agentic-orchestration
Patterns for multi-agent coordination, task decomposition, handoffs, and workflow orchestration. Best practices for building and managing agent systems.
38,472 Skills
Search uses this published catalog; rankings and counts are snapshots.
Patterns for multi-agent coordination, task decomposition, handoffs, and workflow orchestration. Best practices for building and managing agent systems.
面向任意行业与职能岗位进行真实模拟或逐题训练,重点覆盖互联网产品、AI 产品、战略商分、数据分析、咨询及商业化等方向。先确认目标公司、岗位、可选 JD、轮次与运行方式,再组合通用协议、岗位 Playbook、题型、问题模式、领域视角和用户材料。产品经理及以产品判断为核心的复合岗位进行完整模拟时,严格贴合公司业务赛道和岗位性质,在 1 小时内动态覆盖自我介绍题、简历深挖题、行为动机题、工作职能题、开放业务题、产品实战题和费米估算题七类;顺序和权重按 JD、轮次与现场回答调整。普通面试一次一题,真实模拟结束后统一复盘,逐题训练则答完即诊断并重组专业答案。用户
为 Pocky 策划、撰写和制作小红书 AI 图文内容。用户要分享或种草 AI 应用、Skill、网站、提示词、方法论,或要求做 AI 产品拆解、专业配图、图文轮播、普通人视角小红书正文时使用;图片内文采用固定专业产品分析结构,发布正文采用易懂的第一人称种草语气。
Search Banodoco messages and accepted current resource heads, fetch exact revisions, and contribute immutable resource revisions or evidence.
All-in-one autonomous development workflow: requirements gathering, file-based planning, iterative execution, and self-learning distillation. Use when starting any feature, bug fix, or multi-step task.
Trigger Smart Donkey's learning phase: distill insights from the current session into smart-donkey-brain.md.
Show current Smart Donkey workflow status: plan phases, progress, brain file stats, and any blockers.
This skill is coordination-exempt: skip the ai-coord gate for its declared work.
Orchestrates read-only investigation or implementation within the current session after explicit plan approval. Task-handoff instead writes a decision-complete file for a fresh, separate session — use it for work continuing later or elsewhere; use an in-session handoff to impleme
Design **deep modules**: substantial behaviour behind a small interface at a clean seam, testable through that interface. Use this vocabulary when it clarifies a design decision. The aim is leverage for callers, locality for maintainers, and testability.
Compose the semantic commit message from immutable evidence. Let `ai-commit` own deterministic preparation, commit, index reconciliation, and push mechanics.
Apply Effect 3 semantics from project-local architecture, the narrowest relevant reference, and source matching the target's installed packages.
Create a working frontend with a clear, subject-specific point of view, then prove it in the rendered UI.
Role 05 of the Phoenix Security spec pipeline. Red-teams normative requirements for Phoenix-specific failure modes: multi-tenant isolation gaps, vague integration surface definitions, AI agent safety holes (PSC-08), missing auth controls (PSC-06), reachability vs CVSS conflicts,
Role 09 of the Phoenix Security spec pipeline. Slices a Phoenix Security feature into safe, incremental batches sized for a 12-person team (1–3 engineer-days each), with P0 security requirements always in Batch 1, API contracts before consumers, integrations last, explicit rollba
Catalog captured:2026-11-21