Develop and evaluate names for how they behave in the real world — in speech, in memory, in spelling, in search, in sales calls, across languages, and across future products. Use when naming or renaming a company, product, or feature, when a shortlist needs evaluation, or when a favored name needs stress-testing before legal spend. Produces a naming report with behavioral tests, a defended recommendation, and an explicit register of checks that still require professional clearance.
Reconcile strategy, positioning, naming, verbal identity, visual identity, worldbuilding, governance, and applications into one prioritized diagnosis of the whole brand system. Use when a brand needs a full audit rather than a critique of one asset, when specialist reviews contradict each other, when leadership must decide what to protect, change, test, and defer, or before a rebrand decision. Produces a review decision with root causes, priorities, owners, and a validation plan.
Run the final release gate for a brand system — verifying strategy, expression, recognition, real applications, assets, templates, accessibility, legal and cultural boundaries, governance, operational readiness, and measurement before launch. Use before launching or relaunching a brand, before handing a system to another team or agency, or when someone needs to decide whether the brand can actually operate rather than merely present. Produces a release report with a defensible verdict and a post-launch learning plan.
Turn a diagnosis into commercial choices — audience progress, value, distinction, proof, position, promise, and the behavior the organization must change. Use after Brand Intelligence, when a brand needs a defensible strategic direction, when positioning statements exist but nothing downstream changed, or when creative work keeps drifting because nothing is settled. Produces a strategy brief with outcome hypotheses and documented non-choices.
Turn strategy and identity into a living world — recurring behaviors, rituals, environments, narrative patterns, product moments, and cultural cues that make a brand recognizable through what it does. Use when a brand has correct assets but no presence, when every campaign restarts from zero, or when the identity works on a page but has nothing to say in space, time, or interaction. Produces a brand world with pillars, signature behaviors, and campaign translation rules.
Build a visual identity system whose strategic idea survives across typography, color, form, composition, imagery, motion, product surfaces, campaigns, and small formats. Use when a brand needs visual expression built as a system rather than a logo presentation, when identity work looks good in guidelines but falls apart in production, or when a brand is invisible without its logo. Produces an identity system with a recognition map, application rules, accessibility standards, and stress tests.
Generate genuinely different positioning territories and choose between them on strategic mechanism, credibility, behavioral consequence, creative range, and downside risk. Use when a brand needs real alternatives rather than one direction to approve, when every option on the table is the same idea in different words, or when a decision between directions has stalled. Produces a territory matrix and a defended choice with the evidence that would reverse it.
Build a verbal identity that makes a brand recognizable in language — voice, tone, messaging hierarchy, proof language, vocabulary, and how each shifts by context without losing character. Use when writing sounds interchangeable with competitors, when every channel sounds identical or nothing sounds related, when teams need to write without a copywriter, or when tone guidance exists but nobody can apply it. Produces a verbal system with worked examples across real contexts.
Agents are isolated Claude instances with their own context window, tools, and instructions. They run independently and return results to the parent conversation. Read-only. Cannot modify code. Reports findings. Can…
Adapt one interface across space, input, content pressure, text scaling, orientation, localization, and reduced motion. Use when designing or reviewing responsive behavior, touch and keyboard support, or layouts that break under real content.
Design interaction contracts, feedback, motion, timing, direct manipulation, interruption, cancellation, and recovery. Use when specifying or reviewing how an interface responds to input, choosing whether and how to animate, or fixing behavior that feels unresponsive or theatrical.
Model an interface's task hierarchy, surfaces, navigation, flows, component boundaries, and state ownership. Use when structuring a new surface, reorganizing navigation, deciding where a task belongs, or diagnosing whether a problem is structural rather than visual.
Refine visual hierarchy, typography, spacing, density, color, material, and optical alignment. Use when an interface looks unresolved, cramped, flat, or busy, or when tightening visual quality before release.
Adversarially review a complete interface across product, architecture, craft, interaction, adaptation, state, accessibility, and engineering, and diagnose root causes. Use when requesting a hard critique, a pre-release quality pass, or an explanation for why an interface feels wrong.
Reconstruct the design logic and grammar behind an existing interface from live UI, screenshots, source, or DOM. Use when analyzing why an interface works, rebuilding a reference, or extracting a system from an existing product.
Understand the real interface problem before deciding on a solution, separating request from intent and evidence from assumption. Use for ambiguous interface requests, major redesigns, unfamiliar products, consequential interaction decisions, or when the proposed UI may not be the real solution.
Turn a design uncertainty into a controlled comparison of materially different directions that produces a decision. Use when a consequential interface choice is genuinely unresolved and prototyping would reduce the risk of committing.
Run a unified evidence-driven review of an interface, change, flow, or product surface by coordinating the 10X Interface disciplines and producing one consolidated decision.
Run the final evidence-based release gate and issue a SHIP, SHIP WITH KNOWN LIMITATIONS, or DO NOT SHIP verdict. Use before releasing interface work, when deciding whether quality and coverage are sufficient, or when remaining risk must be made explicit.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
Dragoon0xSkill