How do I install the Jiepi Skill skill?

Run npx skillmds@latest add pluviobyte/jiepi-skill in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Jiepi Skill safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Jiepi Skill?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Jiepi Skill free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Jiepi Skill?

pluviobyte (@pluviobyte) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Jiepi Skill by pluviobyte — Agent Skill

Name: Jiepi Skill
Rating: 4.2 (5 reviews)
Author: pluviobyte

Jiepi Skill

洁癖 Skill: Audit installed AI agent skills across Codex, Claude Code, Cursor, and optional project-local skill folders. Use when the user asks which skills are installed, how often Claude Code/Codex/Cursor used skills, whether a skill was used recently, which skills are stale or unused, or wants cleanup/removal/disable recommendations for skills.

pluviobyte d0ca440 3 files · 8.7 KB Updated Sep 17, 2026

File contents

洁癖 Skill

Overview

Use this skill to inventory installed skills, count confirmed historical usage, show recent activity, and produce cleanup recommendations. Prefer the bundled script for deterministic scanning instead of hand-writing ad hoc searches.

Workflow

Run scripts/audit_skill_usage.py from this skill folder.

Use the default scan for installed/synced skills:

python3 scripts/audit_skill_usage.py --format markdown

Add --include-project-local only when the user explicitly wants repository-local skills under Desktop/Documents included. This can find many source/test/example skills that are not globally installed.
Use --days N to define the recent-use window. Default is 30 days.

Save a report when useful:

python3 scripts/audit_skill_usage.py --format markdown --output /tmp/skill-usage.md

Counting Rules

Treat the default call count as confirmed usage: a historical transcript or rollout explicitly referenced/read the skill's SKILL.md.
Do not count system/developer skill lists as usage.
Count each skill at most once per log line or tool call.
Prefer cleanup suggestions phrased as keep, review, or cleanup-candidate; do not delete files automatically unless the user separately asks for removal.
For plugin-provided skills, suggest disabling the plugin or reviewing plugin value before deleting cache files.

Interpreting Results

keep: used recently or used often enough historically.
review: used before, but not inside the recent-use window.
cleanup-candidate: no confirmed usage found in available histories.
scope: distinguishes codex, claude, cursor, and project-local sources so installed tools are not mixed with repository examples.

When presenting results, lead with totals, the top used skills, and the cleanup candidates. Mention the counting rule so the user understands that unconfirmed use may be undercounted.

---name: jiepi-skilldescription: 洁癖 Skill: Audit installed AI agent skills across Codex, Claude Code, Cursor, and optional project-local skill folders. Use when the user asks which skills are installed, how often Claude Code/Codex/Cursor used skills, whether a skill was used recently, which skills are stale or unused, or wants cleanup/removal/disable recommendations for skills.---# 洁癖 Skill## OverviewUse this skill to inventory installed skills, count confirmed historical usage, show recent activity, and produce cleanup recommendations. Prefer the bundled script for deterministic scanning instead of hand-writing ad hoc searches.## Workflow1. Run `scripts/audit_skill_usage.py` from this skill folder.2. Use the default scan for installed/synced skills: ```bash python3 scripts/audit_skill_usage.py --format markdown ```3. Add `--include-project-local` only when the user explicitly wants repository-local skills under Desktop/Documents included. This can find many source/test/example skills that are not globally installed.4. Use `--days N` to define the recent-use window. Default is 30 days.5. Save a report when useful: ```bash python3 scripts/audit_skill_usage.py --format markdown --output /tmp/skill-usage.md ```## Counting Rules- Treat the default call count as **confirmed usage**: a historical transcript or rollout explicitly referenced/read the skill's `SKILL.md`.- Do not count system/developer skill lists as usage.- Count each skill at most once per log line or tool call.- Prefer cleanup suggestions phrased as `keep`, `review`, or `cleanup-candidate`; do not delete files automatically unless the user separately asks for removal.- For plugin-provided skills, suggest disabling the plugin or reviewing plugin value before deleting cache files.## Interpreting Results- `keep`: used recently or used often enough historically.- `review`: used before, but not inside the recent-use window.- `cleanup-candidate`: no confirmed usage found in available histories.- `scope`: distinguishes `codex`, `claude`, `cursor`, and `project-local` sources so installed tools are not mixed with repository examples.When presenting results, lead with totals, the top used skills, and the cleanup candidates. Mention the counting rule so the user understands that unconfirmed use may be undercounted.

Frequently asked questions