Install
$ agentstack add skill-amey-thakur-ai-skills-six-pager-narrative ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Six-pager narrative
Amazon traded slide decks for a six-page prose memo because bullets let a presenter hide thin logic behind delivery. Full sentences force the connective reasoning that a bullet lets you skip, and the gaps show. The meeting opens with everyone reading in silence, so the room reacts to the argument on the page, not to how confidently it was pitched.
Method
- Hold the line at six pages of narrative. The cap is the discipline: it
forces you to decide what matters and cut the rest. Push data, dashboards, and detail into appendices that do not count against the six, and never shrink the font to smuggle in more.
- Write in paragraphs, not bullets. Each claim becomes a sentence with a
subject and a verb, so "improved efficiency" has to say what improved, by how much, and why. If a section only works as bullets, the connective logic is still missing.
- Build it as an argument that lands on an ask. Situation, complication,
options, recommendation, then the specific thing you want the room to approve. A memo that informs without asking has wasted the most expensive hour on the calendar.
- Move every number to the appendix and cite it inline. The narrative makes
the case; the appendix lets a skeptic check it. Charts live there with axes labeled and sources named, so a reviewer can trace any figure without breaking the flow of the argument.
- Start the meeting with ten to twenty minutes of silent reading. Everyone
reads the same document at the same time, in the room, so no one bluffs through a skim. It also ends the meeting where the author narrates slides while the room waits.
- Collect comments in the margins, then debate the hard parts. Reviewers
mark up the doc as they read; discussion goes to the objections and the decision, not a page-by-page recap. The author's job in the room is to defend the reasoning, not to perform it.
Checks
- Does the memo make an ask, or does it stop at description?
- Can every quantitative claim in the narrative be traced to a labeled appendix
exhibit?
- Would the argument survive being read cold by someone who never heard you talk
about it?
Boundaries
The six-pager is for decisions and reviews, not for pitching a brand-new product to customers: for that, use the prfaq-working-backwards skill. This is Amazon's format and cadence, and other companies handle pre-reads differently, so match the local norm on length and on whether reading happens in the room or before it.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Amey-Thakur
- Source: Amey-Thakur/AI-SKILLS
- License: MIT
- Homepage: https://amey-thakur.github.io/AI-SKILLS/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.