.dotfiles

Use when opening a PR and driving it to green CI — push the branch, write a high-level PR description, watch checks, fix failures, and keep looping until green; also use when an already-open PR gets new commits.

Use when the user starts, resumes, switches, saves, or recalls a named task or ongoing work across sessions (e.g. "remember this", "continue X", "what was I doing on Y", "track this task").

Git commit workflow. Load when finishing any code-change task (after verification) to commit and push, or when explicitly staging/committing.

Use when modifying or adding a transform, loss, model, method, package, task-model, config, docs page, or example in a Lightly AG repo (lightly-ssl or lightly-train) and you need repo-specific conventions.

Spawn a subagent to run a task. Use when you want to delegate work to a separate pi instance.

Use when configuring or replicating LT-DETR v2 (ltdetrv2-s/m/l/x) COCO benchmarks via the lightly-train wrapper — model alias map, global vs per-rank batch size, recipe invariants, ECDet config mapping, cluster pins, and common gotchas.

Use when the user starts, resumes, switches, saves, or recalls a named task or ongoing work across sessions (e.g. "remember this", "continue X", "what was I doing on Y", "track this task").

Use when creating, writing, or drafting a GitHub issue. Covers tone, conciseness, detail, scope, and audience-fit — not investigation or gh mechanics.

Git commit workflow. Load when finishing any code-change task (after verification) to commit and push, or when explicitly staging/committing.

Use when the user asks to explore a repository, trace codepaths, map entry points, compare abstractions, or gather implementation context without changing files.

Enforce planning before acting. Load when user says "plan", "create a plan", or "before implementing".

Use when submitting, monitoring, or fixing Slurm benchmark jobs on a remote cluster; always work on the cluster host via SSH, sync files first, bootstrap the env if needed, and keep benchmark code simple and readable.

Use when working with GitHub from the command line with gh for auth, repo/issue/PR triage, reviews, inline review comments, Actions, releases, API requests, aliases, and automation.

Manage Linear issues from the command line using the linear cli. This skill allows automating linear management.

Use before any creative work — features, components, functionality. Explores intent, requirements, and design before any code.

Use when debugging NaN/inf instability, exploding losses, or numerical collapse in PyTorch training runs.

Use when analyzing remote MLflow tracking servers from the CLI to inspect experiments, runs, metrics, params, tags, and artifacts.

Use when debugging a traceback, runtime error, unexpected behavior, value/config mismatch, tensor/data shape issue, or when the user asks to backtrack where variables come from and where they go.

Always load when you need to write some skill.

Fetch and install skills from GitHub, URLs, or skill ecosystems. Use when asked to install, add, fetch, or ingest a skill.

Run multiple commands in parallel and aggregate outputs. Load when tasks are independent and can run concurrently.

Search the web using DuckDuckGo. Use when you need to find information, facts, documentation, or current events on the internet.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Execute implementation plans by dispatching subagents per task with pre-flight question phases. Load when tasks are independent and you want to delegate.

Analyzes pi session history to find repetitive patterns. Load when user asks to suggest or create skills.

Extract text from PDF files. Use when user asks to read, extract text from, or summarize a PDF.