visual-evidence
visual-evidence
Capture browser screenshots and GIF recordings using Playwright headless Chromium. Upload to cloud storage for embedding in PRs and reports.
When to Use
- After implementing a bug fix (before/after comparison)
- After implementing a feature (demo key flows)
- During PR review to verify visual changes
- Interaction/timing bugs (double-click, loading states, race conditions) → use GIF recording
When NOT to Use
- Backend-only changes, config/infra, test-only, CLI tools, APIs without UI
- Skip if Playwright install fails — visual evidence is best-effort, never blocks the pipeline
Prerequisites
Install Playwright and Chromium in the remote environment:
More from fellowship-dev/dogfooded-skills
entropy-check
Sensor — checks doc freshness and computes domain quality grades. Never fixes. Detects staleness, missing coverage, and FlowChad gaps. Updates QUALITY_SCORE.md. Skips inapplicable signals per repo.
17distill
Post-mission audit and distillation — capture mode classifies a completed mission using an 8-code failure taxonomy and writes an audit JSON; analyze mode aggregates audit JSONs into a findings report and creates GitHub issues with recommendations.
15migrate-skill
Move a skill from claude-toolkit plugin (or local .claude/skills) into the dogfooded-skills library, then import it back. Use when consolidating skills into the shared repo.
15skill-builder
Write a high-quality agent skill — covers frontmatter spec, section structure, quality criteria, and common antipatterns.
14popsicle
Agent-native onboarding doc generator — builds coverage maps, health baselines, generated docs, and agent adapters so any AI tool can autonomously navigate your repo.
9setup-harness
Scaffold the knowledge layer for a repo — ARCHITECTURE.md, QUALITY_SCORE.md, enhanced docs/code-structure.md, docs/code-guidelines.md, and FlowChad flow stubs. Gives agents a map, not a 1,000-page manual.
8