572b8acf8c
Make the library multi-platform without duplicating content. Each skills/<name>/SKILL.md body remains the single source of truth; a new generator renders platform-ready exports from it. - scripts/build-exports.mjs — dependency-free Node generator with a PLATFORMS registry so new platforms (Gemini, Cursor, …) are a few lines. Ships ChatGPT exports at exports/chatgpt/<bundle>/<skill>/SYSTEM_PROMPT.md (172 skills), plus generated index READMEs. Supports --platform and --check. - exports/ — generated ChatGPT system prompts, ready to paste into a Custom GPT. - .github/workflows/check-generated.yml — fails a PR if exports or web/skills.json drift from the source skills. - README "Works With" now documents the ready-to-use exports and regen command. - CHANGELOG + SKILL-AUTHORING-STANDARD note the generated artifacts. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016JWn5jRD5tcEFKrubjQ6Px
74 lines
2.8 KiB
Markdown
74 lines
2.8 KiB
Markdown
# Financial Model Narrative Skill
|
|
|
|
Turns financial model outputs into a clear, structured written narrative suitable for board packs, investor updates, or management reporting.
|
|
|
|
## Required Inputs
|
|
- **Financial data** (paste key figures: revenue, costs, margins, EBITDA, cash)
|
|
- **Period covered** (month / quarter / annual / multi-year)
|
|
- **Audience** (board / investors / management / bank / internal)
|
|
- **Key message** (what is the headline story?)
|
|
- **Actuals vs budget / prior period?** (comparison context)
|
|
|
|
## Output Structure
|
|
|
|
### 1. Headline Summary
|
|
3-5 sentences. The financial story in plain English. Lead with the most important insight — not "revenue was X" but what that figure means.
|
|
|
|
### 2. Revenue
|
|
- Performance vs prior period / budget
|
|
- Key drivers: what caused the movement
|
|
- Risks or opportunities in the revenue line
|
|
|
|
### 3. Costs and Margins
|
|
- Gross margin: % and trend
|
|
- Key cost movements and why
|
|
- EBITDA performance and drivers
|
|
- One-off items clearly flagged
|
|
|
|
### 4. Cash and Balance Sheet
|
|
- Cash position and movement
|
|
- Runway (for startups)
|
|
- Key working capital movements
|
|
|
|
### 5. Variance Analysis
|
|
For each significant variance:
|
|
|
|
**[Line item] — Over/Under by [amount]**
|
|
- **Cause:** [Plain English explanation]
|
|
- **Permanent or temporary?** One-time / Structural
|
|
- **Action being taken:** [If applicable]
|
|
|
|
### 6. Forward-Looking Commentary
|
|
- Expected next period
|
|
- Key risks to forecast
|
|
- Key opportunities
|
|
- Any reforecast or guidance change
|
|
|
|
## Writing Rules
|
|
- Never just restate a number — always explain what it means
|
|
- Flag variances over 10% automatically
|
|
- Use past tense for actuals, conditional for forecast
|
|
- One insight per paragraph
|
|
|
|
## Quality Checks
|
|
|
|
- [ ] Headline summary leads with meaning, not just the number
|
|
- [ ] Every significant variance has a cause, permanence, and action
|
|
- [ ] Forward-looking commentary includes specific risks and opportunities
|
|
- [ ] Audience-appropriate language (board vs investor vs management)
|
|
- [ ] One-off items clearly distinguished from recurring items
|
|
|
|
## Anti-Patterns
|
|
|
|
- [ ] Do not list numbers without explaining what is driving them — narrative must go beyond restating the figures
|
|
- [ ] Do not mix one-off items with recurring performance without clearly distinguishing them
|
|
- [ ] Do not write the same level of detail for all line items — focus depth on the items that matter most
|
|
- [ ] Do not omit forward-looking commentary — a narrative without outlook is incomplete for board or investor audiences
|
|
- [ ] Do not use technical accounting language without translation — the audience is executives, not accountants
|
|
|
|
## Example Trigger Phrases
|
|
- "Write a financial narrative for these results: [paste numbers]"
|
|
- "Turn this P&L into a board narrative"
|
|
- "Write the finance section of our board pack"
|
|
- "Explain these financial results in plain English"
|