Review and manage proposals, questions, and memory diffs in a unified dashboard.
npx skills add https://github.com/fontesgerards/chief-of-staff --skill cos-review
Please help me install this Agent Skill. Skill: cos-review Source: https://github.com/fontesgerards/chief-of-staff/tree/main/engine/skills/cos-review Command: npx skills add https://github.com/fontesgerards/chief-of-staff --skill cos-review
This Skill provides a unified interface to review and manage pending proposals, open questions, and Tier-2 memory diffs, enabling efficient decision-making and follow-up.
Use the cos-review skill to review the current review queue and make decisions on pending items.
High-intent search queries and answers about installing and using this skill.
A review queue dashboard consolidates pending proposals, questions, and memory diffs into a single interface for streamlined decision-making. It tracks decisions, edits, rejections, and notes, allowing you to quickly process items and maintain a history of actions taken.
Memory diff tracking stages proposed changes to memory for review before integration. It allows you to evaluate proposed modifications, accept or reject them, and maintain a state of decisions, ensuring memory changes align with system architecture constraints.
Decision tracking records all actions taken on review items, including sends, edits, rejections, and notes left by the user. This maintains a comprehensive state of decisions so you can follow up on pending items and review the history of actions taken.
Yes, the system operates by parsing and updating Markdown files to maintain a state of decisions. This allows the review dashboard to read pending items and record your decisions directly within the existing file architecture.
The dashboard operates within the constraints of an existing system architecture, parsing and updating Markdown files rather than replacing the infrastructure. It provides a comprehensive review interface on top of your current setup without requiring structural changes.
The best way is to use an on-demand review dashboard that manages a queue of proposals, questions, and memory diffs. This lets you quickly review each staged item, make informed decisions, and track the decision history before finalizing any actions.
friedbotstudioCurate auto-extracted memory candidates into canonical .claude/memory files.
Veloxia-agencyLog board meeting decisions into a two-layer memory archive with YAML frontmatter.
asaeedAutomate routing, task scanning, and memory updates for Obsidian vault notes.
stark-ai-deClassify GitHub, GitLab, Linear, and markdown issues using decision trees.
