Skill Claude CodeCodex
Audits and improves code clarity and documentation using APOSD's obviousness rules: naming quality, comment accuracy, AI-facing doc completeness, and the comments-first workflow for new code. Not for generating project-wide convention docs (use code-standards) or structural simplification of the code itself (use…
Skill Claude CodeCodex
Generates or updates docs/code-standards.md by scanning the codebase for actual conventions. Produces an example-rich standards file optimized for LLM consumers, grounded in the project's real patterns. Not for auditing one file's naming, comments, or clarity (use code-clarity-and-docs).
Skill Claude CodeCodex
Maps code symptoms — exploding subclass combinations, switch-on-type dispatch, tangled object construction, incompatible interfaces, one-to-many update cascades — to the matching Gang of Four pattern, then loads that pattern's structural recipe from its 23 reference files. For selecting and implementing a design…
Skill Claude CodeCodex
Applies measure-first performance optimization: profiles to find hot spots, applies algorithm and data-structure improvements before micro-optimizations, and validates each change prevents regression. For single-process code tuning; not for correctness bugs (use cc-debugging) or concurrency, distributed, and real-time…
Skill Claude CodeCodex
Implements the Standard/Full planning pipeline for Medium and Complex tasks: multi-step discovery, phase decomposition with skill matching, cross-cutting concerns, and plan emission with Gate fields.
Skill Claude CodeCodex
Safely modifies untested legacy code by getting it under test first: characterization tests, seam identification, sprout/wrap techniques, and pinch-point testing before any production changes. Not for refactoring code that already has test coverage (use cc-refactoring-guidance).
Plugin Claude Code
A design-foundations system with a four-stage workflow (research → plan → mock → build). Design doctrine is loaded deterministically by Read() via a name→path resolver — six domains (content-design, behavioral, journey, deceptive-patterns, design-systems, ai-native) live as reference files in references/; two…
Instructions file
Claude Code instructions for ryanthedev/design-for-ai, covering claude.md, repository purpose, the workflow (primary front door), dispatched agents and doctrine domains + skills (direct access).
Agent
Produces ONE phase's design artifact — DESIGN.md tokens, a JOURNEY.md page spec, or a rendered mock — honoring the DESIGN.md/JOURNEY.md gates, then validates it with design execution evidence (contrast checks, the mock renders, tokens applied). Reads the phase's doctrine, makes the design decisions, and traces every…
Agent
Independent, execution-grounded cross-pillar critique of a rendered design surface against its done-when requirements. Renders/screenshots first, triages what is actually on the surface, reads and applies only the applicable pillar doctrine, and synthesizes ONE severity-ranked report on the real pixels. Returns PASS…
Command
Execute an approved design plan through gated phases (BUILD → REVIEW → commit) with subagent dispatch. Produces JOURNEY.md, DESIGN.md, design-system tokens, and final mocks. Use when a design plan exists and the direction is approved — per-phase quality gates, design execution evidence (contrast/token/heuristic), and…
Command
Produce a cheap mock from the design plan and gate on user sign-off before committing to the full build. Dispatches the design-build-agent (via prototype skill) to render a viewable mock, then the design-review-agent for a cross-pillar validation on the rendered pixels. Use after plan, before build, to prove the…
Command
Turn a design brief into a phased design plan: clarify gaps, classify complexity, decompose into lifecycle stages (Discover/Design), assign doctrine per phase, and set design done-when items (contrast ratios, token coverage, heuristic pass). Use after research, or standalone when the brief is already known.
Command
Figure out what the user wants to design — even when they don't know yet. Extracts the design brief: purpose, audience, brand feel, JTBD, device constraints, and mood references. Use before plan, or standalone when exploring a design idea.
Skill Claude CodeCodex
Decomposes underspecified design requests by classifying gaps (missing brand context, visual ambiguity, false premises, scope faults) and generating targeted clarifying questions. Produces a confirmed design brief before any design work begins. For sharpening a design request that already exists; not for open-ended…
Skill Claude CodeCodex
Applies data visualization and information design principles to encode data truthfully and efficiently. Use when the question is about charts or graphs — chart type selection (bar, line, scatter, heatmap, small multiples), data-ink ratio and chartjunk reduction (Tufte VDQI), preattentive attributes (Knaflic…
Skill Claude CodeCodex
Produces self-contained HTML/CSS mockups and wireframes from design tokens and page specs — the output is always a viewable .html file, not guidance or code. Use when the request is to see a design, make a mock, build or show a prototype, create a wireframe, render a preview, or visualize what a page looks like before…
Skill Claude CodeCodex
Adjudicate whether users can operate an interface, and run heuristic evaluation. Use when the question is operability rather than looks — is it usable, hard to use, confusing, where do users get stuck; heuristic evaluation, Nielsen heuristics, usability audit, severity rating; the UX laws (Fitts, Hick, Miller/Cowan…
Plugin Claude Code
Discipline plugins for Claude Code — prompt engineering, agent dispatch, writing, search, and browser/DevTools control.
MCP server Claude CodeCodexCursor +2
MCP server "skill-eval" as configured in ryanthedev/oberskills. Launched with bash ./scripts/start-skill-eval-mcp.sh.
MCP server Claude CodeCodexCursor +2
MCP server "mcp-browser" as configured in ryanthedev/oberskills. Launched with bash ./scripts/start-browser-mcp.sh.
Instructions file
Claude Code instructions for ryanthedev/oberskills, covering claude.md, repository purpose, structure, conventions and dual-host support.
Command
Capture and analyze screenshots without burning context.
Skill Claude CodeCodex
Rewrite any reply in pirate speak. Use whenever the user asks to talk like a pirate or mentions pirates.