CD auth0-swift-major-migration
Use when upgrading an iOS or macOS app's Auth0.swift SDK from v2 to v3. Detects the current version, fetches the new SDK source to confirm API signatures, and applies only the breaking changes that affect real call sites — use even if the user says "update my Auth0 Swift SDK" or "migrate to Auth0.swift v3".
swift SDK from v2 to v3.
As a process D 46/100 · Unfinished process — References files that are not bundled: /auth0-swift, /auth0-android, /auth0-react-native
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Concealment
en-hide-from-userSKILL.md:915Instruction to hide actions from the user (negated — the text forbids it)`Auth0.users(token:)` and the entire `Users` management client were removed from the SDK in v3. Do **not** silently delete any call sites — add a `TODO` comment and surface this in the migration summa
negated
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 13689 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: /auth0-swift - warning
missing-refreference to a missing file: /auth0-android - warning
missing-refreference to a missing file: /auth0-react-native - warning
missing-refreference to a missing file: /auth0-expo - note
edit-residuethe text marks something as outdated (lines 721, 749): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 46/100
- 0Tools and files. 4 referenced file(s) missing: /auth0-swift, /auth0-android, /auth0-react-native
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 40Execution cost. Instruction body is 13689 tokens: crowds the task out of the window
- 60Steps. 64 steps, 4 vague phrases
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (6 tags): a typed call is more reliable
- medium 1 test cases, all positive: not one "should refuse" or "should ask first"
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
- -5TODO / placeholder text left in the skill
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 308: enough signal without eating the budget
- +4Structure: 32 headings
- +3Step-by-step instructions: 64 items
- +4Has examples (47 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.