「agent workflow」の検索結果

Read a CONTINUE_HERE.md continuation file at session start and resume from where the prior session left off. Covers detecting the file, assessing freshness, parsing the structured handoff, confirming the resumption plan with the user, and cleaning up after consumption. Optionally configures a SessionStart hook and CLAUDE.md instruction for automatic pickup. Use at the start of a session when a continuation file exists, when bootstrapping after an interrupted session, or when setting up automatic continuation detection.

日本語の概要は準備中です。原文の説明を表示しています。

Manage change control for validated computerized systems. Covers change request triage (emergency, standard, minor), impact assessment on validated state, revalidation scope determination, approval workflows, implementation tracking, and post-change verification. Use when a validated system requires a software upgrade, patch, or configuration change; when infrastructure changes affect validated systems; when a CAPA requires system modification; or when emergency changes need expedited approval and retrospective documentation.

日本語の概要は準備中です。原文の説明を表示しています。

Manage R package dependencies using renv for reproducible environments. Covers initialization, snapshot/restore workflow, troubleshooting common issues, and CI/CD integration. Use when initializing dependency management for a new R project, adding or updating packages, restoring an environment on a new machine, troubleshooting restore failures, or integrating renv with CI/CD pipelines.

日本語の概要は準備中です。原文の説明を表示しています。

Implement comprehensive model drift monitoring using Evidently AI, statistical tests (PSI, KS), and custom metrics to detect data drift and concept drift in production ML systems. Set up automated alerting and reporting workflows to catch degradation before it impacts business metrics. Use when production models show unexplained performance degradation, when new data distributions differ from training data, when seasonal shifts affect input features, or when regulatory requirements mandate model monitoring.

日本語の概要は準備中です。原文の説明を表示しています。

Set up systematic data labeling workflows using Label Studio or similar tools. Implement quality controls, measure inter-annotator agreement, manage labeler teams, and integrate labeled data into ML training pipelines. Use when starting a supervised ML project that requires labeled training data, when model performance is limited by insufficient labeled examples, when labeling text, images, audio, or video, or when implementing active learning to prioritize the most valuable examples.

日本語の概要は準備中です。原文の説明を表示しています。

Compose 2D graphics programmatically using SVG generation, diagram layout algorithms, image compositing, and batch processing workflows. Use when generating diagrams, flowcharts, or infographics programmatically, creating reproducible scientific figures, automating production of badges or visual assets, building custom chart types not in standard libraries, or batch generating graphics with parameter variations.

日本語の概要は準備中です。原文の説明を表示しています。

Set up a Blender scene programmatically via Python (bpy) with objects, materials, lighting, camera, and environment configuration. Use when creating reproducible 3D visualization scenes, automating product or architectural rendering setup, generating multiple scene variations programmatically, building template scenes for batch rendering workflows, or integrating 3D visualization into data pipelines.

日本語の概要は準備中です。原文の説明を表示しています。

Create and manage pull requests using GitHub CLI. Covers branch preparation, writing PR titles and descriptions, creating PRs, handling review feedback, and merge/cleanup workflows. Use when proposing changes from a feature or fix branch for review, merging completed work into the main branch, requesting code review from collaborators, or documenting the purpose and scope of a set of changes.

日本語の概要は準備中です。原文の説明を表示しています。

Design and implement multi-stage CI/CD pipelines using GitHub Actions with matrix builds, dependency caching, artifact management, and secret handling. Create workflows that span linting, testing, building, and deployment stages with parallel execution and conditional logic. Use when setting up automated testing and deployment for a new project, migrating from Jenkins or CircleCI to GitHub Actions, implementing matrix builds across platforms, adding build caching, or creating multi-stage pipelines with security scanning and quality gates.

日本語の概要は準備中です。原文の説明を表示しています。

Select an OCR/HTR engine by benchmarking candidates on the same labelled samples — source ground truth from open datasets (e.g. Hugging Face PAGE-XML corpora) or hand-transcription, wrap every engine behind a transcribe(image_path) -> str adapter (vision-LLMs via any OpenAI-compatible endpoint, dedicated HTR REST APIs, cloud OCR), and score with zero-dependency raw CER, lenient CER, WER, and a critical name/date token diff. Use when choosing an engine for handwriting or historical-document transcription, when published accuracy claims need honest verification on your own material, or when a records workflow must surface confident-but-wrong names and dates that a low aggregate CER hides.

日本語の概要は準備中です。原文の説明を表示しています。

Shared conventions for every SDLC development-phase architect agent: hard rules, code quality bar, workflow steps (superpowers invocation, spec reading, codebase exploration, verification), and the report/compact-summary contract. Architects load this skill first, then apply their stack-specific instructions on top.

日本語の概要は準備中です。原文の説明を表示しています。

Use Therapeutics Data Commons through the PyTDC Python package for registry discovery, approved dataset access, task-aware splits (scaffold, cold-start, temporal, combination), evaluator metrics, benchmark groups, and bounded molecular-oracle workflows. Use this skill to find which TDC datasets exist for a therapeutic task, load them with a split that does not leak, score predictions with the task's own official metric rather than a generic one, and run benchmark groups reproducibly. Also trigger on PyTDC, Therapeutics Data Commons, tdc.single_pred, tdc.multi_pred, ADMET Benchmark Group, scaffold split, get_split, or molecular oracles such as GSK3B, JNK3 and DRD2.

日本語の概要は準備中です。原文の説明を表示しています。

Cheminformatics toolkit for fine-grained molecular control. Parse and write SMILES, SDF, MOL and InChI; compute descriptors (MW, LogP, TPSA, QED, Bertz); build fingerprints (Morgan/ECFP, RDKit, MACCS, atom pair, torsion) and score Tanimoto, Dice or cosine similarity; run SMARTS substructure search and reaction SMARTS; generate 2D depictions and ETKDG 3D conformers; extract Murcko scaffolds and canonical hashes; control sanitization and stereochemistry directly. Also trigger on rdkit, Chem.MolFromSmiles, rdFingerprintGenerator, SDMolSupplier, SMARTS query, ETKDG, or FilterCatalog. For standard workflows with a simpler interface use the datamol skill, which wraps RDKit; use rdkit for advanced control, custom sanitization, and specialized algorithms.

日本語の概要は準備中です。原文の説明を表示しています。

Open a pull request with proper PR template, test coverage, and review workflow. Guides agents through creating a PR that follows repo conventions, ensures existing behaviors aren't broken, covers new behaviors with tests, and handles review via bot when local testing isn't possible. TRIGGER when user asks to "open a PR", "create a PR", "make a PR", "submit a PR", "open pull request", "push and create PR", or any variation of opening/submitting a pull request.

日本語の概要は準備中です。原文の説明を表示しています。

Guide for creating effective skills. Use when creating a new skill or updating an existing skill that extends agent capabilities with specialized knowledge, workflows, or tool integrations.

日本語の概要は準備中です。原文の説明を表示しています。

Design and build reactive, type-safe, production-grade backends on Convex. Covers schema, queries/mutations/actions, indexes, auth, file storage, scheduling, real-time multiplayer, mobile backends, and LLM/agent workflows on Convex's one-platform stack.

日本語の概要は準備中です。原文の説明を表示しています。

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", or "merge and push".

日本語の概要は準備中です。原文の説明を表示しています。

End-to-end automated model quantization and accuracy tuning workflow. Use when user asks for automated model quantization and accuracy tuning, e.g. "自动量化", "量化调优", "一键量化", "精度调优", etc. 当用户给出多卡（≥2 卡）卡号时，量化阶段通过 EP 并行适配（msmodelslim-ep-parallel-adaptation）保证多卡 EP 并行，调优主流程仍在本 Skill。

日本語の概要は準備中です。原文の説明を表示しています。

Aggregate DiT inference outputs into per-dimension VBench metrics via AISBench. Run after the quant-tuning-evaluate DiT workflow produces a directory of mp4s and the user supplies a VBench-1.0-mini JSON + pre-populated cache dir. Single mode (Standard).

日本語の概要は準備中です。原文の説明を表示しています。

Compile, profile, diagnose, optimize, and compare Ascend NPU operators across CANN versions and A2/A3/A5 for Ascend C, CATLASS, Triton-Ascend, TileLang-Ascend, PyPTO, and SHMEM/MC2. Use when an operator already has a runnable implementation and the user asks for msOpProf collection, bottleneck analysis, source-level tuning, or a reproducible before/after performance report. Do not use as the primary workflow for operator creation, migration, or unresolved correctness failures.

日本語の概要は準備中です。原文の説明を表示しています。

Analyze Ascend NPU collective communication profiling data with a DB-first workflow. Use when the user provides `cluster_analysis_output/cluster_analysis.db`, rank-level `analysis.db`, rank-level `ascend_pytorch_profiler_{rank_id}.db`, together with `profiler_info.json`, and asks about HCCL or hcom communication cost, collective communication TOP ops, wait time, slow rank/straggler, Notify Wait, bandwidth, retry, relay, SDMA/RDMA/HCCS links, communication matrix, or Ascend communication fault patterns.

日本語の概要は準備中です。原文の説明を表示しています。

执行模型测评（统一入口）。LLM/VLM 走主流程 scripts/run_evaluation.py + Evaluation YAML；model_family=dit 走 DiT 扩展节（references/dit/evaluate_workflow.md，vbench.py 批量推理产出视频）。

日本語の概要は準備中です。原文の説明を表示しています。

Use when scoring finished content against quality dimensions, evaluating whether a piece meets publishable standards, or determining which workflow phase needs rework based on quality gaps.

日本語の概要は準備中です。原文の説明を表示しています。

Use for every coding task. Enforce strict TDD workflow: activate Serena, investigate first, clarify+confirm requirements, write per-task REQUIREMENTS.md in .requirements/<datetime>_<feature_name>/, verify APIs via web search, then implement in tiny test-verified steps.

日本語の概要は準備中です。原文の説明を表示しています。