AB asc-release-flow
Orchestrate App Store releases with asc, including staging a version, uploading or building an artifact, publishing, and submitting for review. Use when the user wants to prepare or execute a release. Keep Game Center item preparation in this skill; route other readiness failures, stuck submissions, cancellation, and retry decisions to asc-submission-health.
This skill orchestrates App Store releases: stages versions, uploads or builds artifacts, publishes, and submits for review. All four steps sit in one place according to the description.
Grade A with 88 quality and 100 safety score. No critical findings, linter passes. Two files, 1928 tokens—reasonable for an orchestrator. Process score 68 means execution won't lag, though it's not lightning-fast. Game Center prep stays here; other issues (stuck submissions, cancellations, retries) route to asc-submission-health.
Supports Claude, Cursor, Copilot, DeepSeek, and eight more platforms. Safe to install—quality is documented, security checks pass, responsibility split with the sibling skill is clear.
Orchestrate App Store releases with asc, including staging a version, uploading or building an artifact, publishing, and submitting for review.
As a process B 68/100 · Nearly there — weak spots: result and completion, inputs and preconditions, progress reporting
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 68/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Steps. 18 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1928 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
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
- +5Description has no quoted example phrases that should trigger the skill
- +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
- +3Description length 360: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.