一键在 Manus 中运行任何 Skill

cleanup-reset

星标16

分支6

更新时间2026年2月11日 13:13

Reset local experiment state to a fresh slate by clearing runs, prediction outputs, scaling snapshots, and database index files under data/.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

brainqub3

brainqub3/agent-labs

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

cleanup-reset

Use this skill when

You need to start a new experiment cycle with no prior runs or batch index state.
Dashboard and scenario analysis should ignore all historical run artefacts.

Default cleanup scope

Clears data/runs, data/db, data/scaling, and data/predictions contents.
Preserves data/scenarios, data/.gitkeep, and data/paper_extracted_text.txt by default.

Steps

Ensure no dashboard process is actively writing to data/db/brainqub3.sqlite.
Run:

uv run python .claude/skills/cleanup-reset/scripts/reset_data.py

Verify:

data/runs empty
data/db empty
data/scaling empty
data/predictions empty (if present)

Optional flags

Full wipe including scenarios and extracted paper text:

uv run python .claude/skills/cleanup-reset/scripts/reset_data.py --wipe-scenarios --wipe-paper-text

Preview only:

uv run python .claude/skills/cleanup-reset/scripts/reset_data.py --dry-run

同仓库更多 Skills

同仓库

scenario

brainqub3/agent-labs

Create and execute scenario YAML files for architecture what-if predictions.

2026-02-1216

arena

brainqub3/agent-labs

Prepare and run evaluator-gated SAS and MAS experiments with explicit batch control and mandatory elasticity calibration for scenario scaling.

2026-02-1116

task-author

brainqub3/agent-labs

Create or repair Brainqub3 task packages that must pass evaluator tests before runs, including both fabricated instances and user-provided data workflows.

2026-02-1016

eval-builder

brainqub3/agent-labs

Build or repair task evaluators and evaluator tests with deterministic-first strategy.

2026-02-0916

report

brainqub3/agent-labs

Generate markdown reports with observed metrics, predicted metrics, and architecture recommendations.

2026-02-0916

name	cleanup-reset
description	Reset local experiment state to a fresh slate by clearing runs, prediction outputs, scaling snapshots, and database index files under data/.
allowed-tools	["Read","Edit","Bash"]

cleanup-reset

Use this skill when

You need to start a new experiment cycle with no prior runs or batch index state.
Dashboard and scenario analysis should ignore all historical run artefacts.

Default cleanup scope

Clears data/runs, data/db, data/scaling, and data/predictions contents.
Preserves data/scenarios, data/.gitkeep, and data/paper_extracted_text.txt by default.

Steps

Ensure no dashboard process is actively writing to data/db/brainqub3.sqlite.
Run:

uv run python .claude/skills/cleanup-reset/scripts/reset_data.py

Verify:

data/runs empty
data/db empty
data/scaling empty
data/predictions empty (if present)

Optional flags

Full wipe including scenarios and extracted paper text:

uv run python .claude/skills/cleanup-reset/scripts/reset_data.py --wipe-scenarios --wipe-paper-text

Preview only:

uv run python .claude/skills/cleanup-reset/scripts/reset_data.py --dry-run