issue-trees — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited issue-trees (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
An issue tree breaks a vague problem into progressively smaller, more concrete sub-problems until you reach something testable. Each branch is a hypothesis about why the parent problem exists. Done well, the leaves are things you can actually go investigate.
A fenced code block with text syntax. Use ASCII box-drawing characters:
├── non-final child│ vertical continuation under a non-final child└── final child at each levelCore Problem ├── Category 1 │ ├── Sub-factor A │ └── Sub-factor B └── Category 2 └── Sub-factor C
Some destinations mangle box-drawing characters — Slack, certain email clients, and some chat UIs render them as boxes or question marks. If you know the output is heading to one of those, use an indented-dash tree instead:
- Core Problem
- Category 1
- Sub-factor A
- Sub-factor B
- Category 2
- Sub-factor CIt loses some elegance but stays readable everywhere. Default to box-drawing; switch only when needed.
This is "Slack mode." When the user asks for Slack / Teams / email / plain-text output (or names that as the destination), use this indented-dash form for the whole tree by default.
| Default | When to flex |
|---|---|
| At least 2 levels deep | A 1-level tree is a list. Push deeper. For complex problems, 3–4 levels. |
| 3–8 words per node | Stay short — long node text destroys readability. |
| Branches MECE at each level | This one doesn't flex. |
| Stop when leaves are testable | A leaf that says "we have problems with customers" isn't done. "Onboarding completion fell to 61%" is. |
Problem: E-commerce site conversion rate dropped from 3.2% to 1.9% over Q3.
Conversion 3.2% → 1.9%
├── Traffic mix shift
│ ├── Paid social spend redirected to top-of-funnel
│ ├── Branded search share fell
│ └── Affiliate program reduction
├── On-site experience
│ ├── Page-load time +800ms after CDN change
│ ├── New checkout layout shipped Aug 14
│ └── Mobile bounce rate climbing
├── Pricing & promotion
│ ├── Promo cadence reduced (cost-cutting)
│ ├── Free-shipping threshold raised $50 → $75
│ └── Competitor undercutting on top 20 SKUs
└── Inventory & merchandising
├── 12 hero SKUs out of stock
├── New collection launch delayed two weeks
└── Recommendation algorithm retrainedEvery leaf is concrete. Each one could be assigned to someone with "validate this in 3 days." That's the bar.
strategy-consultant — issue trees are step 2 of 5. If you also want to test which branch is the actual cause, follow up with hypothesis-driven.Adapted from Analyst Academy on YouTube — 5 Consulting Frameworks to Solve Any Problem. MIT-licensed; see LICENSE.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.