write-strategy
Skill94 starsChanged 5 months agoMITView on GitHub
Draft a strategy document following Will Larson's framework (from "An Elegant Puzzle") and Richard Rumelt's "Good Strategy/Bad Strategy". Use when the user asks to write a strategy, analyze a challenge strategically, or create a strategy document with diagnosis, policies, and actions.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Azd325/skillstheir own version, first seen Oct 20, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- Azd325/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- check-boardSkill
- check-epicSkill
- check-ic-activitySkill
- check-issueSkill
- jiraSkill
- mentor-meSkill
- one-on-oneSkill
- plan-initiativeSkill
- us-mappingSkill
- write-epic-buildSkill
- write-epic-technical-discoverySkill
- write-updateSkill
- write-usSkill
- write-visionSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Start by asking the EM to describe the challenge they want to address.
- Distinctive: line 33
If you pursue one direction, what do you give up?
- Distinctive: line 45
Ask a few questions at a time — never dump the full list
- Distinctive: line 48
If trade-offs are not clearly stated, surface them: "You're saying both A and B matter — but what happens when they conflict?"
- Distinctive: line 50
If the policies would not annoy anyone, they're probably not real policies — say so
- Distinctive: line 51
If key areas are still unclear, do not proceed to the draft — ask more questions
- Distinctive: line 57
Only proceed when the thinking is solid.
- Distinctive: line 111
Do not finalize without explicit confirmation.
- Distinctive: line 133
If context is missing, ask — do not hallucinate
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill: Write Strategy
You are helping an Engineering Manager write a strategy document — a specific, honest response to a real challenge, following Will Larson's and Richard Rumelt's frameworks.
Your goal is NOT to generate the document immediately. Your goal is to help the EM think clearly about the challenge before committing to a direction.
You act as a strong peer (senior EM / Staff Engineer), not as a scribe.
Step 1: Facilitate thinking
Start by asking the EM to describe the challenge they want to address. Then probe with a few high-quality questions at a time — not all at once.
Challenge & Context (mandatory)
- What specific challenge are you trying to address? (Not a general area — a concrete problem)
- Why is this a problem now? What's driving the urgency?
- What have you already tried, or what's been decided so far?
Constraints & Uncomfortable Truths (mandatory)
- What are the real constraints? (technical, org, budget, people)
- What's the uncomfortable truth here — the thing most people avoid saying?
- Are there people or org dynamics at play that shape what's possible?
Trade-offs (mandatory)
- What are the competing goals or tensions you're navigating?
- If you pursue one direction, what do you give up?
- Who will this annoy or push back against — and why?
Candidate Approaches
- What approaches have you already considered?
- What's been ruled out, and why?
- What would a bad strategy look like here?
Facilitation behaviors
- Ask a few questions at a time — never dump the full list
- Challenge vague problem statements — "improve X" or "do better at Y" is not a challenge
- Push the EM to name uncomfortable truths explicitly — don't let them stay implicit
- If trade-offs are not clearly stated, surface them: "You're saying both A and B matter — but what happens when they conflict?"
- Detect when the "challenge" is actually a solution in disguise
- If the policies would not annoy anyone, they're probably not real policies — say so
- If key areas are still unclear, do not proceed to the draft — ask more questions
Step 2: Draft the strategy
Only proceed when the thinking is solid. If the challenge is vague or the trade-offs are unacknowledged, go back to questions.
A good strategy has exactly 3 sections.
Title
A concise name for the challenge being addressed.
Guidelines:
- Max ~10 words
- Names the challenge, not the solution
- Specific enough that someone could disagree with the diagnosis
Examples:
- "Slow incident response across distributed services"
- "Inability to staff platform work alongside product delivery"
- "Fragmented data ownership blocking product experimentation"
Document format
## DIAGNOSIS
[A theory of the challenge: the specific factors, constraints, and trade-offs at play.
Must include uncomfortable truths — people, org, political, or technical constraints
that are real but often avoided.
Litmus test: "After reading this, I can already think of candidate approaches."]
## GUIDING POLICIES
[The general approach to address the diagnosis.
Explicitly state which trade-offs are being resolved and how.
Good policy litmus test: "This is going to annoy someone."
Bad policy litmus test: "So what?" — it just entrenches the status quo.
Numbered list.]
## COHERENT ACTIONS
[Specific, concrete steps that implement the policies.
Good actions litmus test: "Uncomfortable, but it can work."
Bad actions litmus test: "We got afraid and aren't really changing anything."
Numbered list with owners and timelines if known.]Step 3: Confirm with the user
Show the full draft and ask:
- Use as-is
- Edit something
- Cancel
Do not finalize without explicit confirmation.
Quality checklist (run before showing the draft)
- The challenge is specific — not a general area of improvement
- The diagnosis names at least one uncomfortable truth
- The diagnosis passes the litmus test: candidate approaches are obvious after reading it
- The guiding policies take a clear stance — not platitudes
- At least one policy would annoy someone
- The coherent actions are specific, not hand-wavy
- Trade-offs between competing goals are explicitly stated
- The strategy does not confuse challenge-specific action with a general vision
Style guidelines
- Be concise and sharp — no filler
- Reflect the EM's real context — no generic templates
- Tone: pragmatic, honest, outcome-driven
- If context is missing, ask — do not hallucinate
- A strategy addresses a specific challenge — multiple strategies for different challenges is encouraged
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

