plugins/exploration-cycle-plugin/skills/visual-companion/SKILL.md
Presents layout options to the SME in plain language before any prototype construction begins. Invoked after the Discovery Plan is approved to confirm visual structure and direction. Trigger phrases: "what should it look like", "show me some layout options", "let me see the design options before we build". Also invoked by prototype-builder after plan approval.
npx skillsauth add richfrem/agent-plugins-skills visual-companionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Before doing anything else, silently check for exploration/exploration-dashboard.md.
If the file EXISTS: Read it silently and check the **Status:** line.
**Status:** Complete → the prior session has ended. Proceed with this skill's
standalone flow as normal."It looks like you have an active Exploration Session in progress. Let me take you back to your session dashboard so we can keep your progress on track." Return to the orchestrator. Use the Skill tool:
skill: "exploration-workflow". After invoking it, stop generating output from this skill — do not continue below.
If the file does NOT exist: Proceed with this skill's standalone flow as normal.
This phase may be skipped for brownfield sessions or simple features where the design is straightforward. If skipped, it will be marked - [~] in the dashboard. The downstream Phase 3 skill handles missing layout direction gracefully.
This skill is invoked after the Discovery Plan is approved. Its purpose is to confirm the structure and shape of the output before any building or drafting starts. For software, this means UI layout. For non-software work, this means document structure, process flow shape, or analysis format. It ensures the SME has a clear picture of what they are agreeing to before anything is created.
Read the most recent file in exploration/discovery-plans/. Understand the problem domain, stakeholders, and success criteria before proposing anything. Do not skip this step.
Determine the output type from the Discovery Plan and session type:
Offer 3 structure options adapted to the context of the Discovery Plan. Describe each in plain language (2–4 sentences). No technical terms. No code. No wireframes. Words only.
Label them Option A, Option B, Option C.
For software UI outputs, adapt these starting points:
For process or workflow outputs, adapt these starting points:
For document or analysis outputs, adapt these starting points:
After presenting the three options, ask:
"Which of these feels closest to what you had in mind? Or if none of them fit, describe what you're picturing and I'll work with that."
Reflect back the chosen option in one sentence. For example:
"Got it — we'll go with a step-by-step flow so your team can move through each approval in order."
Then ask: "Is there anything you'd like to adjust about that?"
Wait for the SME's response before proceeding.
Write exploration/captures/layout-direction.md with this structure:
# Layout Direction
**Selected:** [Option letter and name]
**SME notes:** [any modifications or specific requests the SME mentioned]
**Confirmed:** [date]
Announce: "Layout confirmed — Phase 2 is complete."
If operating within an active Exploration Session (i.e., exploration/exploration-dashboard.md
exists and **Status:** is not Complete):
"Returning to your session dashboard now."
skill: "exploration-workflow".
After invoking it, stop generating output from this skill.
If the Skill tool is not available in your harness, tell the user:
"Please run /exploration-workflow to continue your session."If operating standalone (no dashboard file, or **Status:** Complete), the skill is complete.
data-ai
Task management agent. Auto-invoked for task creation, status tracking, and kanban board operations using Markdown files across lane directories. V2 enforces Kanban Sovereignty constraints preventing manual task file edits.
development
Create, audit, repair, and document cross-platform symlinks that work correctly on both Windows and macOS/Linux. Use this skill whenever the user mentions symlinks, symbolic links, junction points, .gitconfig symlinks, broken links after git pull, cross-platform path issues, or needs help with ln -s equivalents on Windows. Also trigger when the user reports that files are missing or wrong after switching between Mac and Windows machines using Git. This skill solves the common problem where symlinks committed on macOS show up as plain text files on Windows (and vice versa) because of Git's core.symlinks setting or missing Developer Mode / elevated permissions. **IMPORTANT FOR WINDOWS USERS:** Developer Mode must be enabled before creating symlinks. Without it, Git will check out symlinks as plain-text files or hardlinks, breaking cross-platform workflows.
development
Interactively prepares a targeted Red Team Review package. It conducts a brief discovery interview to determine the threat model, generates a strict security auditor prompt, compiles a manifest of relevant project files, and bundles them into a single Markdown artifact or ZIP archive ready for an external LLM (like Grok, ChatGPT, or Gemini) or a human reviewer.
tools
Reduces AI agent context bloat across three dimensions: (1) duplicate skill deduplication — clears stale agent directory copies since the IDE already reads from plugins/ directly; (2) instruction file optimization — rewrites CLAUDE.md, GEMINI.md, or .github/copilot-instructions.md to under ~80 lines, keeping only rules that directly change agent behaviour; (3) session token efficiency — guidance on cheap subagent delegation, context compounding across turns, and session hygiene. Trigger with "optimize context", "reduce context bloat", "deduplicate skills", "trim CLAUDE.md", "trim GEMINI.md", "fix my context usage", "why are my skills loading twice", "how do I reduce token usage", or "clean up agent directories".