1.4万 件 ・ 関連度順
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
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。
Inspect and analyze codebases using pygount for LOC counting, language breakdown, and code-vs-comment ratios. Use when asked to check lines of code, repo size, language composition, or codebase stats.
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 the user wants to review a pull request, understand what a PR changes, assess risk of merging, or check for missing test coverage. Examples: "Review this PR", "What does PR #42 change?", "Is this PR safe to merge?"
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。
Replicate and validate a GitHub issue by spinning up Archon, analyzing the issue, and systematically testing all described symptoms using browser automation. Use when: User wants to reproduce a bug, validate a GitHub issue, confirm a reported problem, or investigate whether an issue is real before working on a fix. Triggers: "replicate issue", "reproduce issue", "validate issue", "confirm bug", "test issue", "can you reproduce", "try to replicate", "verify the bug". Capability: Checks out main, pulls latest, starts Archon, reads the GitHub issue, then uses agent-browser to systematically test every symptom and produce a findings report. NOT for: Fixing issues (use /archon or /exp-piv-loop:fix-issue), general UI testing (use /validate-ui).
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 the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"
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。
Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models/skills/agents in DeerFlow, manage DeerFlow memory, upload files to DeerFlow threads, or delegate complex research tasks to DeerFlow. Also use when the user mentions deerflow, deer flow, or wants to run a deep research task that DeerFlow can handle.
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。
Discover, build, verify, and optionally export (HTML, optional PDF) the evidence manifest of one SDD Composy task in evidence_required, routing it toward review_required. Use when acceptance evidence must be assembled or checked — 'juntar as evidências da task', 'gerar o relatório de evidências', 'verify the evidence manifest'. Do NOT use to run tests (sdd-qa), review code (sdd-review), or inspect the trace (sdd-trace).
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 traceable accessibility checks that combine scanners with observable keyboard, focus, semantic, and assistive-technology behavior.
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 traceable data checks for reconciliation, integrity, transactions, and atomicity with separate observable oracles.
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 platform-specific Android and iOS checks with explicit SDK, driver, device, lifecycle, and evidence prerequisites.
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 traceable API checks for contracts, authentication, authorization, errors, and idempotency with observable outcomes.
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 authorized, bounded, reproducible security checks without turning scanner findings into penetration-test permission.
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 an approved PRD must become an executable roadmap — 'gerar roadmap do PRD', 'quebrar o PRD em épicos e features', 'cadeia de dependências', 'roadmap with dependencies' — Phase/Epic/Feature/Task with explicit dependencies, waves and critical path, validated by a deterministic checker, with an approval gate. Do NOT use for a PRD that is not approved (prd- create/prd-refine first).
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 traceable Web and browser checks with explicit browser coverage, observed interactions, isolated sessions, and evidence limitations.
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 the user wants tests planned for existing code or a test audit — unit, integration, E2E scenarios exportable to Playwright, playwright-cli UI checks, a coverage matrix — 'criar testes para o UserService', 'plano de testes E2E do login', 'auditar a cobertura'. Writes .planning/feat/features/{slug}/plan.md. Do NOT use for code review (feat-review), for implementing features (feat-feature) or to run an existing plan (feat-exec).
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 a repository has no PWDEV Power workspace yet, when resuming one, when the codebase map needs refreshing, or when the setup should be checked
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 the user wants a UI-only action plan — components, pages, composables/hooks, state, forms and their E2E coverage — 'plano de frontend para a tela X', 'plan the settings page'. Writes .planning/feat/features/{slug}/plan.md with E2E scenarios and playwright-cli checks. Do NOT use for API/database work (feat-backend), full features (feat-feature), writing code (feat-exec) or UI review (feat-review).
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。
Enable, record, query, summarize, or verify the opt-in PWDEV Flow semantic audit trail. Use when the user asks what Flow actions occurred, wants audit integrity checked, or needs a portable JSONL record of workflow gates and artifacts.
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。
Write and refine high-quality user stories — INVEST criteria, "As a X, I want Y, so that Z" format, Gherkin acceptance criteria when applicable, definition of ready, anti-patterns, and a review checklist. Use when creating or reviewing user stories, PRD section 6, backlog items, or acceptance criteria. Do NOT use for technical specs, architecture decisions, or task decomposition.
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 GitHub releases for this project or similar GitHub repositories. Use when the user asks to release the current master/main branch, create a version tag, publish a GitHub Release, write release notes, check release workflow status, or follow the repository's release process.
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。
Super-skill for developing Haskell projects with cabal nix-style builds. Orchestrates HLS diagnostics, Haddock, Hoogle, source formatting, and cabal-gild into one workflow. Use when writing, editing, refactoring, building, typechecking, fixing compiler errors, renaming symbols, looking up APIs, or changing dependencies in Haskell projects. Treat cabal.project as the source of truth, prefer HLS before full builds, and prefer local docs over remote lookup.
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。
Format Haskell package descriptions and cabal project files with cabal-gild: *.cabal, cabal.project, cabal.project.local, and cabal.project.freeze. Use after editing dependencies or stanzas, when refreshing cabal-gild discover module lists, or when checking cabal file formatting.
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。
Generate creative, memorable, and available domain name ideas for projects, products, and businesses with consideration for branding, SEO, and availability. Use when naming new projects, finding available domains, creating memorable brand names, generating naming ideas, checking domain availability, or establishing online presence.
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。
Systematically review pull requests, feature implementations, and code changes to ensure quality, maintainability, security, and adherence to best practices. Use when reviewing code before merging, conducting peer reviews, performing self-reviews, auditing code quality, checking for security vulnerabilities, ensuring consistent coding standards, verifying test coverage, assessing performance implications, evaluating architectural decisions, or providing constructive feedback to improve team code quality.
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。