Skip to main content
在 Manus 中运行任何 Skill
一键导入
GitHub 仓库

reef

reef 收录了来自 hdresearch 的 14 个 skills,并提供仓库级职业覆盖和站内 skill 详情页。

已收集 skills
14
Stars
0
更新
2026-04-06
Forks
1
职业覆盖
3 个职业分类 · 已分类 100%
仓库浏览

这个仓库中的 skills

code-delivery
软件开发工程师

Use when doing code work that must be integration-friendly: branches, commits, tests, PR-ready receipts, owned paths, and parent-friendly handoff.

2026-04-06
app-deployment
网络与计算机系统管理员

Use when implementing and exposing a product/application service or UI that should run outside Reef root. Choose child/resource VM placement, stand up the app, and report how to reach it.

2026-04-06
command-handling
软件开发工程师

Use when handling parent commands such as steer, abort, pause, or resume, or when deciding how urgently to react to inbox messages from above.

2026-04-06
coordination-patterns
软件开发工程师

Use when agents need to coordinate through reef store, peer signals, barriers, rendezvous, or child/peer communication without breaking authority boundaries.

2026-04-06
create-service
软件开发工程师

Create a new service module for reef. Use when adding a new capability to the server — a new store, API routes, LLM tools, behaviors, or dashboard widget.

2026-04-06
decompose
软件开发工程师

Use when a task has multiple independent subsystems, needs recursive delegation, or requires a parent to split implementation and then integrate the results.

2026-04-06
fleet-inspection
网络与计算机系统管理员

Use when inspecting the live fleet, differentiating active vs historical lineage, tracing ancestry, checking subtree state, or doing post-mortem investigation.

2026-04-06
github-ops
软件开发工程师

Use when working with GitHub repos, branch setup, auth tokens, PR flow, or repo preparation inside Reef.

2026-04-06
logs-debugging
网络与计算机系统管理员

Use when debugging Reef or fleet behavior through logs, including keyword/date filtering, per-agent inspection, post-mortem analysis, and handoff investigation.

2026-04-06
reporting-checkpointing
项目管理专家

Use when signaling done/blocked/failed, reporting artifacts upward, or deciding whether to create a checkpoint before risky or meaningful state transitions.

2026-04-06
resource-ops
网络与计算机系统管理员

Use when spawning, configuring, auditing, or retiring resource VMs that host infrastructure such as databases, services, test environments, or webhook-facing systems.

2026-04-06
root-supervision
网络与计算机系统管理员

Use when root reef must supervise the fleet, maintain continuity across turns, detect drift or stalls, and decide when to steer, recover, schedule follow-up, or clean up.

2026-04-06
scheduled-orchestration
软件开发工程师

Use when reef needs deferred attention, follow-up checks, deadlines, or condition-based orchestration via scheduled checks instead of reminder-style timers.

2026-04-06
setup
网络与计算机系统管理员

Set up a reef server with example services. Use when bootstrapping a new reef instance or adding fleet coordination services to an existing one.

2026-04-06