소스 정보
- 저장소
- dinglebear-ai/dendrite
- 최근 소스 활동
- 2026년 6월 22일 06:00
- 감지된 SKILL.md 언어
- 영어
- 스타
- 1
- 포크
- 0
설치 방법
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
소스 파일 검토
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
메뉴
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/dinglebear-ai/dendrite --skill handoff명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Reconstruct interrupted parallel Claude and Codex work using Cortex session intelligence first, then verify it against Git worktrees, branches, plans, beads, PRs, and CI; distinguish completed, active, blocked, and stale lanes; identify dependencies and drift; and produce verified lane packets plus an actionable restart order. This skill should be used when the user asks to get up to speed across multiple agents or worktrees, asks what multiple agents were working on, needs to resume interrupted work after a usage limit, or wants all active implementation lanes identified and restarted.
Orchestrate a comprehensive, checkpointed, multi-agent review across code quality, architecture, security, performance, testing, documentation, framework practices, and CI/CD, producing durable `.full-review/` artifacts and a prioritized report. Use when the user explicitly asks for a comprehensive, full, exhaustive, multi-agent, or multi-dimensional review of a repository, branch, diff, change set, or path. Security focus, performance criticality, strict mode, and framework selection are optional modifiers. Do not use for routine single-perspective reviews, narrow scans, or requests that only ask to fix already-known findings.
Use this BEFORE creating a git worktree or implementing any plan. Tailored to our workflow — prefer it over superpowers:using-git-worktrees and every other worktree skill. Triggers - creating or adding a worktree; starting lavra-work, lavra-work-ralph, lavra-work-teams, executing-plans, subagent-driven-development, or work-it; whenever a Claude, Codex, or Gemini plan mode is entered or a plan is accepted; or before implementing anything in a fresh branch. Creates the worktree under .worktrees/ in the repo and makes it identical to and as warm as the main checkout - copying secrets and local config (.env, CLAUDE.md.local, .claude/settings.local.json), symlinking warm caches (node_modules, .venv, target, .next), and re-trusting mise/direnv. Also use when a worktree is missing files, builds cold, or reports mise 'not a trusted directory'. Bundles a worktree-sync engine, a create-in-.worktrees entrypoint, a minimal baseline template, and references.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | handoff |
| description | Clipboard-ready handoff prompt for another agent to investigate or continue a task. |
Write a clipboard-ready prompt for another agent to investigate, discuss, or work on a specific task.
Use when the user asks for handoff <task>, "write a handoff", "delegate this",
or wants a prompt for another agent.
The prompt must:
Use this shape by default:
I want to discuss and possibly work on: <short task title>
Context:
- <portable repo/product context>
- <what triggered this task>
- <known current state, branch/issue/PR names or URLs if relevant>
- <important constraints and ownership boundaries>
Before doing any implementation:
- Find the right repository from the current directory, a parent directory, or the usual workspace.
- Read the local agent/repo instructions.
- Inspect the relevant code, docs, tests, recent commits, and linked issue/PR state.
- Decide whether this task is still real, whether the proposed direction is a good idea, and whether a smaller/better fix exists.
- Call out stale assumptions, hidden risks, and anything that should stop the work.
Task:
- <what to investigate or implement if the review supports it>
- <expected behavior or decision criteria>
- <non-goals>
Validation:
- <focused tests/checks/live proof expected>
- <what evidence should be included>
- <what is explicitly not required>
Output:
- Start with your review findings and recommendation.
- Then give the proposed plan or patch summary.
- If you edit code, keep changes scoped and report exact proof run.
- Do not push, merge, close issues/PRs, label, or post public comments unless explicitly told.
On macOS:
pbcopy < /tmp/handoff-prompt.txt
Use a temp file or pipe. Avoid inline shell quoting for prompts containing
backticks, $, quotes, or user text.
If pbcopy is unavailable, use the obvious platform clipboard tool (wl-copy,
xclip, clip.exe) or print the prompt and say clipboard copy was unavailable.