sg-visual-fix
/sg-visual-fix — Fix Annotated Screenshots
Take human-annotated screenshots from /sg-visual-review, analyze the marked problems, fix the code, and produce before/after comparison.
Recommended model: Sonnet 4.6 for mineures fixes (CSS tweaks, copy changes, small layout nits). Switch to Opus 4.7 if the annotations point to a full component refonte or cross-file logic change. Use
/model sonnetor/model opusaccordingly.
Flow
Human annotates screenshots in review.html
→ clicks "Validate & Generate Report"
→ fix-manifest.json is saved to the server via POST /save-manifest
→ runs /sg-visual-fix
→ AI reads each annotated screenshot
→ AI reads the annotation coordinates (problem region)
→ AI identifies the visual bug in that region
→ AI traces to source code (component, CSS, data)
→ AI implements the fix
→ AI rebuilds the app
More from bacoco/shipguard
sg-scout
GitHub intelligence for ShipGuard — scans repos for code audit, debugging, and self-improving agent techniques, then files actionable improvement proposals. Use when you want to discover new approaches, benchmark against similar tools, or find inspiration for ShipGuard improvements. Trigger on "sg-scout", "scout github", "find skills", "benchmark shipguard", "veille technique", "competitive analysis", "what are others doing", "find improvements".
1sg-improve
Auto-improve ShipGuard from real session learnings. Run this after any /sg-code-audit, /sg-visual-run, or debugging session. Analyzes what worked, what broke, and what was slow — saves project-specific learnings locally (zone sizing, patterns, infra timing) and files generic improvements as GitHub issues. The local learnings feed back into the next audit run automatically. Trigger on "sg-improve", "improve shipguard", "ameliore shipguard", "shipguard feedback", "session insights", "retex", "retrospective", "what did we learn".
1sg-record
Record browser interactions as replayable ShipGuard test manifests. Opens a Playwright browser with a floating toolbar — user navigates, clicks Check to mark assertions, clicks Stop to generate YAML. Trigger on "sg-record", "record test", "record interactions", "macro recorder", "enregistrer test", "enregistre les interactions".
1sg-visual-review
Generate an interactive HTML screenshot review page from Visual test results. Browse all test screenshots in a grid, filter by status/category, annotate problems with a pen tool, multi-select failed tests, and export re-run manifests. Trigger on "sg-visual-review", "visual review", "review screenshots", "show test results", "review visual", "visual-review", "show results", "test review".
1sg-code-audit
Parallel AI codebase audit — dispatches agents to find and fix bugs across the entire repo. Produces structured JSON results viewable in /sg-visual-review. Trigger on "sg-code-audit", "code audit", "audit codebase", "find bugs", "code-audit", "audit code", "static audit", "security audit", "ship guard".
1sg-visual-run
Execute Visual test manifests using agent-browser with hybrid scripted+LLM assertions. Accepts natural language to describe what to test or what changed — the skill finds and runs the right tests, generating missing ones if needed. Trigger on "sg-visual-run", "visual run", "run visual tests", "test regressions", "run tests", "visual-run", "check if the app works", "I changed X check it still works".
1