# improvement-plan

The improvement-plan Claude Code skill turns a composite resume and profile score into a ranked list of fixes. It runs after scoring or when asked what to address first.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 73 repo stars
- Author: Jerome Hardaway, Vets Who Code
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Vets-Who-Code/ai-era-job-kit/tree/HEAD/skills/improvement-plan/SKILL.md
- Updated: 2026-11-11
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/improvement-plan

## What it does

The skill builds a prioritized improvement plan from a composite score. A failed resume gate comes first; remaining sections are ranked by points left, using each section’s weight and its gap to 100. The plan lists failed checks and their fixes, with machine and human scores averaged.

Run `python3 $KIT/scripts/scorecard.py plan --composite composite.json --md plan.md` to read `composite.json` and write `plan.md`. Work starts with `portfolio.json` and `brag/entries`, then the resume, LinkedIn, GitHub, and portfolio surfaces are updated. Numbers and skills must be backed by evidence; an unproven skill belongs on a build list, not in a claim.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add Vets-Who-Code/ai-era-job-kit
```
In the agent chat (not a shell):
```text
/plugin install ai-era-job-kit@ai-era-job-kit
```
This installs the whole ai-era-job-kit plugin with all its skills

2. **Skills CLI (Vercel)**
```bash
npx skills add Vets-Who-Code/ai-era-job-kit --skill improvement-plan -a claude-code
```

3. **Manually: put the files in place**
- File: `~/.claude/skills/improvement-plan/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/improvement-plan/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add Vets-Who-Code/ai-era-job-kit --skill improvement-plan -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/improvement-plan/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add Vets-Who-Code/ai-era-job-kit --skill improvement-plan -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/improvement-plan/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install Vets-Who-Code/ai-era-job-kit skills/improvement-plan
```

2. **Manually: put the files in place**
- File: `.github/skills/improvement-plan/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add Vets-Who-Code/ai-era-job-kit --skill improvement-plan -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/Vets-Who-Code/ai-era-job-kit --path skills/improvement-plan
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/improvement-plan/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/Vets-Who-Code/ai-era-job-kit/tree/HEAD/skills/improvement-plan/SKILL.md

## When to use it
- rank failed checks by likely score gain
- identify skills that could lift a resume score
- spot mismatches across a resume, LinkedIn, GitHub, and a portfolio
- turn assessment gaps into specific edits

## Example prompts
- Use the composite score to draft an improvement plan and rank the first fixes.
- Read `composite.json` and write prioritized edits to `plan.md`.
- Compare the resume, LinkedIn, GitHub, and portfolio, then list their mismatches.

## Similar
- [reliability-improvement-plan](https://affpapa.org/en/nevibecode/commands/reliability-improvement-plan.md) — command · ★ 280 repo stars
- [event-continuous-improvement](https://affpapa.org/en/nevibecode/skills/event-continuous-improvement.md) — skill · 6600 installs
- [self-improvement](https://affpapa.org/en/nevibecode/skills/self-improvement.md) — skill · 2100 installs
- [auto-paper-improvement-loop](https://affpapa.org/en/nevibecode/skills/auto-paper-improvement-loop.md) — skill · 596 installs
- [self-improvement-ci](https://affpapa.org/en/nevibecode/skills/self-improvement-ci.md) — skill · 550 installs
- [self-improvement-loops](https://affpapa.org/en/nevibecode/skills/self-improvement-loops.md) — skill · 194 installs

From the same set: [vets-who-code/ai-era-job-kit](https://affpapa.org/en/nevibecode/by/vets-who-code/ai-era-job-kit.md) — 18 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
