Skip to content

AI/ML Research

Experiment tracking, model lifecycle, data versioning, notebooks, fine-tuning, agent frameworks, and the broader research-engineering tooling stack.

Skills in this repo

Local

Skill One-line Notes
mlflow-tracking Generic MLflow — sqlite + mlflow ui solo, PostgreSQL + MinIO docker for teams; LLM tracing, registry, autolog.
dvc-ml-workflow DVC pipelines + queued experiments with metrics auto-bound to ephemeral commits.
marimo-batch-mlflow marimo dual-mode (UI + batch CLI) notebooks with Tyro + MLflow.

Vendored

Skill Upstream Series
marimo-notebook marimo-team/skills flat
streamlit-to-marimo marimo-team/skills flat
anywidget marimo-team/skills flat
deep-research 199-biotechnologies/deep-research deep-research series

External skills (manual install)

Status enum (single source of truth across the catalog)

Every external-skill or MCP entry below carries a status: value:

Status Meaning Where it links
vendored Already in vendor.yaml. Link to the skills/vendor/<name>/ (or series) entry.
deferred Open TODO P? item — under consideration. Link to the TODO.md anchor.
skipped Looked at, chose not to vendor. Inline reason required (1 sentence).
evaluated Read but no decision recorded. Effectively "tracked." Inline 1-line note describing what was learned.
wishlist Surfaced but not yet evaluated. No link required; default for fresh discoveries.

Status changes are explicit edits — see the Adding catalog entries workflow doc (under Workflows in the nav) for the wishlist → deferred → vendored recipe.

Manual install for non-vendored skills

When a skill is not in vendor.yaml, you can still install it directly from upstream via the npx skills CLI:

# Whole-repo install (if SKILL.md sits at repo root or skills/)
npx skills@latest add <owner>/<repo>

# Subpath install (when the skill is nested)
npx skills@latest add <owner>/<repo>/<path-to-skill-dir>

# Cherry-pick by name
npx skills@latest add <owner>/<repo> -s <skill-name>

# Force deep discovery (skill nested >1 level inside skills/)
npx skills@latest add <owner>/<repo> --full-depth -s <skill-name>

For Anthropic-style plugin marketplaces (e.g. anthropics/financial-services, anthropics/knowledge-work-plugins), use the Claude Code plugin commands instead:

claude plugin marketplace add <owner>/<repo>
claude plugin install <plugin-name>@<repo-name>

For MCP servers, see the per-entry "Auth & install" section in the MCP wiki — install commands vary by transport (HTTP / stdio / SSE) and host (Claude Code / Claude Desktop / Cursor / Managed Agents).

Skill / Plugin Upstream Status Why this status Install hint
AI-research-SKILLs (full library) Orchestra-Research/AI-research-SKILLs wishlist 98 skills across 23 categories — full lifecycle from architecture (LitGPT, Mamba, NanoGPT) through fine-tuning (Axolotl, LLaMA-Factory, PEFT) to inference (vLLM, TensorRT-LLM). Too broad to vendor wholesale; will likely cherry-pick. npx @orchestra-research/ai-research-skills (their npm wrapper) or browse and npx skills@latest add Orchestra-Research/AI-research-SKILLs/<category>/<skill>.
bio-research plugin anthropics/knowledge-work-plugins/bio-research wishlist PubMed, BioRender, bioRxiv, ChEMBL, Benchling, Open Targets connectors. Not directly applicable but useful as a reference for life-sciences research workflows. claude plugin install bio-research@knowledge-work-plugins

MCP servers

Name Upstream Status Auth Records
none surveyed yet

Backlog (TODO P? items)

See the P? lane in TODO.md:

  • [?/L] LangChain / LangSmith / LangServe / LangGraph / Langfuse — group orchestration + observability stack into one coherent skill set.
  • [?/L] LLM fine-tuning skill — practical workflow for supervised fine-tuning and adapter-based tuning.
  • [?/M] Build MCP skill — minimum workflow for creating, testing, and documenting MCP servers (note: mcp-builder is already vendored — re-evaluate if this still needed).
  • [?/M] Hugging Face Spaces + Gradio skill — demo app deployment, secrets, local-to-hosted handoff.
  • [?/M] Data visualization skill — Matplotlib + Seaborn + Plotly for exploratory + report-ready output.

See also