Agf Deploying Uat

Runbook to bring up an isolated local UAT compose stack and smoke-test it before hand-off

Works with setup

Test report

Verdict
Works with setup
Score
8.0/10
Tested
Jul 21, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · 018ec25

Fetched the SKILL.md and spot-checked its three referenced files via raw GitHub: .claude/standards/deployment.md (200), .claude/commands/agf-deploy-uat.md (200), .claude/agents/deploy-engineer.md (200); grepped deployment.md and confirmed the cited "UAT 环境部署" §6 and "P0/P1 强制门" sections plus the literal +900 offset (6332/8900/8980) really exist and match the skill. Frontmatter parses with name+description; body is only standard docker compose / curl / psql commands with no curl|sh, base64, secret exfiltration, or injection text; paths use ${APP_NAME}/localhost/relative, no hardcoded machine paths. Could not run the output stage: deploying needs a live Docker daemon, the project's compose stack, and a .env.uat secrets file I cannot execute — producing a deploy report would only restate the skill's own template, so outputMeasured=false and verdict=setup.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 5/10
  • Docs & honesty 5/5

What Agf Deploying Uat does

A step-by-step runbook for the AppGenesisForge deploy-engineer role that deploys merged-to-main code to a physically isolated local UAT Docker Compose stack (independent project name plus +900 port offset), runs in-container Alembic migration, and smoke-tests with real curl/psql output before handing off to qa-engineer. Triggers after code review plus SIT audit pass and merge to main, when a product-lead confirms "deploy UAT" or runs /agf-deploy-uat. Excludes mini-program uploads and E2E/UAT acceptance testing, which belong to other roles.

How to install Agf Deploying Uat

git clone --depth 1 https://github.com/pcliangx/AppGenesisForge.git /tmp/agf-deploying-uat-src
mkdir -p ~/.claude/skills
cp -R /tmp/agf-deploying-uat-src/.claude/skills/agf-deploying-uat ~/.claude/skills/agf-deploying-uat
# Runbook is project-specific to AppGenesisForge. To actually execute a deploy you need:
#   - Docker daemon running (docker compose version)
#   - The AppGenesisForge repo with its docker-compose files (frontend + backend + postgres)
#   - A .env.uat file (gitignored, holds DB/LLM secrets + port-offset vars) you provide
#   - Free +900 ports: 6332 (postgres) / 8900 (backend) / 8980 (frontend/caddy)
# The skill also references ../../standards/deployment.md (single source for the isolation
# contract); that file lives in the same repo under .claude/standards/deployment.md.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agf Deploying Uat

  • /agf-deploying-uat Runbook to bring up an isolated local UAT compose stack and smoke-test it before hand-off

It also activates on plain-language prompts like these:

  • Deploy the merged main branch to the UAT stack
  • Run pre-flight checks before the UAT deployment
  • Bring up the isolated UAT compose environment

Frequently asked questions

Is the Agf Deploying Uat skill free?
Yes. The skill itself is free from pcliangx/AppGenesisForge. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agf Deploying Uat work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Works with setup. Fetched the SKILL.md and spot-checked its three referenced files via raw GitHub: .claude/standards/deployment.md (200), .claude/commands/agf-deploy-uat.md (200), .claude/agents/deploy-engineer.md (200); grepped deployment.md and confirmed the cited "UAT 环境部署" §6 and "P0/P1 强制门" sections plus the literal +900 offset (6332/8900/8980) really exist and match the skill. Frontmatter parses with name+description; body is only standard docker compose / curl / psql commands with no curl|sh, base64, secret exfiltration, or injection text; paths use ${APP_NAME}/localhost/relative, no hardcoded machine paths. Could not run the output stage: deploying needs a live Docker daemon, the project's compose stack, and a .env.uat secrets file I cannot execute — producing a deploy report would only restate the skill's own template, so outputMeasured=false and verdict=setup.
What is the Agf Deploying Uat SkillProof Score?
8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 5/5.
How do I install Agf Deploying Uat?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agf Deploying Uat with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.