AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Structured Writing

skill-viktorbezdek-skillstack-structured-writing · by viktorbezdek

>-

No reviews yet
0 installs
31 views
0.0% view→install

Install

$ agentstack add skill-viktorbezdek-skillstack-structured-writing

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-viktorbezdek-skillstack-structured-writing)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Structured Writing? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Structured Writing

Most writing fails by burying the point. A structured document leads with the conclusion, supports it with grouped evidence, and lets the reader stop reading the moment they have what they need.

Pick a structure

| Structure | Best for | Lead | |---|---|---| | BLUF (Bottom Line Up Front) | Emails, status updates, requests | The ask or the answer | | Minto Pyramid | Reports, strategy memos, analyses | The single governing thought | | Inverted pyramid | News-style updates, announcements | The headline fact | | SPQR (Situation-Problem-Question-Resolution) | Briefs, consulting narratives | The situation, built to the ask |

Pick by reader, not by habit. A busy executive needs BLUF; a peer reviewing analysis needs a pyramid; a team reading an announcement needs inverted pyramid.

BLUF — the default for async work

A BLUF message opens with: the ask, the answer, or the conclusion — in under 30 words — followed by supporting detail the reader can skip.

BLUF: [ask / decision / answer in one sentence]

Why it matters:
- [reason 1 in ≤12 words]
- [reason 2]

Details (only if the BLUF doesn't answer their question):
- [supporting fact with number]
- [supporting fact with reference]

What I need from you:
- [explicit ask with deadline] or "FYI — no action needed."

Rules:

  • The subject line is the BLUF, compressed.
  • The BLUF sentence is self-contained — it must make sense without the rest.
  • If someone replies from the first 30 words, the message worked.

Full worked examples and email/Slack/standup templates in references/bluf-templates.md.

The Minto Pyramid

Barbara Minto's pyramid: every document has one governing thought, supported by 3-5 grouped arguments, each supported by evidence.

                  Governing thought
                 (what + why + so-what)
                          |
          ┌───────────────┼───────────────┐
      Argument 1      Argument 2      Argument 3
          |               |               |
       Evidence       Evidence       Evidence

Rules:

  • Arguments at the same level share a logical relationship (MECE — mutually exclusive, collectively exhaustive).
  • Each argument answers a "why" or a "how" that the governing thought raises.
  • If an argument doesn't raise a predictable question, it doesn't belong at that level.

See references/minto-pyramid-method.md for the question-answer logic, MECE groupings, and the SCQ (Situation-Complication-Question) introduction.

SPQR for briefs

When the reader needs context before the ask:

  • Situation — one paragraph of shared, uncontroversial context.
  • Problem — the change or complication that makes a decision necessary.
  • Question — the specific question you need answered.
  • Resolution — your recommendation + what you need from the reader.

Useful for consulting-style briefs, board materials, vendor proposals. Less useful for async team updates (use BLUF instead).

Skim-readability checklist

Structured writing is skim-tested, not read-tested. Before sending, ask:

  • [ ] Can the reader get the main point in the first 30 words?
  • [ ] Does every paragraph have a clear topic sentence?
  • [ ] Are supporting lists parallel in structure?
  • [ ] Can the reader stop reading at any paragraph and still have the main point?
  • [ ] Does the ask (if any) appear in the first sentence AND the last sentence?
  • [ ] Is the longest paragraph under 100 words?

If any answer is no, restructure before polishing words.

Anti-patterns

  • Buried lede — the conclusion is in paragraph 4. Move it to paragraph 1.
  • Chronological narrative — "here's what we did, then what we discovered, then what we decided." Invert: lead with the decision.
  • Argument without governing thought — three arguments pointing in different directions with no synthesizing claim.
  • Evidence dumping — numbers and screenshots with no argument they support.
  • Parallel violations — some list items are nouns, others are verbs, others are sentences. Make them parallel.
  • Structure for its own sake — applying BLUF to a 200-word email nobody would read twice anyway. Structure serves speed, not ceremony.

Workflow

  1. Identify the reader. Who reads this, how fast, with what in their head?
  2. Pick the structure. BLUF for action, pyramid for analysis, inverted for announcement, SPQR for briefs.
  3. Write the single governing thought. If you can't state it in one sentence, you're not ready to write.
  4. List supporting points. 3-5, parallel, MECE.
  5. Fill in evidence. Numbers, references, quotes.
  6. Polish after structure is right. Clarity editing comes last — see clarity-editing.

References

| File | Contents | |---|---| | references/bluf-templates.md | BLUF templates for email, Slack, standup updates, PR descriptions with worked examples | | references/minto-pyramid-method.md | Full Minto method — governing thought, MECE arguments, SCQ intros, question-answer logic | | references/structure-selection-matrix.md | Reader × purpose × medium matrix for picking the right structure |

Related skills

  • clarity-editing — line-level editing once the structure is right.
  • stakeholder-alignment — when the piece is an RFC/proposal, structure plus roles.
  • documentation-discipline — when to write at all, and which artifact type to use.
  • visual-communication — when a diagram replaces paragraphs.
  • storytelling-for-stakeholders — narrative-heavy pitches and board materials.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.