retrospective
Generate comprehensive learning documents by combining information from tickets, memories, GitHub PRs, and proposals. Use after completing significant work to capture lessons learned.
浏览 RoM4iK 维护的已发布 AI 技能,比较用途与说明,并通过来源仓库了解安装方式。
已收录技能
13收录技能的仓库 Stars 合计
0仓库 Forks
0平均每个技能的仓库 Stars
0同一仓库中的多个技能可能共享 Stars,合计包含重复仓库数据。
Generate comprehensive learning documents by combining information from tickets, memories, GitHub PRs, and proposals. Use after completing significant work to capture lessons learned.
Use for knowledge sharing across sessions. Search memory before starting work, store memory after learning. Critical for avoiding repeated mistakes and maintaining context.
Background process that proactively maintains memory hygiene. Scans for obsolescence to prune irrelevant data and synthesizes scattered information into higher-order patterns.
Use for any git operations: fixing PRs, creating commits, creating branches, pushing changes. Handles proper branch management, commit conventions, and stacked PRs.
Use when creating or updating tickets. Covers ticket writing best practices, what to include, and what to avoid.
Use when executing approved proposals. Only memory_cleanup and test_gap proposals can be executed. Other types should use create_ticket_from_proposal directly.
Acts as a Contextual Analyst. Reviews pending proposals by checking the codebase to establish *plausibility* and *value*. Approves proposals where the code context supports the suggested improvements.
Coordinates agent assignments and manages ticket lifecycle.
Use for workflow guidance on HOW to work effectively. Covers task execution, decision escalation, and team coordination.
Strategic Architect Agent. Synthesizes memory patterns and retrospectives to generate major architectural improvements and strategic task proposals. Invoked when all limited quotas are full.
Tactical Code Analyst. Fills autonomous worker queues with high-quality refactors and autonomous tasks by analyzing code churn and recent changes. Invoked when quotas are open.
Performs a human-level code review focusing on implementation, architecture, and project patterns.
Process incoming Telegram messages from humans by analyzing intent and determining the optimal strategic action (comments, ticket updates, knowledge articles, proposals, or replies).
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。