AD Monorepo Dep Graph
Monorepo internal dependency analyzer for npm/yarn/pnpm workspaces, Cargo workspaces, and Go multi-module repos. Maps every workspace-to-workspace dependency, detects circular internal dependencies (package A imports B imports A), orphaned packages with zero consumers, deeply coupled modules (high fan-in/fan-out), version mismatches when the same external package appears at different versions across packages, and packages that depend on private internal APIs they shouldn't. Generates a dependency graph as ASCII tree or Mermaid diagram. Works by reading package.json/Cargo.toml/go.mod files — no install required. Zero external API. Triggers on "monorepo deps", "workspace dependencies", "circular dependency", "internal package coupling", "shared package", "/mono-deps".
As a process D 47/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 47/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (Monorepo Dep Graph) differs from the folder (phy-monorepo-dep-graph)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 9 steps
- 100Execution cost. Instruction body is 3717 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 776: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (13 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.