- name
SKILL.md
技能文件保留在发布者的仓库中。
在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add notque/vexjoy-agent --skill condense -a cursor -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add notque/vexjoy-agent --skill condense -a claude-code -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add notque/vexjoy-agent --skill condense -a codex -y在终端中粘贴复制的命令。它会把这个 SKILL.md 安装到对应的智能体中。
npx skills add notque/vexjoy-agent --skill condense -a grok -y在 Grok Bot 聊天中发送复制的消息。Bot 会从 GitHub 获取这个 SKILL.md,并添加到你所有 Bot 共享的技能中。
Install this skill: https://github.com/notque/vexjoy-agent/tree/HEAD/skills/code-quality/condense来自发布者
Strip prose filler from .md files. Preserve every instruction. This skill practices what it preaches.
Identify targets.
agents/*.md). Expand, list matches, confirm with user.Mechanical pre-pass (deterministic, run before LLM condensing): strip trailing whitespace and consecutive blank lines that inflate Opus token counts. The script handles the mechanical reduction so the LLM phase focuses on prose density.
python3 scripts/check-whitespace.py --fix <target-file-or-dir> # 0=clean, 1=violations fixed
Run on the scoped targets (defaults to agents/**/*.md and skills/**/*.md when no path given). Then proceed to the LLM pass on the same files.
Gate: At least one target file identified and readable; mechanical pre-pass run.
For each file:
KEEP (never cut):
CUT:
STYLE: Short sentences. Active voice. Concrete words. If you can cut a word without losing an instruction, cut it.
Before cutting any sentence: "If I remove this, does the reader lose an instruction, rule, or decision?" No = cut. Yes = keep.
Do not reorganize sections, change meaning, add ideas, alter paths/commands, drop tables or code blocks, or modify YAML frontmatter values.
For each condensed file:
python3 -c "import yaml; yaml.safe_load(open('<file>').read().split('---')[1])"
| File | Before | After | Reduction | table with word counts.Gate: YAML parses. No instructions lost. Reduction reported.
No prose to cut: Report 0% reduction, move to next file.
Instruction removed: Re-read original, restore missing instruction, re-verify.
YAML broken: Restore original frontmatter verbatim, re-condense body only.
Non-.md file: Skip with warning.
Maximize information density: preserve all instructions, remove prose filler.
---name: condensedescription: Maximize information density: preserve all instructions, remove prose filler.---# skills/code-quality/condense/SKILL.md常见问题
从发布者处下载 skills/code-quality/condense/SKILL.md,或复制路径后打开仓库。PlugMCP 只收录该技能,不托管文件。
发布者将它存放在 https://github.com/notque/vexjoy-agent。
Claude、Cursor、Codex 和 Grok Build 可以读取你从发布者仓库添加的 SKILL.md。在聊天中发送技能的 GitHub 文件夹链接,Grok Bot 就会安装它。