Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
免费在 GitHub 公开
session-handoff
Initiate a session handoff to transfer context and pending actions to a new terminal session. Executing this skill safely drains tasks and launches a new cross-platform window natively.
中文简介正在准备中。当前显示原文说明。
查看安装方法包含的文件（11）
- SKILL.md2.1 KB
- commands/session-handoff.md115 B
- hooks/post-execute.cjs308 B
- hooks/pre-execute.cjs425 B
- references/research-requirements.md456 B
- rules/session-handoff.md524 B
- schemas/input.schema.json645 B
- schemas/output.schema.json259 B
- scripts/main.cjs1.2 KB
- session-handoff.cjs8.9 KB
- templates/implementation-template.md189 B
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
<identity>
Session Handoff Specialist - Executes the Phase 7 context handoff loop, transferring session continuity natively across processes.
</identity>
<capabilities>
- Writing the session handoff log securely directly to disk via atomic locks.
- Checking the Active Task database to prevent corruption and cross-session overlap (Drain Gate).
- Spawning a detached cross-platform GUI terminal window using the verified OS decision matrix.
</capabilities>
<instructions>
When to Use
Invoke this skill:
- When context reaches maximum capacity (>150k limit)
- When the user explicitly asks to restart, shift-change, or prep for continuation.
- Before ending a long work session
How to Execute (MANDATORY)
To trigger the session handoff, you MUST execute the internal skill executable via the Bash tool. You shouldn't generate the log yourself—the executable handles all schema management and polling.
node .claude/skills/session-handoff/session-handoff.cjs
Drain-Complete Gate
If the executable fails and prints [session-handoff] ABORT: Cannot handoff session while tasks are active., you did not follow the drain rule!
You must explicitly use TaskUpdate to either mark all active tasks as completed OR suspended before re-running the skill.
Required Setup (Context Preservation)
Before running the skill, ensure that .claude/context/memory/active_context.md is updated with necessary context you want the next agent to know, as the script will synthesize it into the handoff payload.
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
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新