4,065 件 ・ 関連度順
概要と使いどころ
Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.
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。
Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.
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。
Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
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。
Triage GitHub issues through a label-based state machine. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
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。
Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when deciding whether to maintain or sunset existing code.
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。
Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
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。
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.
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。
Relentless delivery mode for complex, multi-step tasks. Use when: multi-file features, unclear root cause debugging, multi-angle research, architecture decisions with trade-offs. Activates parallel subagent dispatch and strict verification.
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 this skill whenever a task involves running parallel work on a git repository without conflicts — e.g. "fix this bug while I keep working on my feature", "run Claude on two branches at once", "work on this task in isolation", "create a throwaway branch for this experiment", or anything where two agents or sessions might edit the same files. Also trigger when the user asks to use worktrees directly, or when an agent needs its own isolated checkout so it can work without disturbing the main branch. Even if the user just says "do this in parallel" or "don't mess up my current work", consider worktrees.
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。
GEODE evidence-first development workflow. Use for feature work, provider/model changes, GUI/computer-use work, PDF/document ingestion, observability/schema/event/state changes, verification planning, GitFlow merge prep, and requests to "follow the workflow" or "scaffold the 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。
Research process for comparing frontier harnesses (Claude Code, Codex, OpenClaw, autoresearch, Prime Agent) with the original/upstream implementation and performing GAP analysis before feature implementation. Triggered by "research" ("리서치"), "gap", "frontier", "harness", "case study" ("사례 조사"), "pattern exploration" ("패턴 탐색"), "comparative analysis" ("비교 분석") keywords.
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。
Implements one numbered sub-task from a task list at .ai/[feature]/tasks.md, running linters and tests, without staging, committing, or marking the task complete. Use when asked to carry out a specific sub-task by number, or as the inner step of a larger loop that handles commits separately. For the full loop including commits, use task-orchestration.
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。
Plan dependency-aware atomic commits for changes that span multiple logical concerns. Use when a refactor, feature, or API change would benefit from reviewable, independently meaningful commit boundaries. To triage an already-dirty working tree and propose commits for existing uncommitted changes, use `planning-commits` instead.
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。
Implements sub-tasks from a task list at .ai/[feature]/tasks.md strictly one at a time, stopping after each to ask the user before starting the next, and keeping the task list and Relevant Files section current. Use when the user wants to review or approve each sub-task before work continues, rather than letting the agent run the list unattended with task-orchestration.
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。
Deterministic AI development workflow orchestrator. Manages task boards (.jonggrang/jonggrang-tasks.json), runs 16-phase pipelines (BUGFIX/SMALL/MEDIUM/LARGE), installs lifecycle hooks for Claude Code and OpenCode, and coordinates five specialist roles (Lead/Developer/Reviewer/TestLead/Tester). Use when planning features, executing multi-step development workflows, or orchestrating AI coding agents. Run via npx jonggrang.
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。
Used by the Lead agent during Phase 6 (Brainstorm) to collaboratively explore user intent, requirements, and alternative approaches before locking in the architecture. Helps turn raw ideas into fully formed specs through natural dialogue.
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 Product Requirements Document from feature intent/description
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。
Used by the Developer agent during Phase 8 (Implement) when building web components, pages, or UI features. Provides strict aesthetic guidelines to create distinctive, production-grade frontend interfaces that avoid generic 'AI slop' aesthetics.
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。
DiT 计算模块（L3）：把**已定位的 DiT 计算瓶颈**落成特性级选档与实施—— 量化档（W8A16 / W4A16 / W8A8 系列 / W4A4 / MXFP8 / FA 量化）、稀疏（rf_v2 / ada_bsa）、 缓存（DiTCache / AttentionCache / 时间步优化）、编译启用（MindieSDBackend / Pattern 融合 / ACLGraph） 的**开不开、开哪一档、怎么开、怎么复验**；依据是 `docs/zh/features/*`（特性真源）+ framework-integration/references/framework-support-matrix.md（支持状态）。 即使用户只说"这个模型怎么加速""量化/稀疏/Cache 怎么选怎么开""要不要开量化、开哪一档""这个档位开了有没有效果" 而未提 profiling，也应触发。 **入口条件**：瓶颈点已明确（用户带一句实测锚点，或编排层交付标签）时由域入口 `performance-optimization` 按标签分发到本技能；**瓶颈未明（"怎么加速 / 跑通 / 采 profile"）先走 `model-auto-optimization` 定位**，不在本技能内做占比分析。 near-miss：多卡并行形态 / 通信掩盖 / TP·offload 选型 → `dit-parallel-opt`；VAE 解码段与 host 固定开销 → 各自模块（VAE / host）；单算子实现级实测选型（mindie_bench）→ `benchmark-dev`； 需要新增 pattern / 算子才能落地本档 → `pattern-dev` / `operator-dev`；框架侧开关与使能验证 → `framework-integration`；量化器位级契约与精度对齐（编码公式 / 舍入 / scale 粒度）→ `quantization-dev`；精度验收判据 → `accuracy-gate`；数字入库口径 → `perf-gate`。
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。
分布式并行策略选型与实测（USP / CP 通信掩盖 / CFG / TP/RSP/PP 概览；含拓扑相关选型 （按实测拓扑分域条件化：域内 bulk vs 跨域 head-parallel 翻转）与 AlltoAllV 缺陷绕过）。在 model-auto-optimization 中承担 S3：优先 USP、结合拓扑带宽差异选 CP，少量 step + 多 rank 验证特性开启与掩盖（产物：并行方案 + 多 rank 证据）。当用户需要多卡并行 策略选择、**序列并行形态抉择**（纯 Ulysses vs 复合 AllGather-KV×Ulysses：按 GQA / 跨域带宽 / 形态 plumbing 条件化定胜负）、**并行 × 稀疏叠加**（seam 契约：先汇聚后稀疏、 窗口偏移、块对齐、per-head 掩码；含「稀疏看似生效实则未生效」判定）、通信掩盖调优 （含**掩盖率上限**：1-1/n 何时成立、c/f 决定的真实上限、没生效的排查）、**并行方案 差异归因**（阶段 Δ 分解 / 集合通信按 communicator 归属 / 4→8 卡线性度），或排查多卡 跑不动 / 通信暴露大 / 换卡组 / 端口 bind / HCCL 带宽验证问题时使用；**并收编原并行作用域诊断**： 改了 SP/CP/Ulysses/AllGather-KV 后**不报错但结果没变/性能没变**、或小规模能跑大规模崩 （如 Ascend EE1003 coreDim 超限）时，用本技能证明"改动到底有没有生效"（判别量逐层收窄 + 两侧对照 + 日志≠生效，见 `references/scope-effectiveness-check.md`）； 即使用户只说 "多卡跑不动""通信暴露大""为什么没达到 6/7 的掩盖率""CP 和 USP 该选哪个""CP 叠稀疏 怎么不生效"而未说并行，也应触发。特性档位/接口事实见 `docs/zh/features/parallelism.md` /`usp.md`（仓内真源），框架侧开启见 framework-integration； 本技能承载选型决策、monkey-patch 掩盖与多卡诊断实测。 由 dev-workflow 多卡场景触发，亦由 model-auto-optimization 的 S3 阶段触发。
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。
Expert debugger for Next.js + Cloudflare Workers + Supabase stacks. Systematic troubleshooting for auth, caching, workers, RLS, CORS, and build issues. Activate on: 'debug', 'not working', 'error', 'broken', '500', '401', '403', 'cache issue', 'RLS', 'CORS'. NOT for: feature development (use language skills), architecture design (use system-architect).
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。
Build and extend pd-console — Port Daddy's GPU-native macOS operator console (GPUI 0.2.x, Zed's Rust UI). Covers the render-agnostic Block/Pane(Surface) contract, the two-thread reqwest↔smol refresh pipeline, Taffy flexbox layout, uniform_list virtual scroll, focus + keyboard nav, the OKLCH theme and ICS maritime flag badges, GPUI's missing text-input, and the real feature-gated cargo/CI gate. Use when adding panes, visual polish, or debugging GPUI rendering/layout/focus in core/pd-console. NOT for the TypeScript daemon, generic Rust toolchain/borrow-checker help (use rust-with-claude-code), or non-pd GPUI apps with a different theme/architecture.
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。
Multi-stage Docker build optimizer for minimal, secure production images. Activate on: Dockerfile optimization, multi-stage build, distroless image, container size reduction, Docker security scanning, BuildKit features. NOT for: container orchestration (use kubernetes-manifest-generator), CI/CD pipelines (use github-actions-pipeline-builder), runtime container config (use environment-config-manager).
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。
Handle mental health crisis situations in AI coaching safely. Use when implementing crisis detection, safety protocols, emergency escalation, or suicide prevention features. Activates for crisis keywords, safety planning, hotline integration, and risk assessment.
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。