dozybot001
@dozybot001
Public Skills
intent-cli
by dozybot001
Record semantic history (.intent/) — goals, snapshots, and decisions that persist across agent sessions. Triggered when user asks to record semantics.
rag-research-template
by dozybot001
Advanced RAG-style research schema with literature-grounded fields. Use when RefineIdea for hardware-aware or citation-heavy proposals.
refined-idea-quality
by dozybot001
Quality criteria for refined_idea output. Use before RefineIdea or when ValidateRefinedIdea returns low score. Focus on concrete, decomposable, and specific output.
research-templates
by 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.
topic-refinement
by 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
by 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
by 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.
decomposition-patterns
by 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.
literature-grounding
by 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.
research-scoping
by dozybot001
Guidelines for scoping research ideas into actionable tasks. Use when the root idea is broad or ambiguous to ensure appropriate granularity and feasibility. Helps with initial decomposition. Apply at root (task "0") and when refining broad sub-tasks.
source-attribution
by 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.
format-specs
by dozybot001
Guidelines for defining input/output specifications of atomic tasks. Use when formatting tasks (FormatTask) to ensure Task Agent and validator have clear, checkable criteria. Apply when CheckAtomicity returns atomic=true.
comparison-report
by dozybot001
Produce comparison reports between two or more options (technologies, approaches, products). Use when task involves comparing, evaluating alternatives, or making recommendations. Output typically includes criteria, comparison table, pros/cons, and recommendation.
web-research
by 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.
literature-synthesis
by dozybot001
Synthesize literature, findings, or multiple sources into a coherent report. Use when task involves literature review, synthesizing research, or combining multiple inputs into themes and conclusions.
markdown-reporter
by dozybot001
Generate structured Markdown reports, summaries, and documentation. Use when task output format is Markdown, document, report, summary, or README. Covers structure, tables, code blocks, and common report types. Essential for FormatTask output spec format: Markdown.
task-output-validator
by dozybot001
Validate task output against criteria before calling Finish. Use when the task has a validation spec (criteria, optionalChecks). Load this skill, write output to sandbox, run validate script, fix issues if validation fails, then call Finish.
atomicity-criteria
by 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.
dependency-rules
by 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.
data-analysis
by dozybot001
Analyze structured data (JSON, tables, metrics) and produce insights. Use when task involves analyzing data, computing metrics, or deriving conclusions from structured input. Output can be report (Markdown) or structured (JSON). Covers aggregation, comparison, trends, and validation.
json-utils
by dozybot001
Validate, format, and structure JSON output. Use when task output format is JSON, or when producing structured data (lists, configs, API responses). Ensures valid JSON and correct schema. Essential for FormatTask output spec format: JSON.