메뉴
Compact the current conversation into a handoff document for another agent to pick up.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff.
Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.
Oversight-first daily PR maintenance for the current repo. Use when the user wants to triage and maintain their pull requests — "do my PR rounds", "pr daily", "review my PRs", "check my open PRs", "rebase and fix my PRs", daily PR cleanup. Resolves the right GitHub account first, fans out read-only parallel code reviews on PRs awaiting the user's review (never auto-submitted), and single-threads verification-gated fixes (rebase, review comments, failing CI) on the user's own PRs. Works on any repo and any stack — discovers conventions and checks from the repo itself. Do NOT use for a one-off review of a single specific PR, or to merge PRs.
Audit JS supply-chain hygiene (Safe Chain on dev machine, .npmrc/equivalent in repo, GitHub Actions CI gates, CONTRIBUTING.md mention) and offer interactive fixes. INVOKE ONLY when the user explicitly types `/supply-chain-check` — do NOT auto-invoke based on project type, lockfile presence, security mentions, or any related context.
Split working-tree changes into multiple logical commits using Conventional Commits format. Use when the user says "split commits", "logical commits", "break this into commits", "commit my changes", "commit strategy", or has accumulated multi-concern changes on a branch. Auto-detects the repo's commit conventions from recent history and asks for type/scope/approval through interactive selections (AskUserQuestion) instead of free typing. Never bypasses git hooks. Do NOT use for amending existing commits, rewriting history, interactive rebase, or pushing as the primary goal — only for creating new local commits from current changes.
Use when challenging ideas, plans, decisions, or proposals. Invoke to play devil's advocate, run a pre-mortem, red team, stress test assumptions, audit evidence quality, or find blind spots before committing. Do NOT use for building plans, making decisions, or generating solutions — this skill only challenges and critiques.
| name | handoff |
| description | Compact the current conversation into a handoff document for another agent to pick up. |
| argument-hint | What will the next session be used for? |
Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save to the temporary directory of the user's OS - not the current workspace.
Include a "suggested skills" section in the document, which suggests skills that the agent should invoke.
Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
Redact any sensitive information, such as API keys, passwords, or personally identifiable information.
If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.
