Results for “research-memo”

Conducts exhaustive multi-source research on a topic, tagging each claim with source class and confidence, and includes a mandatory adversarial counterpoint and open-questions list.

Diverga HUD (Heads-Up Display) management skill. Configure and manage the research project statusline display. Supports multiple presets: research, checkpoint, memory, minimal. Triggers: "hud", "statusline", "display settings"

Provides expert guidance for fast fine-tuning with Unsloth, including LoRA/QLoRA optimization, with 2-5x faster training and 50-80% less memory usage.

ByteDance's open-source super agent harness — spawns parallel sub-agents, Docker sandbox execution, persistent long-term memory, modular skills (research/report/slides). Built on LangChain + LangGraph. Triggers on: 'deerflow', 'deer-flow', 'bytedance agent', 'super agent harness', 'LangGraph agent orchestration', 'multi-hour agent tasks', 'spawn sub-agents', 'agent sandbox docker', 'persistent agent memory', 'agent skills system', 'AI research orchestrator', 'long-running agent tasks', 'agent with memory', 'langgraph orchestrator', 'IM channel agent integration'.

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

Quantize LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss using bitsandbytes. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers.

Optimize AI agents through automated evolution cycles using LLM-driven mutation of prompts, skills, and memory against measurable benchmarks.

Write legal memoranda with analysis and conclusions. TRIGGERS - Use when user needs help with legal-memo related tasks.

Write legal memoranda with analysis and conclusions. TRIGGERS - Use when user needs help with legal-memo related tasks.

Guides agents through the full lifecycle of NeMo-RL experiments: understanding recipes, launching reproducible runs, analyzing results, and preserving human oversight with git and TSV logs.

Write the private-equity investment committee memo for a deal — thesis, company and market, financials and QoE, valuation and returns with base/bull/bear MOIC and IRR, value-creation plan, risks and mitigants, structure and financing, sensitivities, and a conditioned recommendation.

Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs

Use RWKV, a linear-time RNN-Transformer hybrid, for efficient long-context inference and training with constant memory usage.

Search and retrieve past work from claude-mem's persistent cross-session memory database using a three-layer workflow: search, timeline, and fetch.

Generates a comprehensive narrative report analyzing a project's entire development history from claude-mem's persistent memory timeline.

Master the AI tools that accelerate research and information gathering. From market research to academic analysis, find insights faster and make better decisions. Use when "research, find information, academic papers, market research, competitive intelligence, fact check, research, information, analysis, academic, market-research" mentioned.

Extract project vision and decisions from a user through iterative Q&A, then convert them into clear repo documentation (README, ADRs, lessons). Use when user asks to document ideas in their head.

Organize research by managing references, notes, and collaboration across Google Drive, Docs, Sheets, and Gmail.

Provides persistent, self-hosted semantic memory for AI agents via MCP, storing worklogs, decisions, and notes in PostgreSQL with pgvector for meaning-based retrieval across sessions.

Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題.

Evidence-first current-state research workflow for ECC. Use when the user wants fresh facts, comparisons, enrichment, or a recommendation built from current public evidence and any supplied local context.

Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics.

Persistent cross-session memory management. Enables agents to remember user preferences, project conventions, and past decisions across different sessions using a structured MEMORY.md index and topic files.

Researches an open-ended question — options, possible solutions, prior art, trade-offs, or how something works — and produces a durable, evidence-backed, adversarially-validated report that recommends an option without committing the team to any artifact. Use when you want to research approaches, weigh options, survey prior art or the state of the art, or understand how something works before committing to a direction. Does not diagnose a bug, failure, or root cause — use investigate. Does not specify a feature — use plan-a-feature. Does not create or update a coding standard — use coding-standard. Does not compare two concrete artifacts for gaps — use gap-analysis. Does not assess an existing module's architecture — use architectural-analysis. Does not capture feedback on Han's own skills — use han-feedback.

端到端研究编排器：idea 发现 → 实验设计 → 执行 → 判决 → 论文撰写，带人工门控和状态恢复

Retrieve task-relevant project and global memory without loading everything. Load when the user asks what we decided, recall prior context, find memory about a feature, explain past rationale, resume a task, or check deferred ideas.

Route research prompts to evidence, retrieval, scraping, data, market, or scientific research skills. Use when prompts mention deep research, current facts, citations, Exa, iterative retrieval, search-first, scraping, data pipelines, PubMed, USPTO, gget, literature review, or scholar evaluation.

Indexes document metadata in SQLite and manages ephemeral key-value state in Redis for cross-session context.

Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics. Use when the user runs /si:review or asks what has been learned and what should be promoted or pruned.