Skip to content
Get packs

Orchard Release Review

Checks deployment evidence and recovery conditions before a release decision.

Source Download skill
Repository
rohitg00/ai-engineering-from-scratch
Stars
76,331
Licence
MIT
Files
2 files

What it does

This skill gives an AI agent a short instruction set for reviewing a software release. When installed, the agent reads a companion reference file (references/restore.md) and includes a timestamp in its release decision. The provided SKILL.md is very brief, so the detailed review criteria live entirely in that reference file, which was not included in the files reviewed.

Great for

  • Teams testing an example of how a release-review skill is structured
  • Developers learning how SKILL.md files reference supporting documents

Skip it if

  • Making real production release decisions, because the skill is a minimal example and its checks are not described in the reviewed files
  • Environments needing verified recovery procedures, since the restore criteria are in a file that was not available for review

Try asking

  • “Review the deployment evidence for this release and give me a go or no-go decision.”
  • “Check whether the recovery conditions are met before we ship.”
Step-by-step guide: how to use Orchard Release ReviewInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    orchard-release.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip orchard-release.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip orchard-release.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Read references/restore.md yourself before relying on this skill, since its actual criteria are unknown from SKILL.md alone.
  • Treat the output as a prompt-driven suggestion and verify deployment evidence independently.

What's inside

  • references/restore.md
  • SKILL.md

Redistributed unmodified from rohitg00/ai-engineering-from-scratch under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.