← 返回 Skills 市场

Durable Files Weekly Review (Public)

Name: Durable Files Weekly Review (Public)
Author: andyylin

作者 Andy · GitHub ↗ · v1.0.0

cross-platform ✓ 安全检测通过

317

总下载

当前安装

版本数

在 OpenClaw 中安装

/install durable-files-weekly-review-public

功能描述

Run a weekly token-optimization audit for durable instruction files in any OpenClaw workspace, generate a markdown report, and propose approval-gated cleanup...

使用说明 (SKILL.md)

Durable Files Weekly Review (Sanitized / ClawHub)

Use this skill to audit durable instruction files and prepare cleanup proposals.

Default scope

Audit these files relative to a workspace root:

AGENTS.md
SOUL.md
USER.md
TOOLS.md
MEMORY.md
IDENTITY.md
PRIORITIES.md
SKILLS.md
projects.md

Run

python3 scripts/durable_files_review_generic.py --root .

Optional:

python3 scripts/durable_files_review_generic.py --root /path/to/workspace --out knowledge/reports/durable-files

Workflow

Run scanner.
Open generated report.
Summarize top token-heavy files + stale markers.
Propose cleanup in batches.
Require explicit user approval before any deletions.
Apply approved edits and post concise changelog.

Success output

Dated markdown report with metrics/findings
Clear approval queue for removals
No silent content removal

安全使用建议

This skill appears coherent and limited in scope: it reads the listed durable files in whatever root you point it at, generates a markdown report, and requires explicit approval before edits. Before running: (1) confirm the --root argument points to the intended workspace (avoid running against system or home directories), (2) review the generated report before applying any cleanup, and (3) consider running the script in a sandbox or test workspace first. Note: the script has a minor implementation quirk in its regex patterns (double-escaped backslashes) that may reduce stale-marker detection accuracy — you may want to inspect or test the patterns if you rely on automated detection.

功能分析

Type: OpenClaw Skill Name: durable-files-weekly-review-public Version: 1.0.0 The skill is designed for a weekly audit of specific markdown files within a workspace, generating a local report on file metrics and potential stale content. The Python script `durable_files_review_generic.py` only reads files from the specified `--root` directory and writes a markdown report locally; it does not perform any deletions, modifications, network calls, or data exfiltration. The `SKILL.md` instructions explicitly emphasize requiring user approval before any deletions, acting as a safeguard against prompt injection attempts to bypass approval. All content aligns with the stated purpose and lacks any indicators of malicious intent or harmful capabilities.

能力评估

✓ Purpose & Capability

Name/description, SKILL.md, and the included Python script are consistent: the script scans the listed durable files, estimates token counts, detects stale markers, and writes a report. The skill does not request unrelated credentials, binaries, or config paths.

ℹ Instruction Scope

Runtime instructions are narrowly scoped (run the included Python scanner on the workspace root and review its report). Note: the CLI accepts a --root argument, so whoever runs the tool can point it at any filesystem path; ensure the root parameter is set to the intended workspace to avoid scanning unrelated directories.

✓ Install Mechanism

No install spec (instruction-only with a bundled script). Nothing is downloaded or executed from remote URLs. The script runs locally with standard Python and writes a markdown file to the specified output directory.

✓ Credentials

No environment variables, credentials, or external endpoints are requested. The script only reads the specified filenames under the given root and writes a local report; this is proportionate to the stated purpose.

✓ Persistence & Privilege

The skill does not request always:true and does not modify other skills or global agent settings. It writes only its own report file and does not perform deletions without explicit user approval as stated in SKILL.md.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install durable-files-weekly-review-public
安装完成后，直接呼叫该 Skill 的名称或使用 /durable-files-weekly-review-public 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial public release: generic weekly durable-file audit with approval-gated cleanup workflow.

元数据

Slug durable-files-weekly-review-public

版本 1.0.0

许可证 —

累计安装 0

当前安装数 0

历史版本数 1

常见问题