skill-cleaner

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Skill Cleaner

Skill Cleaner 技能清理工具

Use this when trimming skill prompt budget, finding duplicate skills, auditing enabled/disabled skill roots, or deciding which skills/plugins to remove.

当你需要削减技能提示词预算、查找重复技能、审核启用/禁用的技能根目录，或决定移除哪些技能/插件时，可以使用本工具。

Workflow

工作流程

Run the analyzer from this skill directory or repo root:

bash

node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --months 3

Useful variants:

bash

node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --no-logs
node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --months 6 --max-log-mb 800 --deep-logs
node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --context-tokens 272000 --budget-percent 2 --no-logs
node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --root ~/Dropbox/boxd/skills --no-logs

Read the report in this order:

```
Skill Budget
```
: GPT-5.5 context size, 2% skills budget, Codex-budgeted usage, and pre-budget full-list pressure.
```
Description candidates
```
: long descriptions where relaxed grammar saves prompt budget.
```
Duplicates
```
: same skill name or near-identical description/body across Codex, plugin cache, repo siblings, and personal skill roots.
```
Unused candidates
```
: no recent
```
$skill
```
mention,
```
SKILL.md
```
read, or explicit skill-use trace in recent Codex/OpenClaw logs.
```
Root summary
```
: where skills came from and whether config marks them disabled.

Before deleting or editing:

Verify the kept copy exists and is loaded.
Prefer deleting repo-local or
```
agent-scripts
```
duplicates when Codex built-ins cover them.
Keep repo-local OpenClaw maintainer skills when they encode repo policy or live operations.
Preserve trigger nouns in descriptions: product, tool, action, object.

bash

node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --months 3

实用命令变体：

bash

node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --no-logs
node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --months 6 --max-log-mb 800 --deep-logs
node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --context-tokens 272000 --budget-percent 2 --no-logs
node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --root ~/Dropbox/boxd/skills --no-logs

按以下顺序阅读报告：

```
技能预算
```
：GPT-5.5上下文窗口大小、2%技能预算占比、Codex预算使用情况，以及预算前完整技能列表的压力。
```
待精简描述候选
```
：可通过简化语法节省提示词预算的冗长描述。
```
重复技能
```
：在Codex、插件缓存、仓库同级目录和个人技能根目录中存在同名或描述/内容几乎完全一致的技能。
```
未使用技能候选
```
：近期Codex/OpenClaw日志中无
```
$skill
```
提及、
```
SKILL.md
```
读取记录或明确的技能使用痕迹。
```
根目录汇总
```
：技能的来源以及配置中是否标记为禁用。

删除或编辑前注意事项：

确认保留的技能副本已存在且已加载。
若Codex内置技能已覆盖功能，优先删除仓库本地或
```
agent-scripts
```
中的重复技能。
若仓库本地的OpenClaw维护者技能包含仓库策略或实时操作逻辑，请予以保留。
保留描述中的触发名词：产品、工具、动作、对象。

Analyzer Notes

分析器说明

The script mirrors Codex's model-visible line shape:
```
- name: description (file: path)
```
.
It applies Codex-like frontmatter rules: YAML frontmatter only, default name from parent dir, single-line sanitized
```
name
```
and
```
description
```
.
It follows Codex
```
core-skills/src/render.rs
```
: 2% of raw
```
context_window
```
, token cost
```
ceil(utf8_bytes / 4)
```
, then full descriptions -> equal description truncation -> omitted minimum lines.
It reads
```
~/.codex/models_cache.json
```
for GPT-5.5
```
context_window
```
; fallback is 272,000 tokens and 2%.
It scans only normal Codex/plugin/repo skill roots by default. Extra folders such as Dropbox archives are included only with
```
--root <path>
```
.
It realpath-dedupes roots, so symlinked roots such as
```
~/.codex/skills/agent-scripts -> ~/Projects/agent-scripts/skills
```
do not create false duplicates.
For duplicate names, it reports description/body similarity and suggests deletion candidates only when bodies are near copies. Keep priority defaults to direct Codex system skills, then direct Codex skills, then plugin skills, then personal/repo copies.
It scans
```
~/.codex/history.jsonl
```
and recent
```
~/.codex/sessions/**/*.jsonl
```
by default. Add
```
--deep-logs
```
for archived sessions and common OpenClaw/Clawd log folders.
Usage evidence is heuristic:
```
$skill
```
,
```
Use $skill
```
, and paths like
```
skills/<name>/SKILL.md
```
.

脚本镜像Codex模型可见的行格式：
```
- name: description (file: path)
```
。
它应用类Codex的前置规则：仅支持YAML前置内容，默认名称取自父目录，
```
name
```
和
```
description
```
需为单行净化后的内容。
它遵循Codex
```
core-skills/src/render.rs
```
的逻辑：占用原始
```
context_window
```
的2%，token成本按
```
ceil(utf8_bytes / 4)
```
计算，处理顺序为完整描述→等长描述截断→省略最少行数。
它从
```
~/.codex/models_cache.json
```
读取GPT-5.5的
```
context_window
```
值； fallback值为272,000 tokens和2%占比。
默认仅扫描常规的Codex/插件/仓库技能根目录。仅当使用
```
--root <path>
```
参数时，才会包含Dropbox归档等额外文件夹。
它会通过真实路径对根目录去重，因此像
```
~/.codex/skills/agent-scripts -> ~/Projects/agent-scripts/skills
```
这样的符号链接根目录不会产生虚假重复项。
对于同名技能，仅当内容几乎完全相同时，才会报告描述/内容相似度并建议删除候选。保留优先级默认顺序为：Codex直接系统技能→Codex直接技能→插件技能→个人/仓库副本。
默认扫描
```
~/.codex/history.jsonl
```
和近期的
```
~/.codex/sessions/**/*.jsonl
```
。添加
```
--deep-logs
```
参数可扫描归档会话及常见的OpenClaw/Clawd日志文件夹。
使用证据为启发式判断：包括
```
$skill
```
、
```
Use $skill
```
以及
```
skills/<name>/SKILL.md
```
这类路径。

Output Policy

输出策略

Suggest first; edit only when the user asks.
If asked to apply cleanup, make small grouped commits: descriptions, deletes, config disables.
Do not delete ignored/untracked skill dirs without naming the destination or confirming they are disposable.

先给出建议；仅在用户要求时进行编辑。
若用户要求执行清理操作，需进行分组小提交：精简描述、删除技能、禁用配置。
若未指定目标位置或未确认可丢弃，请勿删除已忽略/未追踪的技能目录。