problem-structuring
Skill13 starsChanged 4 months agoMITView on GitHub
MECE issue trees, pyramid principle and 80/20 prioritization for breaking a product problem into testable hypotheses — the structuring engine behind /hypotheses and /validate. Use for "разложи проблему", "issue tree", "MECE", "почему падает метрика", "structure this problem", "root cause".
1 other project uses a version of this.
Adopted by
Most recently taken up by
- itseffi/agentic-ostheir own version, first seen Jan 23, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- itseffi/agentic-os★ 114same 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 repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ambiguity-resolverSkill
- challengeSkill
- deep-thinkSkill
- design-critique-templateSkill
- experiment-designSkill
- ingestSkill
- interview-analysisSkill
- multi-source-signal-synthesiserSkill
- next-advisorSkill
- pipeline-stepsSkill
- post-launch-reviewSkill
- product-requirements-docSkill
- setup-initiativeSkill
- solution-scoringSkill
- strategic-narrative-generatorSkill
- system-design-docSkill
- technical-spec-documentSkill
- tracking-and-funnelsSkill
- ui-pattern-librarySkill
- user-persona-builderSkill
- user-story-generatorSkill
- user-testingSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 29
Stop drilling: when a leaf is testable with one data pull or one experiment — deeper splits past that point are decoration.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Problem Structuring (MECE for the pipeline)
The structuring engine of /hypotheses (step 1) and the synthesis logic of
/validate (step 6). For a facilitated partner-led thinking session on a
problem that is not an initiative yet, use /deep-think.
MECE issue tree
- Root = the metric gap, phrased as a question with a number: "Why do only X% of [segment] reach [outcome]?" — from CONTEXT.md.
- First split — choose ONE dimension and stick to it: funnel stages, user segments, or jobs-to-be-done. Mixing dimensions is the #1 MECE violation.
- Branches must be mutually exclusive, collectively exhaustive. Test: every lost user lands in exactly one branch. If a case fits two branches — re-split. If no branch fits — add "other/unknown" and size it.
- Leaves localize the gap; hypotheses explain it. A leaf states WHERE
the metric is lost ("high-frequency viewers never click") with a size
estimate. For each sized leaf write 1–3 falsifiable hypotheses about WHY
("recommendations are irrelevant for this segment") and register them
(
hypotheses.py add). Don't collapse the two: one leaf often has competing explanations, and validating decides between them. 5–15 hypotheses total is the healthy range. - Stop drilling when a leaf is testable with one data pull or one experiment — deeper splits past that point are decoration.
- Name the blind spots explicitly — branches you cannot size with
current data. These become research questions for
/brief.
Pyramid principle (for validated findings)
Answer first, then grouped support, then evidence: conclusion → 2–3 insight
groups → data per group with sources from the registry. Used in
/validate outputs and gate presentations — never a data walk-through that
ends with "so, in conclusion".
80/20 prioritization
Size every branch before drilling: 80% of the metric gap usually sits in 2–3 leaves. Depth-first into the biggest branch beats breadth-first completeness. The registry's segment-size fields carry the sizing; priorities follow SIF = Severity × Impact × Frequency (each 1–10: how painful per affected user × share of the metric gap / segment size × how often the situation recurs) — format in output-formats.md.
Anti-patterns
- A "tree" that is really a list (no exclusivity test performed)
- Solution leaves in a problem tree ("нет кнопки X" is a solution in disguise — rephrase as the user problem)
- Drilling into a branch nobody sized
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.