remote-project-control
Remote Project Control
Help the user operate a project whose code is edited locally but actually runs on one or more servers over SSH. Establish project memory first, then coordinate safe local, Git remote, and server actions.
Terminology used by this skill:
local: the user's local development machine, usually the Mac where the agent is runningremoteorgit remote: the Git hosting remote such as GitHub or GitLab, e.g.originserver: an execution machine or cluster reached by SSH, such asquest,ibex-vscode, orepfl-haas
The skill name is historical. In project memory and user-facing summaries, prefer server for SSH/HPC/RunAI execution environments and reserve remote for Git remotes unless quoting an existing field name.
Pair this skill with research-project-memory when server execution state should be linked to project-level experiments, evidence, actions, or worktree status.
Skill Directory Layout
<installed-skill-dir>/
├── SKILL.md
More from a-green-hand-jack/ml-research-skills
project-init
Initialize an ML research project control root. Use for paper/code/slides repos, shared memory, GitHub Project alignment, agent guidance, worktree policy, and lifecycle handoffs.
39init-python-project
Initialize or enhance a Python/ML project. Use for new repos or forks needing production structure, uv environment setup, and research evidence docs.
37new-workspace
Create Git branches or worktrees for research code and paper versions. Use for experiments, baselines, rebuttal fixes, arXiv/camera-ready branches, and worktree memory.
36project-sync
Sync verified code-side experiment results into paper memory. Use when logs, reports, run docs, or user-confirmed metrics should become paper-facing evidence.
36init-latex-project
Initialize a LaTeX academic paper project. Use for new conference or journal papers needing templates, macros, venue preambles, and writing guidance.
36add-git-tag
Create annotated Git milestone tags. Use when completing a phase, releasing a version, or marking a research checkpoint.
36