Read-only preflight for Google Play, Amazon, Microsoft Store, itch.io or Apple: assets, signing, permissions, versions and blockers.
Verify a versioned software release is genuinely complete — tickets actually implemented (not just closed), docs discoverable (not just present), CI green on all matrix platforms, coverage gated, security scan clean, rollback path tested, and version metadata consistent. Produces a structured READY / NOT READY / BLOCKED report with evidence-backed findings and action items.
Paste a diff and get a risk-ranked checklist of what it'll actually break — hidden dependencies, config drift, and blast radius that static analysis can't see, checked before you ship.
Audit Flutter repositories before Google Play or App Store submission. Get an evidence-backed readiness score, go/no-go verdict, critical blockers, Android and iOS checks, and a prioritized remediation plan.
Before you write code, kill the causes of rework. A phase-gate skill that runs a pre-implementation diagnosis (clarify requirements, success criteria, non-goals, hidden risks) and sets up the dev environment (toolchain check, repo init, dependency/secret/config templates, DB/API contract, folder layout). Each gate must pass before moving on. Delivers a diagnosis report, a stack-selection doc, and a ready-to-build foundation to hand off to implementation.
Run actionable creative QA before a design draft, marketing asset, landing page, ad creative, or social post ships. This download skill checks brand fit, message hierarchy, readability, conversion goal, format and mobile crop, claim / compliance / cultural / IP / platform risk, then produces a launch verdict, P0 / P1 / P2 fix list, and edit order.
Audit Excel workbooks before you trust, send, or deliver them. Detect formula, structure, data-quality, hidden-content, dependency, validation, and consistency risks with traceable evidence — without modifying the original file.
Check an agent skill before you publish it. A bundled offline Python script reads your skill folder or zip and reports invalid SKILL.md frontmatter, long or vague descriptions, references to files that don't exist, leftover placeholder text, secrets, oversized, junk or unrelated files, missing tests and examples, and inconsistent versions or wording. Your AI agent explains each issue and proposes fixes. Download package: you bring your own AI agent and Python 3; no model included.