── SKILL
strategic-doc-structure✓ APPROVED

Make a strategic doc land in one read.

Names the doc type, the reader's one question, and the structure that answers it fast. Two bets, max.

Inside: The doc-type router and the two-bet plan structure.

01 / HOW TO USE

Install it in one line, or paste it in.

1
In Claude Code (one command)
Copy the install line, paste it into your terminal, and restart Claude Code. The skill installs itself to ~/.claude/skills/ and runs automatically when it is relevant.
2
In Claude, ChatGPT, or a Project (no terminal)
Open the file, then upload it to your chat or paste its contents in. A skill is just a markdown file of instructions, so any capable AI can follow it.
New to skills? A skill is a plain-text file that teaches your AI a workflow. Point any capable assistant at it and it follows the steps, on your data.
02 / MAKE IT YOURS

Connect your context. Set it to your motion.

SET IT TO YOUR MOTION
SlotWhat it isMake it yours
Your doc typesThe kinds of leadership docs you shipAdd or rename to match what your team writes (QBRboard memolaunch plan). Keep the reader-question column.
Your vocabulary lockThe words you ban and the words you requireBan process-words ("work streams" "tracks" "pillars"). Require motion verbs. Set your own lists.
Your audienceWho the doc names and howDepartmentsnever individualsby default. Use your org's labels.
03 / THE FULL SKILL

Everything the skill does, in full.

A forcing function for any leadership-facing strategic document. It stops one failure mode: a document so deep and wide the reader cannot tell what you are committing to. The fix is always the same. Pick what matters most, say it first, name who owns it, push the depth to a companion.

── WHAT THIS DOES

Takes a strategic document and makes it land. Tells you what kind of doc you are writing, what the reader's one question is, and the structure that answers it fast. For strategic plans it enforces the hardest discipline: a maximum of two bets, a five-block bet card, named owners, and a closing the reader reaches in seconds. The output survives a 30-second skim and a five-minute read.

── THE METHOD
  1. 1
    STEP 0, triage the document type
    Type Reader's question Template
    Strategic Plan "What are we committing to?" 2 bets, 30-second read
    Deep Dive "Where is the depth behind the plan?" Speaking points, receipts
    Deck "What does this look like presented?" 7 to 8 slides, no new info
    Methodology "How does this model work?" Trust contract + worked example
    Analysis Report "What did we find?" Verdict + 3 findings + actions
    Playbook "What should I do tomorrow?" Findings paired with actions
    Brief "Give me the 60-second take" Verdict + 3-bullet why + named move

    If unsure, default to Analysis. Never force the Strategic Plan template onto a methodology or analysis.

  2. 2
    Universal rules, every doc type
    1. Verdict first. The conclusion before the evidence.
    2. Vocabulary lock. Motion verbs (finalize / attack / stop / ship / launch / re-engage / coach / close). Never "work streams," "build," or "optimize" in headlines.
    3. Departments, not individual names, in the body.
    4. Plain voice. Humanize numbers. No filler.
    5. The closing is reachable. Short docs show it in the first screens; long docs show a table of contents early.
  3. 3
    Strategic Plan template

    The test: in 30 seconds the reader answers what we are committing to (the number), what is the plan (two bets), who is doing what (named team), what winning looks like (the evidence at period end).

    Structure (do not reorder): a one-line page hero (the strategic motion); a commit banner (target + binary verdict + what failure looks like); the plan sentence ("The plan is two bets..."); the bets (2 max, 3 ceiling), each a 5-block card:

    • Bet header (number + name).
    • The problem (specific, numbers, two sentences max).
    • The bet (the call, one sentence).
    • The 2 moves (exactly 2; verb-led headline + department owner + one line each).
    • What we are going after (the GO list, 4 outcome-led bullets max, each opening with a motion verb and naming a campaign/cohort with sizes).
    • What winning looks like (a one-line verdict + 3 to 5 measurable bullets).

    Then: How we execute (departments grid + a one-sentence cadence line); the closing (standalone, restates the commit); receipts (one row of links).

    Cut from the body and link instead: diagnosis sections, transformation tables, diagrams, deep-dive metric grids, operating-system sections, resourcing, appendices, already-shipped proof. The plan reads as a plan; the companion shows the data.

  4. 4
    The other templates

    Deep Dive equips the presenter (speaking-point Q&A cards + "what is in field this week" + numbered depth). Deck mirrors the plan in 7 to 8 slides with no new info. Methodology answers four reader questions with a worked example. Analysis is verdict + exactly 3 stacked findings + one conclusion + 3 to 5 actions. Playbook pairs each finding with the action it produces plus a peer comparison. Brief is one screen: color-coded verdict + 3-bullet why + one named move.

── OUTPUT (EXAMPLE)
EXAMPLE OUTPUT
Bet 1 - Build the Pipeline Engine

THE PROBLEM
Sales created only a third of its own pipeline last quarter. When inbound
dipped, the quarter dipped with it.

THE BET
Sales owns pipeline creation. We stop waiting for leads and build our own.

THE 2 MOVES
1. Stand up the outbound motion     Owner: Sales
2. Fix the routing                  Owner: Revenue Operations

WHAT WE ARE GOING AFTER
- Attack the priority cohorts: Tier 1 named accounts (130), re-engage cold (800)
- Launch the weekly outbound cadence across the team
- Stop chasing unqualified inbound; route it to nurture
- Ship the new routing rules to production

WHAT WINNING LOOKS LIKE
"A sales org that creates its own pipeline."
- Sales-sourced pipeline at 50%+ of total
- Qualified-to-meeting conversion at 18%+
- Time-to-first-touch under 24 hours
── EXAMPLE CHAT
EXAMPLE CHAT
You
I have a 12-page strategic plan draft for the board, can you tighten it?
CLAUDE
Triaged it as a Strategic Plan. Reader's question: "What are we committing to?" Here's the cut. Cut: the 4-page diagnosis section, the tooling appendix, the 3rd bet. Kept: commit banner, 2 bets (Pipeline Engine, Retention Motion), 5-block cards each. The draft had three bets and a diagnosis section eating the first four pages, so the reader never actually reached the commitment. Key insight: the vocabulary lock caught "optimize the funnel" in a headline, that's a process word doing a verb's job, swapped it for "fix the routing." One sharpener: name the department owner for each of the 2 moves under each bet. Right now the doc just says "the team," and that's not an owner.
04 / GO FURTHER

Where an operator takes this next.

The structure is set. Here is where an operator takes it once the manual pass proves out.

The structure does the work once; the checks keep it from drifting back.

01
Triage every doc before it's written

Wire a scheduled Claude task to classify drafts as they land in a shared doc tool (Notion, Google Docs) and flag the wrong template before someone writes 12 pages in the wrong shape.

02
Enforce the vocabulary lock automatically

A lightweight script scans for banned words ("work streams," "optimize," "pillars") on save and flags the line, the same discipline a human editor would apply, just faster.

03
Route the closing to where it actually gets read

Push the finished commit banner into Slack as its own message the day the doc ships, so the 30-second version reaches people who will never open the doc.

05 / PART OF A BIGGER PLAY

One skill is the on-ramp.

── GET NEW SKILLS IN YOUR INBOX

One operator-built skill a week. Free.