Results for “research-memo”

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.

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

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.

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.

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.

Drafts structured client memoranda translating legal analysis and strategic recommendations into plain language for non-lawyer audiences. Covers corporate governance, fiduciary duties, compliance, and transactional advice. Enforces standard memo architecture: heading block, executive summary, background, analysis, options, and recommendations. Use when preparing client-facing memos, opinion letters, or governance briefings.

Stores verified cross-session facts, decisions, preferences, and open questions without secrets, speculation, or monitoring.

Condenses complex materials into a one-page executive decision memo with recommendation, evidence, tradeoffs, and next actions.

Simulates a NeurIPS/SC/ICSE-style peer review with five reviewer personas (HPC, ML, Stats, Reproducibility, Devil's Advocate) that verify every claim against actual result data before submission.

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

Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.