How do I install the Repo D UI Guardrails skill?

Run npx skillmds@latest add tomevault-io/repo-d-ui-guardrails in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Repo D UI Guardrails safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Repo D UI Guardrails?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Repo D UI Guardrails free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Repo D UI Guardrails?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Repo D UI Guardrails by tomevault-io

Name: Repo D UI Guardrails
Author: tomevault-io

Repo D UI Guardrails

Enforce <PRIVATE_REPO_D> AGENTS.md guardrails for UI/Electron work. Use when modifying apps/desktop, packages/ui, packages/engine, packages/services, or docs tied to deterministic visuals, startup acceptance, state persistence, no-download policy, local-only behavior, and no-CI constraints. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

File contents

Repo D Sandbox UI Guardrails

Use this skill to keep changes compliant with repository rules.

Workflow

Read AGENTS.md and README.md before editing.
Identify whether changes touch visuals, startup flow, assets, or docs.
Apply guardrails before coding:
- Do not add .github/workflows/* or CI automation.
- Keep deterministic visuals behind explicit toggles or presets.
- Do not add runtime asset downloads.
- Keep front-end boundaries intact; do not embed out-of-scope orchestration logic.
- Do not change Electron boot/renderer readiness sequencing without explicit validation notes.
- Do not accept backend-only startup as success for desktop lanes.
- Do not allow stale-window relaunches or empty console windows in canonical startup paths.
- Do not regress persisted user state (window placement, layout, profile/settings restore).
Update progress docs on scoped work:
- docs/SCOPE_TRACKER.md
- docs/TODO.md
- repo-local reconciliation docs when present
Include a status block in notes/PR summary:
- scope lane(s),
- changed files,
- validation commands with pass/fail,
- remaining blockers.
Run local checks and report results.

Required Checks

Run from repo root:

npm install
npm run build
npm run dist
npm run lint
npm run format

When startup flow or renderer wiring changes, also run:

npm run verify-startup
npm run dev
npm run startup:lockdown

Scope Boundary

Use this skill only for the repo-d-ui-guardrails lane and workflow defined in this file and its references.

Do not use this skill for unrelated lanes; route those through $skill-hub and the most specific matching skill.

References

Guardrail summary: references/guardrails.md

Loopback

If this lane is unresolved, blocked, or ambiguous:

Capture current evidence and failure context.
Route back through $skill-hub for chain recalculation.
Resume only after the updated chain returns a deterministic next step.

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: repo-d-ui-guardrailsdescription: Enforce <PRIVATE_REPO_D> AGENTS.md guardrails for UI/Electron work. Use when modifying apps/desktop, packages/ui, packages/engine, packages/services, or docs tied to deterministic visuals, startup acceptance, state persistence, no-download policy, local-only behavior, and no-CI constraints. Use when this capability is needed.---# Repo D Sandbox UI GuardrailsUse this skill to keep <PRIVATE_REPO_D> changes compliant with repository rules.## Workflow1. Read `AGENTS.md` and `README.md` before editing.2. Identify whether changes touch visuals, startup flow, assets, or docs.3. Apply guardrails before coding: - Do not add `.github/workflows/*` or CI automation. - Keep deterministic visuals behind explicit toggles or presets. - Do not add runtime asset downloads. - Keep front-end boundaries intact; do not embed out-of-scope orchestration logic. - Do not change Electron boot/renderer readiness sequencing without explicit validation notes. - Do not accept backend-only startup as success for desktop lanes. - Do not allow stale-window relaunches or empty console windows in canonical startup paths. - Do not regress persisted user state (window placement, layout, profile/settings restore).4. Update progress docs on scoped work: - `docs/SCOPE_TRACKER.md` - `docs/TODO.md` - repo-local reconciliation docs when present5. Include a status block in notes/PR summary: - scope lane(s), - changed files, - validation commands with pass/fail, - remaining blockers.6. Run local checks and report results.## Required ChecksRun from repo root:```bashnpm installnpm run buildnpm run distnpm run lintnpm run format```When startup flow or renderer wiring changes, also run:```bashnpm run verify-startupnpm run devnpm run startup:lockdown```## Scope BoundaryUse this skill only for the `repo-d-ui-guardrails` lane and workflow defined in this file and its references.Do not use this skill for unrelated lanes; route those through `$skill-hub` and the most specific matching skill.## References- Guardrail summary: `references/guardrails.md`## LoopbackIf this lane is unresolved, blocked, or ambiguous:1. Capture current evidence and failure context.2. Route back through `$skill-hub` for chain recalculation.3. Resume only after the updated chain returns a deterministic next step.---> Converted and distributed by [TomeVault](https://tomevault.io/claim/grtninja) — claim your Tome and manage your conversions.

Frequently asked questions