Skill Improve

Improve existing skills after use. When Claude uses a skill and discovers issues (outdated steps, missing edge cases, unclear instructions, wrong assumptions), suggest "/skill-improve" after the current task completes. Also use when user says "fix this skill", "this skill is wrong", "update skill", or "/skill-improve <skill-name>".

65 stars 6 forksProductivity & Notes Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add Yrzhe/claude-skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Yrzhe/claude-skills --skill skill-improve
Manual install
git clone --depth 1 https://github.com/Yrzhe/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/plugins/skill-improve/skills/skill-improve ~/.claude/skills/skill-improve

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Skill Improve — Post-Use Skill Maintenance

Improve existing skills based on real usage experience. Always finish the current task first.

## Trigger Rules

- **After task completion**: If a skill was used and had issues, suggest: "The `<skill-name>` skill had some gaps — want me to `/skill-improve` it?"
- **Manual**: `/skill-improve <skill-name>` or `/skill-improve` (defaults to most recently used skill in session)
- **NEVER interrupt** the current task to improve a skill. Finish first, improve after.

## Improvement Flow

### 1. Identify Target

Determine which skill to improve:
- If `<skill-name>` provided, use that
- If no argument, use the most recently invoked skill in this session
- If no skill was used, ask the user which skill to improve

### 2. Read Current Skill

Read the target skill's `SKILL.md` and any bundled resources (`scripts/`, `references/`, `assets/`).

### 3. Diagnose Issues

Compare the skill's instructions against actual execution experience. Categorize problems:

| Category | Example |
|----------|---------|
| **Outdated** | Tool/API changed, deprecated method |
| **Missing** | Edge case encountered that skill didn't cover |
| **Redundant** | Steps Claude already knows, wasting context |
| **Unclear** | Ambiguous instruction that caused wrong action |
| **Wrong** | Incorrect assumption or factual error |

### 4. Generate Diff Preview

Show the user exactly what will change:
- Quote the original text
- Show the proposed replacement
Read the full skill on GitHub

Details

Skill name
skill-improve
Path
plugins/skill-improve/skills/skill-improve/SKILL.md
License
MIT
Repo updated
27 October 2026

FAQ

What does the Skill Improve skill do?

Improve existing skills after use. When Claude uses a skill and discovers issues (outdated steps, missing edge cases, unclear instructions, wrong assumptions), suggest "/skill-improve" after the current task completes. Also use when user says "fix this skill", "this skill is wrong", "update skill", or "/skill-improve <skill-name>".

How do I install the Skill Improve skill?

Claude Code plugin: /plugin marketplace add Yrzhe/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Skill Improve popular?

It lives in Yrzhe/claude-skills, which has 65 GitHub stars and 6 forks.

Related skills

Adaptive Compaction

65

Yrzhe/claude-skills

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without chang

AI, LLMs & Agents

Agentlog

65

Yrzhe/claude-skills

Load when the user wants to view, sync, or analyze multi-agent activity across multiple devices — Claude Code / Codex / Cursor / Maestri / browser-use sessions captured to a shared GitHub-synced pool, OR wants a distilled per-project context document so a fresh agent in a different tool can pick up where another left off. Triggers on "agentlog X" commands, "what did I do today across all my agents", "show me my pool", "sync the pool", "拉一下另一台机器上的 agent 记录", "看看 vps 上跑的", "跨设备 agent log", "跨工具上下文", "switch from Codex to Claude Code", "AGENTS.md / CLAUDE.md", "项目状态文档", "agent context". Do NOT lo

AI, LLMs & Agents

Akshare a Shares

65

Yrzhe/claude-skills

针对中国A股的行情与数据查询(基于本地 akshare 源代码与API映射)。当用户请求获取A股实时行情、历史K线(日/周/月)、分钟级分时(1/5/15/30/60)、复权数据(前复权/后复权)、股东户数(含详情)、以及巨潮资讯公告披露结果时使用本Skill。默认优先使用东方财富(EM)接口;如用户指定新浪(Sina)来源或需要特定接口,则按映射调用对应函数。可使用内置脚本输出CSV/JSON,或内联Python调用。

Software Development

Sleight of Hand

113

Hmbown/Wizards-of-the-Ghosts

Sleight of Hand is not about solving a problem — the solution is already known. It is about executing a known change with zero collateral damage. The skill is precision, not creativity.

Productivity & Notes11

Seamless Isometric Terrain

49

0xheycat/isometric-game-skills

Generate seamless, tileable isometric terrain tiles (Hay Day / farm-game style) with ComfyUI on consumer GPUs (RTX 3060 12GB). Use this skill whenever the user wants to create ground tiles (grass, dirt, water, road, plowed field, sand, stone, snow), build a tilemap that connects without seams or gaps, fix tiles that have visible edges/mismatched shapes/mixed colors, or set up the proven "Resep D" isometric tile workflow, prompts, and post-processing (transparent PNG via rembg/SAM).

Productivity & NotesIn 1 list

Teleport

113

Hmbown/Wizards-of-the-Ghosts

Teleport is FULL-CONTEXT migration, not partial transformation. The defining characteristic is that EVERYTHING must move together and keep working: data, dependencies, auth, traffic routing, background jobs, secrets, and human workflows. The old system must remain recoverable until the new one is proven. This spell IS: Database migrations (RDS→Cloud SQL, self-managed→Atlas), cloud provider moves (on-prem→AWS, Heroku→K8s), environment promotions (staging→prod), account/tenant consolidations, platform migrations (Jenkins→GitHub Actions, SendGrid→SES), identity migrations (AD→Azure AD), cluster u

Productivity & Notes11

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.