# implementation-pack

Builds a post-award project pack: applies the signed grant-agreement figures to a proposal baseline and produces files a project manager can run with.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 551 installs · ★ 3
- Author: gasserane
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/gasserane/personal-skills/tree/HEAD/skills/implementation-pack/SKILL.md
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/skills/implementation-pack

## What it does

The skill takes the baseline from your proposal and layers the signed grant agreement on top of it: budget, dates, revised targets. From there it writes a folder holding a six-tab `Implementation_Tracker.xlsx` with branding, a scaffold for the periodic technical report, and a README. A full project manager can work with the result without any AI in the loop.

It runs in steps. First it loads the donor profile from `ane_package/proposals/donor_profiles/<name>.json`, `cerv` by default. Then `load_baseline` pulls in the baseline; if none exists, the skill asks you for the proposal `handback.json` or a short brief. It will not make up work packages, indicators or partners. Next, `apply_awarded` merges the agreement figures and raises `BaselineError` on an unknown work package or an incoherence. When the grant is not awarded yet, that step is skipped and the Guide and README mark “baseline = submitted”.

Some boundaries matter up front. Your finance system of record, reporting through the official portal, and the authorising officer's approval stay with finance, the portal and that officer — this skill does not stand in for them. The Word report carries an AI-disclosure note, and AI is never listed as an author. If the output folder already holds hand-edited files, the skill treats your edits as canonical and does not regenerate everything from scratch.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill implementation-pack -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill implementation-pack -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill implementation-pack -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install gasserane/personal-skills implementation-pack
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill implementation-pack -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/gasserane/personal-skills --path skills/implementation-pack
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill implementation-pack -a opencode
```

### 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/gasserane/personal-skills/tree/HEAD/skills/implementation-pack/SKILL.md

## When to use it
- carry signed agreement figures onto the proposal baseline
- produce a branded Excel tracker for the project
- prepare a scaffold for the periodic technical report
- check that indicators still line up with the work packages
- hand a manager a pack they can run without AI

## Example prompts
- Build the implementation pack from the proposal baseline, donor cerv
- Run `/implementation-pack --donor cerv` and show me the output
- Apply the signed agreement figures to the baseline and rebuild the pack

## Similar
- [grants](https://affpapa.org/en/nevibecode/skills/grants.md) — skill · 355 installs
- [meeting-analyzer](https://affpapa.org/en/nevibecode/skills/meeting-analyzer.md) — skill · 576 installs
- [senior-pm](https://affpapa.org/en/nevibecode/skills/borghei-senior-pm.md) — skill · 364 installs
- [wiki-context-pack](https://affpapa.org/en/nevibecode/skills/wiki-context-pack.md) — skill · 1600 installs
- [Excel Sheet](https://affpapa.org/en/nevibecode/prompts/excel-sheet.md) — prompt · ★ 174676
- [flue](https://affpapa.org/en/nevibecode/skills/flue.md) — skill · 12600 installs

From the same set: [gasserane/personal-skills](https://affpapa.org/en/nevibecode/by/gasserane/personal-skills.md) — 13 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