bat-adhoc SKILL.md skillA

bat-adhoc from homeassistant-ai/ha-mcp is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add homeassistant-ai/ha-mcp/bat-adhoc@git:20260926.4e60907

Pins git:20260926.4e60907 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
homeassistant-ai/ha-mcp
Path
.claude/skills/bat-adhoc/SKILL.md
Versions recorded
3
Latest version
git:20260926.4e60907, committed Sep 26, 2026
First version recorded
Feb 16, 2026
Size
5,534 bytes
Repository stars
5,167
License
MIT

Run bot acceptance tests to validate MCP tools work correctly from a real AI agent's perspective. Use when testing PRs, detecting regressions, or verifying tool changes end-to-end with Claude/Gemini CLIs.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# BAT - Bot Acceptance Testing

Bot acceptance testing validates that MCP tools work correctly from a real AI agent's perspective. You design test scenarios dynamically, run them via `tests/uat/run_uat.py`, and evaluate results.

## When to Use BAT

- **PR validation**: Test that tool changes work correctly from an agent's perspective
- **Regression detection**: Compare behavior between branches
- **Integration verification**: Ensure MCP tools work end-to-end with real agent CLIs

## Workflow

1. **Analyze the change**: Read the diff, identify which tools are affected
2. **Design scenario**: Generate a scenario JSON with setup/test/teardown prompts
3. **Run the script**: Pipe the scenario to `uv run python tests/uat/run_uat.py`
4. **Evaluate summary**: Check `all_passed` per agent. If true, you're done.
5. **Dig deeper on failure**: Read `results_file` for full output, stderr, raw JSON
6. **Regression check**: If test fails, re-run with `--branch master` to compare

## Output Structure

The runner returns a **concise summary** to stdout (saves context when all passes):

```json
{
  "results_file": "/tmp/bat_results_abc123.json",
  "agents": {
    "gemini": {
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add homeassistant-ai/ha-mcp/bat-adhoc@sha256:56142a19c69884fd

The line at the top of this page pins the label git:20260926.4e60907, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_tpvjv2o4ne7fxeyn.svg)](https://markdownregistry.com/a/art_tpvjv2o4ne7fxeyn)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Feb 16, 2026 and Sep 26, 2026, about one every 111 days.

versioncommittedcommitsizeaudit
git:20260926.4e60907 latest2026-09-26 4e60907 5,534 BA view · diff
git:20260217.b022d3a2026-02-17 b022d3a 5,486 BA view · diff
git:20260216.4e72ecf2026-02-16 4e72ecf 5,063 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5534 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

homeassistant-ai/ha-mcp · 5,167 stars · license MIT · pushed 2026-10-21 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_tpvjv2o4ne7fxeyn
GET https://markdownregistry.com/api/v1/resolve?ref=homeassistant-ai/ha-mcp/bat-adhoc
GET https://markdownregistry.com/api/v1/blob/56142a19c69884fd93abb7015ad942b068b4d293a87b4f46505c839078435f74

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from homeassistant-ai/ha-mcp

bat-story-eval SKILL.md skill
homeassistant-ai/ha-mcp · .claude/skills/bat-story-eval/SKILL.md · Compare MCP tool behavior between target and baseline versions using pre-built and custom stories with diff-based…
git:20260926.4e60907 · audit A · 5,167 stars
contrib-pr-review SKILL.md skill
homeassistant-ai/ha-mcp · .claude/skills/contrib-pr-review/SKILL.md · Review a contribution PR for safety, quality, and readiness. Checks for security concerns, test coverage, size…
git:20260928.793abe9 · audit A · 5,167 stars
contributors-update SKILL.md skill
homeassistant-ai/ha-mcp · .claude/skills/contributors-update/SKILL.md · Find merged PR authors missing from README and update the contributors list after approval
git:20260719.177dae1 · audit A · 5,167 stars
issue-analysis SKILL.md skill
homeassistant-ai/ha-mcp · .claude/skills/issue-analysis/SKILL.md · Deep analysis of a single GitHub issue with codebase exploration, implementation planning, and architectural…
git:20260516.bad13aa · audit A · 5,167 stars
issue-to-pr-resolver SKILL.md skill
homeassistant-ai/ha-mcp · .claude/skills/issue-to-pr-resolver/SKILL.md · Implement a GitHub issue end-to-end — create a worktree branch, implement the feature with tests, create a draft PR…
git:20260926.4e60907 · audit A · 5,167 stars
my-pr-checker SKILL.md skill
homeassistant-ai/ha-mcp · .claude/skills/my-pr-checker/SKILL.md · Manage your own GitHub pull requests — check CI status, inline review comments, PR-level comments, resolve review…
git:20260926.4e60907 · audit A · 5,167 stars
wt SKILL.md skill
homeassistant-ai/ha-mcp · .claude/skills/wt/SKILL.md · Create a git worktree in worktree/ subdirectory with up-to-date master
git:20260506.0c8cd0d · audit A · 5,167 stars
AGENTS.md AGENTS.md file
homeassistant-ai/ha-mcp · AGENTS.md
git:20261019.621a4f5 · audit A · 5,167 stars
CLAUDE.md CLAUDE.md file
homeassistant-ai/ha-mcp · CLAUDE.md
git:20250919.2eb83e0 · audit B · 5,167 stars
AGENTS.md@homeassistant-addon-webhook-proxy-dev AGENTS.md file
homeassistant-ai/ha-mcp · homeassistant-addon-webhook-proxy-dev/AGENTS.md
git:20260702.a543521 · audit A · 5,167 stars
CLAUDE.md@homeassistant-addon-webhook-proxy-dev CLAUDE.md file
homeassistant-ai/ha-mcp · homeassistant-addon-webhook-proxy-dev/CLAUDE.md
git:20260702.a543521 · audit B · 5,167 stars
AGENTS.md@homeassistant-addon-webhook-proxy AGENTS.md file
homeassistant-ai/ha-mcp · homeassistant-addon-webhook-proxy/AGENTS.md
git:20261001.17d8658 · audit A · 5,167 stars

Every file in homeassistant-ai/ha-mcp

Browse by kind, by grade A, or by owner.