A behavioral skill that forces every claim the agent makes to be evidence-gated and honestly labeled.
SeldonFrame merge gate — run unit tests + tsc + check-use-server + migration-journal + regression-grep and return ONE pass/fail verdict.
Select and execute the verification that actually proves the change works, based on what type of change it is.
Verify information accuracy against codebase and documentation.
Extracts and verifies the runnability and code coverage of all Python code blocks inside a Markdown file.
Verify persistence.xml configuration before git push.
Audit-only verification of manuscript references against PubMed and CrossRef.
Use for a technical incident, disputed diagnosis, bug fix, or claim that a change works.
Explicit-use only — invoke when the user explicitly names this skill, or when an active explicitly invoked workflow calls it.
Use when about to run tests/builds for ctsnetwork-event, after editing any file in event/backend or event/frontend, or before reporting…
Manage semantic version updates for claude-mem project.
Natural-language undo, rollback, and checkpoints that hide git entirely — "ย้อนกลับ", "undo", "ไม่เอาแล้ว", "เอาอันเดิมคืน" map to safe…
Semantic version parsing, bump strategies, and document version management.
Protect durable behavior across version changes.
Use when a Godot/.NET task needs a Layer 4 overlay upgrade review that evaluates engine, SDK, C# compatibility, addons/plugins, export…
Library of reusable solution briefs, architecture, and pricing frames per industry.
Vets whether to build a feature from scratch, use an existing free/open-source solution, or pay for a third-party API/service.
Use when improving accessibility — WCAG 2.2 compliance across Perceivable, Operable, Understandable, Robust.
Use when optimizing for Answer Engine Optimization — LLM citation tracking and E-E-A-T.
Use when designing APIs or module boundaries — contract-first, Hyrum Law, error semantics.
Use when making CEO decisions — vision, market, and organizational strategy.