AD release-handoff
Finish an iOS release after the build is uploaded. When a build has been uploaded to App Store Connect by any tool (fastlane, asc, Xcode, Xcode Cloud, CI) and the user wants it shipped: attach the build to the version, clear export compliance, run the readiness sweep, fix what blocks, and submit for review through MetaRun. Also the way back after App Review rejects a version: read the verdict, fix, resubmit. Trigger phrases: "ship it", "submit the build", "finish the release", "send 2.4 to review", "the build is up", "Apple rejected it", "resubmit".
Finish an iOS release after the build is uploaded.
As a process D 47/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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
✓ No remarks against the Agent Skills spec
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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (release-handoff) differs from the folder (metarun-release-handoff)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 100Steps. 36 steps
- 100Execution cost. Instruction body is 2332 tokens
- 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 (5 tags): a typed call is more reliable
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
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 555: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.