メニュー
Use when resuming work in this repo after a pause or starting a fresh session on in-flight changes. Reconstruct the current state, open risks, relevant files, completed verification, and next actions.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | dr-session-pickup |
| version | 2026-04-09.1 |
| description | Use when resuming work in this repo after a pause or starting a fresh session on in-flight changes. Reconstruct the current state, open risks, relevant files, completed verification, and next actions. |
Use this skill to recover working context quickly without re-deriving everything from scratch.
It should produce a compact, actionable state summary for the current task or repo area.
Before summarizing, load:
dr-repo-referenceAGENTS.mdSTATUS.md when the task touches known architecture or integration gapsAlways dispatch read-only subagents in parallel before running sequential commands yourself.
When the area is unfamiliar, spans multiple components, or the next step depends on broad repo evidence, launch 2-3 specialists simultaneously:
codebase_explorer — ownership, routes, execution-path mappinglong_context_reader — broad subsystem evidence across many filesarchitecture_consultant — structural assumptions (only when the next step depends on one)consumer_advocate — user workflow friction (only when that is central)Dispatch all of them in a single message. Do not wait for one to finish before starting the next.
Respect delegation limits (AGENTS.md):
long_context_reader, architecture_consultant, reliability_consultant, consumer_advocate)codebase_explorer, documentation_researcher)After the parallel evidence pass returns, run fast local checks for anything the subagents did not cover:
git status --short
git diff --stat
git diff
git log --oneline -n 10
Then inspect the likely task area:
rg -n "<symbol>|<route>|<command>|TODO|FIXME" portal dr-agent gateway installer migrations
If the work is portal-heavy, use portal_explorer.
If it touches dr-agent/, load dr-agent-windows.
If it touches auth, commands, sessions, tokens, or DB boundaries, load dr-security-review.
Produce a short state block with:
## Session Pickup
- Goal:
- Active component:
- Relevant files:
- What changed:
- Verified already:
- Not verified yet:
- Open risks:
- Next best action:
GOOS=windows explicitly if dr-agent/ is involveddr-autonomous-iteration, end with the next executable slice, not a passive summaryUse this skill when:
Use when asked to work in a continuous loop until done or truly blocked. Orchestrates pickup, planning, TDD execution, implementation waves when needed, debugging side-chains, verification, and resume behavior.
Use before planning when a feature or change request is underspecified. Resolve high-impact ambiguity around scope, consumers, security, failure handling, and acceptance criteria before writing the implementation plan.
Use for both preparing work for review and responding to review feedback. Keep review evidence local, concrete, and scoped to the real contract. Verify technically before agreeing or changing code.
Use before implementation. Merge design discovery and plan writing into one DR-specific flow: identify the consumer, inspect the repo, debate boundaries with partner and combatant, and produce an execution-ready plan that hands off cleanly into DR-native tasks, TDD, and implementation waves.
Use for the last mile: rerun verification, inspect diffs, commit or push if requested, and perform local docker-compose checks when needed. This is the DR local-tools replacement for MCP-style finish/deploy carryovers.
Use after planning and before implementation when you need a concrete, dependency-ordered task list. Turn the DR feature spec and plan into independently testable task slices with exact file paths and verification commands.