agentleFS
dagoStedagoSte/squadra/migliora/SKILL.md

migliora

Skill1.2k starsChanged 30 days agoMITView on GitHub

Improve a project's development workflow from observed failures, repeated work and avoidable waits. Apply scoped, verified remedies and useful project instructions, then automatically commit owned changes when the project's required checks and reviews are complete. Use after recurring development friction or when asked to improve the process; do not add rules without evidence.

Adopted by

Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Sep 13: 0 new projectsWeek of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projectsWeek of Oct 25: 0 new projectsWeek of Nov 1: 0 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 0 in all, so this is a hint, not a trend.

Who's talking about dagoSte/squadra

The biggest 5 of 40 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 40

Talked about on GitHub and Hacker News (40 times).

On GitHub · 39

34 more on GitHub
  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the project's operating instructions and recall its lessons.

    line 13
  2. Distinctive:

    Prefer fixing the tool to adding an instruction.

    line 16
  3. Distinctive:

    No actionable evidence means no change.

    line 25

≈ “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

Migliora

Answer in the user's language. This skill is bundled with Squadra and also works when the user names it directly. Resolve this directory's real location; the bundled CLI is ../scripts/squadra.py and the detailed workflow is the migliora guide. Read that guide.

Read the project's operating instructions and recall its lessons. Look for concrete failures, repeated proof runs, waits and manual steps in the current task's evidence. Choose a bounded remedy that preserves requirements and other sessions' changes. Prefer fixing the tool to adding an instruction. A useful instruction needs an observable trigger, evidence, an action, a real check and a retirement condition.

Apply the remedy within the existing authorized scope, verify it and automatically create a local commit containing only the owned, checked changes after any required independent review. Preserve staged work belonging to others and run native hooks. The bundled migliora apply helper manages only its block in AGENTS.md; code remedies use the project's ordinary workflow. Never bypass checks, publish or push implicitly, change requirements automatically, or approve project memory proposals. No actionable evidence means no change. Measure the effect at the next matching trigger and remove ineffective rules through the same checked workflow.

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.