Skip to content
SkillCheatSheet Sign in

bat-story-eval

An AI agent skill from homeassistant-ai/ha-mcp, scored 64 out of 100 by code.

64/ 100C

Code score by group

  • Spec20/20
  • Description7/20
  • Procedure12/15
  • Done criteria4/15
  • Resources9/10
  • Scripts2/8
  • Safety7/7
  • Upkeep3/5

It loses the most points in Description (13), the group that checks whether the description says what the skill does and when to use it.

What the author says it does

Compare MCP tool behavior between target and baseline versions using pre-built and custom stories with diff-based triage.

This is the description in the skill's own SKILL.md, written by its author, not by SkillCheatSheet.

Repository
homeassistant-ai/ha-mcp
Folder
.claude/skills/bat-story-eval
License
MIT
GitHub stars
7,619
SKILL.md lines
376
Other files
2

Add bat-story-eval to your agent

npx skills add homeassistant-ai/ha-mcp --skill bat-story-eval

The command uses the open skills CLI. A skill is instructions and scripts your agent will follow, so read it first: open the folder on GitHub at the commit that was scored.

More skills from homeassistant-ai/ha-mcp

  1. my-pr-checker

    Manage your own GitHub pull requests — check CI status, inline review comments, PR-level comments, resolve review threads, fix issues, and iterate until all checks pass and thread…

    67C
  2. bat-adhoc

    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…

    66C
  3. issue-analysis

    Deep analysis of a single GitHub issue with codebase exploration, implementation planning, and architectural assessment. Use when you need to analyze a GitHub issue, assess its co…

    66C
  4. issue-to-pr-resolver

    Implement a GitHub issue end-to-end — create a worktree branch, implement the feature with tests, create a draft PR, then iteratively resolve all CI failures and review comments u…

    66C
  5. contributors-update

    Find merged PR authors missing from README and update the contributors list after approval

    63C
  6. contrib-pr-review

    Review a contribution PR for safety, quality, and readiness. Checks for security concerns, test coverage, size appropriateness, and intent alignment. Use when reviewing external c…

    58C
  7. wt

    Create a git worktree in worktree/ subdirectory with up-to-date master

    50D

All skills in homeassistant-ai/ha-mcp

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.