agentleFS
Muriel-SalvanMuriel-Salvan/x_aeon_agents/skills/validating-production-quality/SKILL.md

validating-production-quality

Skill2 starsChanged 2 months agoBSD-3-ClauseView on GitHub

Validates that the task is following all production-grade quality checks. What this does is check for regressions, update documentation, update the branch on the latest base, commit any remaining changes, push them on GitHub and create a Pull Request. Use this when attempting task completion on a task or when the user asks for validating production qulity gates.

  • Commits and pushes

The file

Show its rules and text

We split this skill into the rules it gives an agent

21 rules. About 0 are common, 15 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈15

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When validating production quality, follow those steps.

    line 16
  2. Distinctive:

    Before executing anything, create a checklist named validating-production-quality Execution Checklist with all steps of these instructions.

    line 20
  3. Distinctive:

    After completing each step of these instructions, mark the item in the validating-production-quality Execution Checklist as completed.

    line 22
  4. Distinctive:

    Do not skip any item.

    line 23
  5. Distinctive:

    If an item cannot be executed, explicitly explain why.

    line 24
  6. Distinctive:

    Never mark the task as completed while any item from the validating-production-quality Execution Checklist remains open.

    line 25
  7. Distinctive:

    Always tell the user "SKILL: I am validating production quality" to inform the user that you are running this skill.

    line 29
  8. Distinctive:

    Always run all test scenarios.

    line 33
  9. Distinctive:

    Always fix all the failures that you see in the tests output.

    line 34
  10. Very specific:

    Always use skill: updating-doc to update the project documentation.

    line 43
  11. Very specific:

    Always use skill: committing-changes to commit all your changes in the current branch.

    line 47
  12. Very specific:

    Always use skill: syncing-branch-with-base to make sure the current branch is up-to-date with its base.

    line 51
  13. Distinctive:

    Always check that there is no merge commit between the current branch and its base.

    line 55
  14. Very specific:

    If you find any merge commit, then always remove them by rebasing the branch in a linear way, using cli: git rebase, and push again to the …

    line 56
  15. Distinctive:

    Always check on the corresponding GitHub project if there is already a Pull Request created for the current branch.

    line 67
  16. Very specific:

    If there isn't any Pull Request for the current branch, then always use skill: creating-pull-request to create one.

    line 68
  17. Distinctive:

    Before declaring the task complete:

    line 78
  18. Distinctive:

    If any step was not executed, execute it now.

    line 82
  19. Very specific:

    Always use it every time another skill specifically mentions skill: validating-production-quality.

    line 86
  20. Distinctive:

    Always use it every time the user asks you to validate production quality gates.

    line 87
  21. Distinctive:

    Always use it just before attempting completion of a task that is a full production-grade feature or bug fix.

    line 88

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Validating production quality

Sequential steps to be followed when using this skill

When validating production quality, follow those steps.

Create the validating-production-quality Execution Checklist (MANDATORY)

  • Before executing anything, create a checklist named validating-production-quality Execution Checklist with all steps of these instructions.
  • The validating-production-quality Execution Checklist must include all numbered steps explicitly.
  • After completing each step of these instructions, mark the item in the validating-production-quality Execution Checklist as completed.
  • Do not skip any item.
  • If an item cannot be executed, explicitly explain why.
  • Never mark the task as completed while any item from the validating-production-quality Execution Checklist remains open.

1. Inform the user

  • Always tell the user "SKILL: I am validating production quality" to inform the user that you are running this skill.

2. Fix any potential regression

  • Always run all test scenarios.
  • Always fix all the failures that you see in the tests output.

For example, in a Python project:

python -m unittest

3. Update documentation

  • Always use skill: updating-doc to update the project documentation.

4. Commit all pending modifications

  • Always use skill: committing-changes to commit all your changes in the current branch.

5. Sync the branch with its base

  • Always use skill: syncing-branch-with-base to make sure the current branch is up-to-date with its base.

6. Remove any merge commit in the current branch

  • Always check that there is no merge commit between the current branch and its base.
  • If you find any merge commit, then always remove them by rebasing the branch in a linear way, using cli: git rebase, and push again to the GitHub remote using --force-with-lease option.

Example, in case of merge commits found:

git log --oneline --ancestry-path github/main..my_branch
git rebase main
git push github --force-with-lease

7. Create a Pull Request for the current branch

  • Always check on the corresponding GitHub project if there is already a Pull Request created for the current branch.
  • If there isn't any Pull Request for the current branch, then always use skill: creating-pull-request to create one.

Example to check for a Pull Request:

gh pr list --head my_branch
# Execute skill creating-pull-request if our branch is not in this list

Final Verification (MANDATORY)

Before declaring the task complete:

  • Re-list all numbered steps from the validating-production-quality Execution Checklist.
  • Confirm each one was executed.
  • If any step was not executed, execute it now.

When to use it

  • Always use it every time another skill specifically mentions skill: validating-production-quality.
  • Always use it every time the user asks you to validate production quality gates.
  • Always use it just before attempting completion of a task that is a full production-grade feature or bug fix.

Usage and code examples

Before attempting completion on a task

# 1. Check tests
python -m unittest
# Fix any failing test

# 2. Run skill updating-doc.

# 3. Run skill committing-changes.

# 4. Run skill syncing-branch-with-base

# 5. Remove merge commits
git log --oneline --ancestry-path github/main..my_branch
git rebase main
git push github --force-with-lease

# 6. Create Pull Request if not already present
gh pr list --head my_branch
# Run skill creating-pull-request

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.