorough analysis, stress-testing arguments, or finding weaknesses. Implements Hegelian refinement enhanced with interleaved multi-domain evaluation and convergent synthesis.
dialectical
Zpankz
Compose intellectually sophisticated persuasive essays using tripartite dialectical structure (establish-critique-synthesize), paradox accumulation, conversational register calibration, and strategic humility. Supports three atomic writing primitives (AGONAL α, MAIEUTIC β, APOPHATIC γ) with hypersoft plithogenic composition, plus legacy style modes and hybrid combinations. Triggers on requests for persuasive writing to mixed/skeptical audiences, defending counterintuitive claims, Socratic pedagogical dialogue, editorial first-person essays, or writing that must balance accessibility with depth. Implements recursive thematic anchoring, forced dilemma construction, and transformed return closure. Use when linear argumentation is insufficient and accumulated tension resolves through synthesis.
dependency-rules
dozybot001
Rules for task dependencies in decomposition. Use when defining dependencies in Decompose/AddTasks to ensure acyclic, sibling-only, correct execution order. Critical for valid plan structure.
source-attribution
dozybot001
Ensure research reports, comparison reports, and synthesis documents include proper citations and a References section. Use when task output is a Markdown report with quantitative claims, benchmarks, or findings that require source attribution for credibility. Load alongside markdown-reporter or web-research for citation-heavy tasks.
research-templates
dozybot001
Three academic research templates (Heilmeier, scientific discovery, system optimization) with schemas and use cases. Use when RefineIdea to align output structure with research type.
context-router
Zpankz
Routes context extraction requests to appropriate CLI tools. Triggers on /context, /limitless, /research, /pieces, or detected context needs from intent hook. Supports single, parallel, and augmented extraction modes.
deep-research
petekp
Conduct exhaustive, citation-rich research on any topic using all available tools: web search, browser automation, documentation APIs, and codebase exploration. Use when asked to "research X", "find out about Y", "investigate Z", "deep dive into...", "what's the current state of...", "compare options for...", "fact-check this...", or any request requiring comprehensive, accurate information from multiple sources. Prioritizes accuracy over speed, cross-references claims across sources, identifies conflicts, and provides full citations. Outputs structured findings with confidence levels and source quality assessments.
guided-ooda-loop
m31uk3
Universal pattern for structured LLM interaction managing finite context windows through phased progression (Observe-Orient-Decide-Act). Use when the user has a complex problem, wants to design/build/create something (software, strategy, document, process), or uses phrases like "I have an idea for...", "help me design...", "guide me through...", or mentions OODA, RPI, or PDD. Reduces hallucinations through structured interaction.
compound-learning
Zpankz
Self-improving holon implementing Plan→Execute→Assess→Compound workflow loops with explicit knowledge crystallization. Generalizes compound engineering beyond coding to any domain where work produces learnable signals: writing, research, learning, problem-solving, design. Use when: (1) task quality matters and can improve over time, (2) patterns emerge from repeated work, (3) institutional knowledge should accumulate, (4) future tasks should benefit from past learnings, (5) "compound", "learn from", "improve process", "capture learnings", or multi-step workflows with review cycles. Orchestrates parallel research agents, multi-lens assessment, and structured knowledge codification into searchable documentation with YAML frontmatter. Implements λο.τ → λ(ο,Κ).τ where Κ is accumulated knowledge that compounds interest-like over time.
prompt-driven-development
m31uk3
Transform rough ideas into detailed design documents with implementation plans. Use when a user wants to develop an idea into a complete specification, create a design document from a concept, plan a feature implementation, or mentions "PDD", "prompt-driven development", "idea to design", "design doc from idea", or wants to systematically refine requirements before building. Guides through requirements clarification, research, detailed design, and implementation planning.
decomposition-patterns
dozybot001
Common patterns for decomposing research tasks. Use when decomposing complex tasks to ensure MECE (mutually exclusive, collectively exhaustive) splits and clear phase boundaries. Essential for Decompose tool. Apply when CheckAtomicity returns atomic=false.
atomicity-criteria
dozybot001
Criteria for judging if a task is atomic (executable in one step). Use with CheckAtomicity to decide when to Decompose vs FormatTask. Essential for atomicity decisions. Apply when processing each task in the planning workflow.
literature-grounding
dozybot001
Guidelines for citing literature in refined ideas. Use [Source ID: X] format when referencing papers. Apply when RefineIdea output should be grounded in retrieved papers.
topic-refinement
dozybot001
Guidelines for refining broad or fuzzy ideas into concrete research topics. Use when user input is vague to guide ExtractKeywords and RefineIdea. Includes RESEARCH_TOPIC_SCHEMA and refinement tactics.
paper-evaluation
dozybot001
Criteria for evaluating paper relevance (EvaluatePapers) and filtering (FilterPapers). Use before EvaluatePapers/FilterPapers to ensure consistent scoring and selection. Score 1–5, should_retry when score < 3.
keyword-extraction
dozybot001
Guidelines for extracting arXiv search keywords from fuzzy research ideas. Use before ExtractKeywords or when EvaluatePapers suggests retry. Ensures keywords are technical, domain-specific, and suitable for literature retrieval.
web-research
dozybot001
Conduct web research, gather information from multiple sources, and synthesize findings. Use when task involves searching, comparing sources, or aggregating information. Covers process, synthesis techniques, and output structure. Note: MAARS Task Agent uses provided artifacts and general knowledge—no live web search.
codebase-researcher
Zpankz
Deep research skill for analyzing codebases systematically. Use when comprehensive codebase understanding is needed, particularly for new projects or when documenting architecture. This skill should be used when users request deep analysis, architecture documentation, or systematic codebase research starting from root-level directories.
refined-idea-quality
dozybot001
Quality criteria for refined_idea output. Use before RefineIdea or when ValidateRefinedIdea returns low score. Focus on concrete, decomposable, and specific output.
rag-research-template
dozybot001
Advanced RAG-style research schema with literature-grounded fields. Use when RefineIdea for hardware-aware or citation-heavy proposals.
context-orchestrator
Zpankz
Orchestrates context retrieval from three CLI sources: limitless (personal life transcripts), research (online documentation/facts), pieces (local code/LTM). Use when external context is needed beyond the current codebase. Triggers on /context, /limitless, /research, /pieces, or balanced detection on complex prompts involving personal memory, technical documentation, or development history.
market-research
mfwarren
Production-ready entrepreneurship skills for Claude Code — marketing, sales, operations, finance, and leadership. 24 skills built by a founder, for founders.
crucible-outliner
forsonny
Chapter-by-chapter outline generator for stories planned with the Crucible Structure. Use when a user has completed Crucible planning documents (thesis, strand maps, forge points, etc.) and wants to create detailed chapter outlines. Triggers on requests like "outline my book," "create chapter outline," "outline Book 1," "turn my Crucible plan into chapters," or when user has Crucible planning docs and wants to start writing. Works for single books or multi-book series.
debug-like-expert
cfircoo
Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when standard troubleshooting fails or when issues require systematic root cause analysis.