ワンクリックで
aitask-pickrem
Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.
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。
メニュー
Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.
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 | aitask-pickrem |
| description | Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls. |
This is a profile-aware skill stub. Pre-rendered variants for headless
profiles (currently remote) are committed to the repo so the skill works in
environments where the rendering toolchain (minijinja) is unavailable —
e.g., Claude Code Web. Other profiles render on demand. Execute these steps
in order, then stop:
Resolve active profile. Parse ARGUMENTS for --profile <name>. If
found, use that as <profile> and remove the --profile <name> pair
from ARGUMENTS. Otherwise run:
./.aitask-scripts/aitask_skill_resolve_profile.sh pickrem
and use the single-line stdout as <profile>.
Render only if needed. If the committed pre-rendered file at
.claude/skills/aitask-pickrem-<profile>-/SKILL.md already exists, skip
this step. Otherwise run:
./.aitask-scripts/aitask_skill_render.sh aitask-pickrem --profile <profile> --agent claude
(requires ait setup to have installed minijinja).
Dispatch via Read-and-follow. Read the file at
.claude/skills/aitask-pickrem-<profile>-/SKILL.md and execute its
instructions as if they were this skill, forwarding the (possibly
stripped) ARGUMENTS unchanged.
Create, refresh, or show an implementation trail — a durable, wave-structured, evidence-backed task-sequencing artifact stored via ait artifact.
Create, refresh, or show an implementation trail — a durable, wave-structured, evidence-backed task-sequencing artifact stored via ait artifact.
Shadow companion for a followed coding agent — reads its captured terminal output and, in one instruction-driven flow, explains it, helps answer an AskUserQuestion, or critically interrogates a plan. Advisory-only. Spawned by minimonitor; not a task-implementation command.
Draft a manager-facing work report from selected board columns.
Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.
Pick and implement a task on Claude Code Web. Zero interactive prompts. No cross-branch operations — stores task data locally in .aitask-data-updated/.