evidence-driven-testing
Capture observable runtime proof with video, screenshots, or measured output.
Skill by michaelshimeles
Chalk Labs
Need help deploying evidence-driven-testing?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/jaydubya818-evidence-driven-testing-720e29
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: not checked yet.
What's inside
- Skill name
evidence-driven-testing- Description
- Capture observable runtime proof with video, screenshots, or measured output. Use when a change needs evidence beyond test reports.
- License
- unknown
- Compatibility
- Requires Python 3 and FFmpeg for recording, or Node.js 20+ and Chromium for headless capture. Desktop capture also needs OS screen-recording access. Publishing evidence requires network access and authorized destination tooling.
- Metadata
- risk: medium · owner: software-factory · author: michaelshimeles · version: 1.3.0 · capabilities: runtime-evidence,visual-evidence,test-reporting
- Instructions
- 304 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (6)
- SKILL.md
- openai.yaml · agents/
- evidence.py · scripts/
- package-lock.json · scripts/playwright/
- package.json · scripts/playwright/
- run-playwright.sh · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from jaydubya818/skillz
- 0.586score
api-and-interface-design
Addy Osmani and Skillz contributors
Design API contracts, compatibility, and duplicate-safe mutations.
SkillAFreshness: A★ 1Claude Code +9 - 0.586score
deprecation-and-migration
Addy Osmani and Skillz contributors
Retire APIs or migrate consumers and persistent data across releases.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
an
Builder.io
Operate granted Agent-Native apps through Dispatch MCP; use for /an.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
ci-cd-and-automation
Addy Osmani and Skillz contributors
Create or change CI/CD pipelines, quality gates, and delivery controls.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
efficient-frontier
Builder.io
Delegate costly independent work while a frontier model retains judgment.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
factory-babysit-pr
Builder.io
Monitor one authorized PR with separate fix, publish, reply, and merge gates.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
factory-collect
Builder.io
Triage configured product signals under separate fix, reply, and close policies.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
efficient-fable
Builder.io
Delegate bounded independent work while Claude Fable retains judgment.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
agent-watchdog
Builder.io
Audit, monitor, compare, or repair another agent's session or PR when asked.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 17, 2026 (1 month ago)
- Last release
- Sep 18, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.3.0
- License
- License unknown
- Repository
- github.com/jaydubya818/skillz
- Website
- agentskills.io
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from michaelshimeles
- 0.563score
evidence-driven-testing
michaelshimeles
Capture observable runtime proof with video, screenshots, or measured output.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
code-structure
michaelshimeles
Separate orchestration from reusable mechanics while preserving transactions.
SkillBFreshness: B★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get evidence-driven-testing running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
evidence-driven-testing skill. Agent Mart. https://agentmart.dev/skills/jaydubya818-evidence-driven-testing-720e29 (last updated 2026-10-24)