Research

Create new Claude Code skills with proper structure, documentation, and

'Guides the creation of engineering calculation documents through a 6-phase

Parallelize research, synthesize findings in main context, spawn independent reviewer, then commit—a structured 4-phase execution pattern for complex deliverables.

"Main orchestrator as lightweight router \u2014 stay responsive to user\

Throwaway experiments to validate an idea before build.

Assess a multi-machine, multi-repo AI-enabled workspace for readiness, provider allocation, and issue prioritization.

Retrieve bounded curated wiki context and source metadata for domain tasks. Resolve the existing owner checkout and supported query surface; report unavailable operations and missing provenance.

End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Integrates automated experiment monitoring, statistical analysis, iterative writing, and citation verification.

Spotify: play, search, queue, manage playlists and devices.

Triage and rank GitHub issues across a workspace-hub style multi-repo ecosystem using machine-readiness, provider-utilization, and leverage scoring.

"Deep multi-repo ecosystem audit \u2192 domain gap matrix \u2192 structured\

A robust workflow for handling a batch of related investigative tasks that require file system research, documentation, and version control.

"Systematize research and literature gathering for engineering categories\

"Systematic workflow for finding, downloading, and indexing engineering

Plan and operate a Hermes-led control plane that routes AI provider work across workstations using quota urgency, machine readiness, GitHub issue gates, and a dispatch ledger.

Protocol for workers to capture and propagate discoveries back to the orchestrator and shared knowledge base. Phase 3 of orchestrator/worker context enforcement (#2020).

Pre-flight checks at session start — load context, check prior state, validate env, check for in-flight work from other terminals

Clean a stale `status:plan-review` queue by separating missing-plan drift

Audit a status:plan-review queue to identify true approval candidates without being fooled by stale labels, conditional review summaries, or unresolved prerequisite blockers.

"Adversarial review workflow for GTM feature work before user approval\

Verify proposed copy changes to vamseeachanta/aceengineer-website against canonical sources in workspace-hub (llm-wiki, live site, strategy repo) before shipping. Produces a GitHub issue on the site repo documenting the check with a Match / Drift / Gap verdict.

Operate ace-linux-1 as the continuous AI-agent control surface for overnight and continuous batches that keep GTM material moving toward client outreach.

Gather actionable sales intelligence on companies and individuals before outreach

Synthesize qualitative and quantitative user research into structured insights and opportunity areas