Plugin Claude Code
Capability-first AI development skill graph (Anthropic-native): plan → build with a warm-context orchestrator, contract-wired skills, and independent verification.
Plugin Claude Code
Capability-first AI development skill graph (Anthropic-native): plan → build with a warm-context orchestrator, contract-wired skills, and independent verification.
Skill Claude CodeCodex
Use before any build, when an idea or intent must become an agreed, sharp requirement and design — explores intent, weighs approaches, and decomposes if too big.
Skill Claude CodeCodex
Use when verified work is ready to be recorded in version control.
Skill Claude CodeCodex
Use when an ACCEPTED deliverable must be shipped to a live environment. Never mid-run, never on unaccepted work.
Skill Claude CodeCodex
Use when a feature needs a new or changed architectural decision — a service, data model, cross-cutting pattern, or external integration — before stories are drafted.
Skill Claude CodeCodex
Use after a UI feature is built and running, before merging, to review the rendered interface against its UI spec, the design system, and world-class craft.
Skill Claude CodeCodex
Use when a project has no design direction yet, or must (re)establish its aesthetic — produces the durable design system (aesthetic POV, type, color, space, motion) before any UI is designed.
Skill Claude CodeCodex
Use when a feature has a user interface, to design its screens and flows by applying the project's design system with world-class craft, before stories are drafted.
Skill Claude CodeCodex
Use when a feature request or requirement must become an implementable spec with acceptance criteria, before any code is written.
Skill Claude CodeCodex
Use when something is broken and the CAUSE is unknown — a repeatedly failing verify, a bug report, a regression — before any fix is attempted.
Skill Claude CodeCodex
Use when entering an EXISTING codebase (brownfield) before designing or changing anything — build an evidence-based map of its architecture, conventions, and hazards.
Skill Claude CodeCodex
Use when a goal must be delivered end-to-end by composing skills, with the human approving direction at the start and the result at the end.
Skill Claude CodeCodex
Use when a planning or design decision needs external facts — market, competitor, feasibility, or a library/tech choice — before committing.
Skill Claude CodeCodex
Use after implementing a task or feature and before merging, to check a diff against its spec and for quality.
Skill Claude CodeCodex
Use before claiming any work is complete, fixed, or passing, and before committing or handing off.
Skill Claude CodeCodex
Use when the deliverable is a runnable app or service and its real user flows must be proven working from the OUTSIDE (browser/HTTP/CLI) before acceptance — unit tests passing is not that proof.