AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Planr Design Review

skill-openplanr-openplanr-planr-design-review · by openplanr

Review and revise an existing product design using stable board pins and scoped browser-verified changes. Use for focused improvements while preserving unrelated screens and feedback.

↗ Website ↗ Repository
— No reviews yet
0 installs
0 views
— view→install

Install

$ agentstack add skill-openplanr-openplanr-planr-design-review

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-openplanr-openplanr-planr-design-review)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● today

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Planr Design Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Planr Design Review

Improve the existing design in this active host session, retaining the user's intent and recorded feedback.

  1. Read [review.md](references/review.md), then inspect the existing design

document, authored sources, specification, manifest, prior revision and board feedback using [utilities.md](references/utilities.md) and [scripts/design.mjs](scripts/design.mjs). Legacy HTML, canvas and image artifacts remain reviewable; preserve originals and distinguish static images from working interaction. Preserve the [document contract](schemas/design-document.schema.json). Use the public planr artifact route when available.

  1. Consult [discovery.md](references/discovery.md) only for missing context or

consequential ambiguity. Read the project's components and tokens using [design-system.md](references/design-system.md). Ask through native structured questions with concise chat fallback; do not ask again for settled decisions.

  1. Map pins to stable screens and anchors. Report missing or stale targets as

unresolved rather than attaching them elsewhere. Chat may request broad changes; board state remains the pin/rating authority. State shared-component scope before updating every affected instance.

  1. Apply changes only to the targeted source or component, following

[generation.md](references/generation.md) and [craft.md](references/craft.md). Keep unrelated screens, identities, feedback and arrangement intact. Stage a complete revision; a failed revision preserves the last working studio. Read [team-review.md](references/team-review.md) and update the sibling review-context.json for the changed journey and unresolved review questions. Create it when missing. Ground the welcome purpose and up to three consequential questions in the supplied brief and recorded feedback; preserve still-relevant wording and implementation guidance, and never invent requirements.

  1. Inspect revised screenshots at affected responsive frames, exercise the

changed journey and keyboard focus, and record evidence. Resolve pins only after the relevant change is rendered and checked. A static lint pass does not establish visual verification; absent browser inspection means unverified.

  1. Synchronize the specification, document and compatibility manifest using

[handoff.md](references/handoff.md) and the [ten-section template](references/design-spec-template.md). Update only affected specification sections. Record retained and rejected project preferences.

Return applied feedback and affected screens, remaining/stale pins, source and studio paths, and verification results. Plan is an optional next invocation. Opening, revising or selecting a design never auto-starts Plan, Ship, publication, deployment, review-link creation or review-URL import. When company review is requested, validate, render and inspect the current welcome context before using the studio's encrypted Share flow. Preserve reviewer attribution.

For company reviews and implementation handoff, follow [team-review.md](references/team-review.md). Keep review guidance outside product screens, preserve reviewer intent, and let the owner approve the refined handoff. Only an explicit Continue to Plan action may return the host-native Plan invocation for the current approved package. Preparing or approving a package does not write planning files, dispatch an agent, change Git, or start Ship.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Developer Tools