ワンクリックでManusで任意のスキルを実行

aitask-trail

スター6

フォーク1

更新日2026年7月24日 11:54

Create, refresh, or show an implementation trail — a durable, wave-structured, evidence-backed task-sequencing artifact stored via ait artifact.

インストール

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。

Manusで実行

ソース

beyondeye

beyondeye/aitasks

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

関連職種SOC

SOC 職業分類に基づく

ソフトウェア開発者コンピュータ・数学職·SOC 15-1252

ファイルエクスプローラー

2 ファイル

SKILL.md

readonly

name	aitask-trail
description	Create, refresh, or show an implementation trail — a durable, wave-structured, evidence-backed task-sequencing artifact stored via ait artifact.

This is a profile-aware skill stub. 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 trail and use the single-line stdout as <profile>.
Render per-profile variant. Run: ./.aitask-scripts/aitask_skill_render.sh aitask-trail --profile <profile> --agent claude No-op if the per-profile SKILL.md is already up to date.
Dispatch via Read-and-follow. Read the file at .claude/skills/aitask-trail-<profile>-/SKILL.md and execute its instructions as if they were this skill, forwarding the (possibly stripped) ARGUMENTS unchanged.

このリポジトリの他の Skills

同じリポジトリ

aitask-trail

beyondeye/aitasks

Create, refresh, or show an implementation trail — a durable, wave-structured, evidence-backed task-sequencing artifact stored via ait artifact.

2026-07-246

aitask-shadow

beyondeye/aitasks

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.

2026-07-246

aitask-work-report

beyondeye/aitasks

Draft a manager-facing work report from selected board columns.

2026-07-246

aitask-pickrem-remote

beyondeye/aitasks

Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.

2026-07-236

aitask-pickweb-remote

beyondeye/aitasks

Pick and implement a task on Claude Code Web. Zero interactive prompts. No cross-branch operations — stores task data locally in .aitask-data-updated/.

2026-07-236

aitask-pickrem-remote

beyondeye/aitasks

Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.

2026-07-236

name	aitask-trail
description	Create, refresh, or show an implementation trail — a durable, wave-structured, evidence-backed task-sequencing artifact stored via ait artifact.

This is a profile-aware skill stub. 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 trail and use the single-line stdout as <profile>.
Render per-profile variant. Run: ./.aitask-scripts/aitask_skill_render.sh aitask-trail --profile <profile> --agent claude No-op if the per-profile SKILL.md is already up to date.
Dispatch via Read-and-follow. Read the file at .claude/skills/aitask-trail-<profile>-/SKILL.md and execute its instructions as if they were this skill, forwarding the (possibly stripped) ARGUMENTS unchanged.