Design Feedback Collector
Collect, structure, deduplicate, and resolve user and agent feedback on UI/UX skills, subprocesses, design directions, progress-screen gates, Stitch/Pencil/Figma outputs, and implementation steps. Use when comments need statuses such as open, accepted, partially accepted, applied, rejected, or when review-board/progress-page fields must become actionable decisions.
Install
$ agentstack add skill-sergekostenchuk-ui-ux-agent-skill-system-design-feedback-collector ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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 Used
- ● Environment & secrets Used
- ✓ 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-sergekostenchuk-ui-ux-agent-skill-system-design-feedback-collector) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Design Feedback Collector
This skill turns comments into a controlled feedback register. It is not a visual critic by itself; it structures feedback so the chair and specialist skills can act without losing context.
Operating Modes
collect: gather user comments, agent critiques, and review-board notes.triage: assign severity, owner, affected skill, affected subprocess, and decision status.resolve: convert feedback into accepted, partially accepted, rejected, or applied decisions.sync-dashboard: update review-board or task-plan-facing summaries.sync-progress: update progress-screen user gates and feedback artifacts after a user decision.handoff: send accepted feedback to the right specialist skill.
Required Workflow
- Read [references/feedback-status-contract.md](references/feedback-status-contract.md).
- Use [assets/feedback-register.schema.json](assets/feedback-register.schema.json) as the register shape.
- Separate feedback sources:
- user comment;
- colleague/agent critique;
- validation finding;
- council decision.
- Assign each item:
- target skill or subprocess;
- severity;
- status;
- owner;
- required action;
- evidence needed.
- Use color/status semantics:
- blue: no comment/open empty state;
- red: unresolved comment exists;
- orange: partially accepted or partially applied;
- green: accepted and applied.
- For progress-screen gates, preserve
gate_id, selected option, comment, target phase/subprocess, and source artifact. - Do not mark an item applied unless the changed artifact or decision record is referenced.
Safety Rules
- Remove secrets, tokens, private URLs,
.envvalues, recovery codes, and private screenshots from feedback before saving. - Do not collapse disagreement into a fake consensus; preserve rejected and partially accepted reasoning.
- For high-impact disagreements, route to
senior-ui-ux-orchestratorin council mode.
Handoff Shape
Feedback mode:
Target skill/subprocess:
Source:
Status:
Severity:
Decision:
Applied artifact:
Open risk:
Next owner:Validation
When editing this skill, run:
python3 $CODEX_HOME/skills/.system/skill-creator/scripts/quick_validate.py $CODEX_HOME/skills/design-feedback-collector
python3 $CODEX_HOME/skills/senior-skill-architect/scripts/lint_production_skill.py $CODEX_HOME/skills/design-feedback-collector
python3 -m json.tool $CODEX_HOME/skills/design-feedback-collector/evals/evals.json >/dev/nullSource & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: sergekostenchuk
- Source: sergekostenchuk/ui-ux-agent-skill-system
- License: Apache-2.0
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.