Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
中文简介正在准备中。当前显示原文说明。
wrg32786/aigent-os252026年10月29日 更新
免费在 GitHub 公开
brief
Generate a structured delegation brief for any task
中文简介正在准备中。当前显示原文说明。
wrg32786/aigent-os星标 25(GitHub 25 + cccskills 0)
实测评分 未实测
查看安装方法包含的文件（1）
- SKILL.md1.3 KB
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
Delegation Brief Generator
Quickly create a structured brief for delegating work to a sub-agent. Uses the template from system/05_delegation_protocol.md.
Usage
/brief [task description]
What It Produces
## Brief: [Task Name]
**From:** the AIgent
**To:** [Recommended agent based on task type]
**Priority:** [P0/P1/P2 based on context]
**Date:** [Today]
### Objective
[One sentence derived from the task description]
### Context
[Relevant context pulled from vault — active priorities, related project notes, recent decisions]
### Deliverable
[Specific, verifiable output]
### Constraints
[Time, scope, dependencies inferred from context]
### Verification
[How to check the work is actually done]
Behavior
- Parse the task description from the user's input
- Check
vault/memory/ACTIVE_PRIORITIES.mdto understand current mode and context - Check
vault/memory/DELEGATION_TRACKER.mdfor related pending work - Determine the right agent and priority level
- Draft the brief using the delegation protocol template
- Present to the principal for approval before sending
Always recommend a model tier for the receiving agent based on task complexity.
评价
还没有评价。欢迎分享你的使用感受。
评论
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
同一仓库的技能
Compose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures + recommended reflex.
中文简介正在准备中。当前显示原文说明。
wrg32786/aigent-os252026年10月29日 更新
Quarterly skill that walks the skill-index against the actual SKILL.md files on disk, reports drift (skills indexed that no longer exist, skills on disk that aren't enrolled, skills whose descriptions have changed since enrollment). Hardens the auto-enrollment pipeline against silent rot.
中文简介正在准备中。当前显示原文说明。
wrg32786/aigent-os252026年10月29日 更新
When a [CADDY] hint fires and the principal is confused why, /caddy-explain walks the scoring transparently — which trigger matched, what points it earned, what the threshold was, what other skills were close. Pairs with the legibility thesis. Caddy's decisions should be inspectable on demand.
中文简介正在准备中。当前显示原文说明。
wrg32786/aigent-os252026年10月29日 更新
Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives. Use when a new skill is created, copied in, or when a skill needs updated triggers. Usage — "/caddy-enroll <path to SKILL.md>".
中文简介正在准备中。当前显示原文说明。
wrg32786/aigent-os252026年10月29日 更新
Mute a Caddy hint class for a window. Defaults to 4h auto-expiry. Classes — memory, context, body, routing, all.
中文简介正在准备中。当前显示原文说明。
wrg32786/aigent-os252026年10月29日 更新