メニュー
SkillsMP は LibreYOLO/libreyolo から 29 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
収集済み skill 29 件中 29 件を表示しています。
Write the PRD (port handoff) for adding a new model to LibreYOLO: the single markdown document an implementing agent executes end to end. Use when someone proposes a model ("should we add X?", "can we port X?", "write a PRD for X", "what would it take to add…
原文の言語: 英語
Run the RF100-VL (Roboflow 100-VL) detection benchmark on LibreYOLO models end to end: dataset download with version locking, per-dataset fine-tuning, protocol-conformant pycocotools evaluation at maxDets 500, artifact publishing, and multi-GPU execution on…
原文の言語: 英語
Prepare and upload a LibreYOLO weight repo to the HuggingFace LibreYOLO org. Use when publishing new weights (new family, new size, or new task like -seg). Covers filename, README, LICENSE, NOTICE, and collection membership.
原文の言語: 英語
Cut a LibreYOLO version release end to end: evidence-backed changelog built by fan-out agents over the release..dev diff, a gate scoreboard (unit CI, GPU e2e on Modal reusing the nightly, weight autodownload probe, wheel smoke, notices sync, docs drift,…
原文の言語: 英語
Work on LibreYOLO's export subsystem: debug a failing export, fix an exported model that predicts differently from the .pt, extend a format's coverage to a new family/task, or add a new export format. Use when someone reports "export to X fails", "the…
原文の言語: 英語
Export LibreYOLO models for Hailo accelerators (Hailo-8/8L, Raspberry Pi AI Kit/AI HAT+). Use when a user asks to run LibreYOLO on Hailo, compile to HEF, or asks whether a given model family can be deployed on Hailo. Covers the "will it compile?"…
原文の言語: 英語
Port a model into LibreYOLO. Executable guide — finds your closest existing family to clone, gives paste-ready templates for the model class, conversion script, runtime auto-convert recognizer, and trainer subclass, then walks the port as a sequence of…
原文の言語: 英語
Launch LibreYOLO's end-to-end (e2e) test suite the right way — the heavy GPU tests under tests/e2e/ that load real weights, export to ONNX/TensorRT/OpenVINO/ ncnn/TorchScript/CoreML, train on real datasets, and check inference parity. Use whenever someone…
原文の言語: 英語
Edit LibreYOLO's README.md (and its README.zh-CN.md mirror) safely. Use whenever someone asks to update, fix, extend, or review the README, when a README claim contradicts the code ("the readme says X but..."), when a release or new feature tempts a README…
原文の言語: 英語
Signpost for updating www.libreyolo.com (docs pages, feature announcements, SEO articles) when something ships in the library. Use when a change needs user-facing docs beyond the repo ("document this on the website", "add a docs page for X", "the site still…
原文の言語: 英語
Prove that a LibreYOLO model actually trains correctly, not just that train() runs without crashing. Use when adding or changing a trainer, loss, augmentation, scheduler, or DDP path; when someone asks "does training work for family X?", "is this model…
原文の言語: 英語
Add or extend LibreYOLO e2e test coverage the right way: a new model family's GPU coverage, a new export backend file, a nightly case, or a training e2e. Use when someone asks to "add e2e tests for X", wire a new family into the nightly, cover a new export…
原文の言語: 英語
Use LibreYOLO as a computer vision library: run inference, train, validate, export, and track with object-detection / segmentation (and pose, classify, gaze, OBB, semantic, depth, point, restore) models on your own images and video. This is the guide for…
原文の言語: 英語
Audit and maintain LibreYOLO's licensing and provenance surfaces, and handle contamination correctly. Use when adding ported code or weights (which notice files must change), when reviewing a PR for license risk, when someone asks "can we use/host/ship X?",…
原文の言語: 英語
The whole dance for landing code on LibreYOLO's dev branch: branch, commit, push to upstream, then either open the PR against dev or hand the user a one-click compare URL that pre-fills the PR title and description (including the required Code provenance…
原文の言語: 英語
Launch a one-off / batch GPU job (training, evaluation, export, benchmarking) on a rented or serverless GPU when you don't have a local one — or need a bigger/faster card than you have. Covers three providers: Vast.ai (cheap marketplace GPUs you rent + tear…
原文の言語: 英語
Diagnose and fix slow LibreYOLO with the `libreyolo profile` CLI — both TRAINING throughput (`profile run`) and INFERENCE latency (`profile infer`). Use whenever training feels slow, GPU utilization is low, images/sec is disappointing, inference/predict…
原文の言語: 英語
Use LibreYOLO's zero-shot and promptable tiers: open-vocabulary detection with text vocabularies (LibreOpenVocab: Grounding DINO, OWLv2), promptable segmentation with points/boxes or concept text (LibreSAM: SAM-1, SAM-2, SAM 3, MobileSAM), zero-shot…
原文の言語: 英語
Signpost for benchmarking LibreYOLO models for visionanalysis.org. Use when someone wants to "benchmark for visionanalysis", produce a submission for the site, measure a model on COCO for publication, or add a hardware/runtime row to the site. The actual work…
原文の言語: 英語
Report a problem or friction to the LibreYOLO maintainers with a one-click, pre-filled GitHub issue link. Use for defects: a crash or traceback inside libreyolo, weights that fail to download or 404, training that does not converge on sane defaults, wrong or…
原文の言語: 英語
Add or extend a LibreYOLO CLI command or flag correctly: the Typer + KeyValueCommand architecture, both argument grammars (key=value and --key value), the --json/--quiet/--help-json contract, mode-aware aliases, family-derived defaults, and the unit tests…
原文の言語: 英語
Add a new task type to LibreYOLO (a new output kind like detect, segment, semantic, pose, classify, gaze, obb, point, depth, restore), as opposed to adding a model family to an existing task. Use when someone proposes a new capability that no current task's…
原文の言語: 英語
The rules every user-facing LibreYOLO surface must follow (Python API, CLI, dataset YAMLs, metric keys, Results fields) and the safe method for checking parity with the de-facto YOLO ecosystem conventions. Use when designing or reviewing any new public API,…
原文の言語: 英語
Inspect, validate, produce, and debug LibreYOLO .pt checkpoint metadata. Use when a checkpoint won't load ("not a LibreYOLO checkpoint", wrong family/task/class-count errors), when writing or reviewing a conversion script, when deciding what a converter must…
原文の言語: 英語
Review a LibreYOLO pull request the way this repo expects: contract-first (REVIEW.md axioms + /docs schemas), evidence-based, and verified live in a worktree rather than by reading the diff alone. Use whenever the user asks to review a PR, assess an external…
原文の言語: 英語
Run and write LibreYOLO's unit tests and the PR gate: the fast, hermetic, CPU-only suite under tests/unit/ that gates every push and PR to dev. Use whenever someone wants to run unit tests, "run the tests before pushing", check whether a change breaks the PR…
原文の言語: 英語
Triage a LibreYOLO GitHub issue or user bug report: reproduce it, classify it, find the owning code, and hand the user a decision-ready assessment. Use when someone says "look at issue #N", "a user reports X", "triage the new issues", or pastes a bug report /…
原文の言語: 英語
Prepare and upload a LibreYOLO dataset repo to the HuggingFace LibreYOLO org. Use when publishing a training/eval/smoke dataset (detection, segmentation, OBB, pose, semantic, depth, restore, or classification). Covers the redistribution license gate,…
原文の言語: 英語
Delegate work to OpenAI's Codex from inside Claude Code — a generic task (implement a feature, investigate a bug, refactor) or a code review as a cross-model second opinion. Trigger ONLY when the user explicitly names Codex — e.g. "use codex to implement…
原文の言語: 英語