Claude
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
64 lines
3.0 KiB
Markdown
64 lines
3.0 KiB
Markdown
# Executive Update Skill
|
|
|
|
Produce a stakeholder update that busy executives will actually read — structured around what they care about: decisions, risks, and numbers.
|
|
|
|
## Required Inputs
|
|
|
|
Ask the user for these if not provided:
|
|
- **Product update or notes** (raw input to transform — even bullet points work)
|
|
- **Audience** (CEO, board, specific exec, or general leadership)
|
|
- **Period** (this week / sprint / month / quarter)
|
|
- **Key metrics** (what numbers matter to this audience)
|
|
|
|
## Executive Communication Principles
|
|
- Lead with the headline, not the context
|
|
- Every update should answer: "So what does this mean for the business?"
|
|
- Flag decisions needed clearly — don't bury asks in paragraphs
|
|
- Be honest about risks — executives hate surprises more than bad news
|
|
|
|
## Process
|
|
1. Read the full product update provided
|
|
2. Identify: key metric movements, decisions required, risks to flag, wins to celebrate
|
|
3. Write in reverse pyramid style — most important first
|
|
4. Limit to 250 words maximum for the main body
|
|
5. Add a "Decisions Needed" section with clear options and your recommendation
|
|
6. **Validate** — Confirm every decision needed has a specific option and recommendation (not just "TBD"), and every risk has a mitigation or watch plan
|
|
|
|
## Output Structure
|
|
|
|
### Product Update — [Date / Sprint / Month]
|
|
**Headline:** [One sentence on the most important thing]
|
|
|
|
**By the Numbers:**
|
|
- [Metric 1]: [value] ([vs. target / last period])
|
|
- [Metric 2]: [value] ([vs. target / last period])
|
|
- [Metric 3]: [value] ([vs. target / last period])
|
|
|
|
**Progress This Period:**
|
|
[3-4 bullet points, outcome-focused not activity-focused]
|
|
|
|
**Risks & Watch Items:**
|
|
[2-3 bullets — be direct, include mitigation]
|
|
|
|
**Decisions Needed:**
|
|
1. [Decision] — Options: [A] or [B] — Recommendation: [your view] — Needed by: [date]
|
|
|
|
**What's Next:**
|
|
[2-3 bullets on next period priorities]
|
|
|
|
## Quality Checks
|
|
|
|
- [ ] Whole update is under 250 words (if not, cut ruthlessly)
|
|
- [ ] Every metric includes a comparison point (vs. target or last period)
|
|
- [ ] Every risk has a mitigation or watch action
|
|
- [ ] Every decision needed has at least two options and a recommendation
|
|
- [ ] Written for a CFO or CEO — no jargon, all outcomes
|
|
|
|
## Anti-Patterns
|
|
|
|
- [ ] Do not lead with context or background — executives read the headline first; bury the important thing below two sentences of setup and they will miss it
|
|
- [ ] Do not present metrics without a comparison point — a number without context (vs. target, vs. last period) cannot be interpreted and will prompt follow-up questions
|
|
- [ ] Do not soften or spin risks — executives rely on these updates to make resource and escalation decisions; sanitised risk sections destroy the update's utility
|
|
- [ ] Do not present a "Decisions Needed" item without a recommendation — asking an executive to decide without your view forces them to do the analytical work the PM should have done
|
|
- [ ] Do not exceed 250 words in the main body — length signals the author has not done the compression work; every word over 250 reduces the chance the update is read
|