con un clic
oconnorlab-agent-config
oconnorlab-agent-config contiene 47 skills recopiladas de oclb, con cobertura ocupacional por repositorio y páginas de detalle dentro del sitio.
Skills en este repositorio
Planning-centric workflow for substantial work across software, analyses, artifacts, documentation, and configuration. Invoke manually with $work-cycle when alignment matters; not for straightforward one- or two-edit requests.
Create or update developer-facing and agent-facing project documentation, or run module-scoped codebase audits. Invoke manually with $documentation for codebase maps, module documentation, codebase review/audit workflows, and README.md or AGENTS.md work.
Documentation subskill for project hygiene maintenance. Use through $documentation when the user asks to maintain, clean up, health-check, refresh AGENTS.md/notebook/TODOs, inspect git branches/PRs/stashes, or review overall project state. Do not use for codebase audit, codebase review, release-check, or module-scoped bug-finding requests; those belong to module-codebase-review.
Manual-only workflow for codebase audit, codebase review, release-check, paper-freeze-check, and module-scoped multi-agent read-only bug/code-smell audits that produce a prioritized notebook report and TODO-ready findings. Use this instead of maintain-project for requests that ask to audit or review code behavior.
Ergonomic notebook-backed TODO capture for deferred work. Invoke manually with /defer when the user asks to defer, save, park, or add a TODO for later work while preserving the current conversation context.
Initialize a project workspace for Claude Code with project instructions, repository checks, notebook scaffolding, optional remotes, and optional O2/SLURM setup. Invoke manually with /init-project for first-time project setup, notebook bootstrap, project remotes, or O2/SLURM setup.
Ergonomic notebook-backed TODO capture for deferred work. Invoke manually with $defer when the user asks to defer, save, park, or add a TODO for later work while preserving the current conversation context.
Initialize a project workspace for Codex with project instructions, repository checks, notebook scaffolding, optional remotes, and optional O2/SLURM setup. Invoke manually with $init-project for first-time project setup, notebook bootstrap, project remotes, or O2/SLURM setup.
Planning-centric workflow for substantial work across software, analyses, artifacts, documentation, and configuration. Invoke manually with /work-cycle when alignment matters; not for straightforward one- or two-edit requests.
Create or update durable project notebook entries. Use whenever Codex creates notebook memory, especially from a forked subagent.
Repo-local onboarding for this lab-agent-config repository. Auto-trigger inside this repository when the user asks to set up, initialize, install, onboard, configure, or get started with this repository or its Claude Code configuration.
Repo-local onboarding for this lab-agent-config repository. Auto-trigger inside this repository when the user asks to set up, initialize, install, onboard, configure, or get started with this repository or its Codex configuration.
Internal init-project subskill for first-time O2/SLURM remote-bridge setup, including bridge installation, permissions, SSH keys, and first connection.
Internal init-project subskill for first-time O2/SLURM remote-bridge setup, including bridge installation, permissions, SSH keys, and first connection.
Use when creating, editing, converting, polishing, checking, or inspecting public-facing artifacts such as DOCX, PDF, PPTX, TikZ diagrams, manuscript figures, or manuscripts being prepared for journal submission.
Presentation-style subset of a high-impact manuscript figure workflow. Use when the user asks to style, polish, critique, audit, or improve manuscript figures, multi-panel scientific plots, scientific slide figures, SVG/PDF/TIFF outputs, figure legends, panel layouts, or journal-ready visual presentation. Focuses on visual argument, hierarchy, typography, color, layout, export readability, and reviewer-risk checks. Not for dashboards, exploratory plots, Illustrator/Figma-first infographics, or choosing/implementing the full plotting backend.
Use when creating, editing, converting, polishing, checking, or inspecting public-facing artifacts such as DOCX, PDF, PPTX, TikZ diagrams, manuscript figures, or manuscripts being prepared for journal submission.
Use when the user wants to systematize a workflow, encode desired or undesired agent behavior, create or edit a skill, or get support with their Codex setup.
Use when the user asks about their Codex configuration, or encounters issues related to missing skills, the AGENTS.md file, or the O2 bridge.
Work with PowerPoint presentations
Use when the user wants to systematize a workflow, encode desired or undesired agent behavior, create or edit a skill, or get support with their Claude Code setup.
Guide for creating effective skills. Use when users want to create a new skill or update an existing skill that extends Claude Code with specialized knowledge, workflows, or tool integrations.
Work with PowerPoint presentations
Guide for creating effective skills. Use when users want to create a new skill or update an existing skill that extends Codex with specialized knowledge, workflows, or tool integrations.
Customize AGENTS.md file(s) for either the user or a project, including guidance on project, subdirectory, and user-level instruction scope.
Work with Word documents
Comprehensive pre-submission and resubmission manuscript checklist for academic papers. Runs 20 parallel checks covering citations, display items, factual claims, writing quality, data/code availability, cover letters, and response to reviewers. Supports AJHG and Nature Genetics policies. Use when: user says 'finalize manuscript', 'check manuscript', 'pre-submission check', 'manuscript checklist', 'ready to submit', or when preparing a paper for journal submission or resubmission.
Work with PDF files
Create publication-quality TikZ/LaTeX flowcharts, architecture diagrams, and schematic figures. Use when the user asks to create a diagram, flowchart, schematic, figure with boxes and arrows, or architecture diagram for a paper or writeup. Trigger words: "diagram", "flowchart", "figure", "schematic", "TikZ", "tikz", "boxes and arrows", "architecture diagram".
Create or update developer-facing and agent-facing project documentation. Invoke manually with /documentation for codebase maps, module documentation, and README.md or CLAUDE.md work.
Manual-only workflow for documenting a module, file, package, or subsystem for developer understanding.
Documentation subskill for comprehensive project maintenance audits. Use through /documentation when the user asks to "maintain", "audit", "clean up", "health check", or review overall project state. Checks CLAUDE.md freshness, notebook index, TODO list, git state, test suite, and compiles actionable suggestions.
Manual-only workflow for decomposing a repository, package, or subsystem into high-level modules, boundaries, and relationships for developer understanding.
Check and manage DNAnexus jobs. Use when the user asks to check DNAnexus job status, monitor dx jobs, inspect failures, review job logs, summarize failed jobs, or resubmit failed DNAnexus jobs.
Create or update durable project notebook entries. Use whenever Claude Code creates notebook memory, especially from a forked subagent.
Resume the current conversation after a break. Invoke manually with /remind-resume to get a summary of work done in this session, git state, and what to pick up next. User-invoked only - never auto-trigger.
Install and run GraphLD graphREML on the HMS O2 cluster, including SuiteSparse, scikit-sparse, MKL, polars-lts-cpu, data downloads, and SLURM job setup. Use when the user asks to install GraphLD on O2, set up GraphLD on O2, or get graphREML running on the O2 cluster.
Customize CLAUDE.md file(s) for either the user or a project, including guidance on project, subdirectory, and user-level instruction scope.
Use when something did not go as expected and the user likely wants to change a system prompt, CLAUDE.md file, skill, or configuration so it does not happen again.
Use when the user asks about their Claude Code configuration, or encounters issues related to missing skills, the CLAUDE.md file, or the O2 bridge.