jay
Talk directly to Jay, CARBON's AI test manager: ask questions, discuss evidence, choose what to test, or request an assessment.
Skill by jarbon
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jarbon-jay
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/jay
What's inside
- Skill name
jay- Description
- Talk directly to Jay, CARBON's AI test manager: ask questions, discuss evidence, choose what to test, or request an assessment.
- License
- MIT
- Instructions
- 13 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- openai.yaml · agents/
- jay-dark.webp · assets/
- jay-light.webp · assets/
SKILL.md (first lines)
# Jay · AI Test Manager Agent Read [Jay's conversation and identity contract](../../references/jay-conversation.md) first. Reply directly as Jay. A greeting or question is a conversation, not permission to start testing. For a testing request, follow [this edition's CARBON workflow](../carbon/SKILL.md) or its available focused command. Preserve target resolution, evidence rules, edition limits, budgets and permissions. Do not route a question through a demo. <!-- jay-background --> For first-use quick assessment, automatic selection and optional background setup, read [first-use guidance](../../background/first-use.md). Explicit user scope and limits take precedence. <!-- /jay-background -->
From jarbon/carbon-lite, MIT.
More from jarbon/carbon-lite
- 0.612score
Testers.ai CARBON Test Harness Lite
jarbon
Local QA workflows, test evidence, screenshot maps and confidence reports for AI coding agents.
ConnectorAFreshness: ALocal★ 2Claude Desktop - 0.594score
carbon-background
jarbon
Set up, pause, inspect or review Jay's bounded background checks after code changes.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
carbon
jarbon
Test a project or verify a recent feature or bug fix with Jay: risk-based checks, reproducible findings and confidence in a visual report.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
j
jarbon
Talk directly to Jay, CARBON's AI test manager: ask questions, discuss evidence, choose what to test, or request an assessment.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
carbon-map
jarbon
Explore the current CARBON Lite assessment through a screenshot-led evidence map.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
carbon-settings
jarbon
Read or change project-local CARBON Lite testing preferences.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
carbon-studio
jarbon
Open CARBON Lite's portable local quality workspace or summarize supplied test evidence.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
carbon-accessibility
jarbon
Investigate accessibility using source, keyboard, zoom, visual and dynamic evidence.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
carbon-issues
jarbon
Hunt reproducible bugs, especially stateful and persona-driven failures common in AI-generated code.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
carbon-demo
jarbon
Create a fresh disposable bundled demo with or without existing tests.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
carbon-test
jarbon
Test one named feature, journey, API, component or behavior with CARBON Lite.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
carbon-help
jarbon
Explain the included CARBON Lite commands and suggest a useful next investigation.
SkillAFreshness: A★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Oct 4, 2026 (25 days ago)
- Last release
- Oct 3, 2026 (25 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/jarbon/carbon-lite
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jarbon
- 0.619score
CARBON
jarbon
AI testing harness with Jay: risk-based checks, bug investigation, and local evidence reports.
ConnectorAFreshness: ALocal★ 2Claude Code +5 - 0.612score
Testers.ai CARBON Test Harness Lite
jarbon
Local QA workflows, test evidence, screenshot maps and confidence reports for AI coding agents.
ConnectorAFreshness: ALocal★ 2Claude Desktop - 0.594score
carbon-background
jarbon
Set up, pause, inspect or review Jay's bounded background checks after code changes.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
carbon
jarbon
Test a project or verify a recent feature or bug fix with Jay: risk-based checks, reproducible findings and confidence in a visual report.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
j
jarbon
Talk directly to Jay, CARBON's AI test manager: ask questions, discuss evidence, choose what to test, or request an assessment.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
carbon-help
jarbon
Explain the included CARBON Lite commands and suggest a useful next investigation.
SkillAFreshness: A★ 2Claude Code +9
Cite this page
jay skill. Agent Mart. https://agentmart.dev/skills/jarbon-jay (last updated 2026-10-24)