agentleFS
Sign inStart free
MesteriisMesteriis/Engineering-Bible-AI/skills/agents-md-retrospective/SKILL.md

agents-md-retrospective

Skill0 starsChanged 4 months agoMITView on GitHub

Updates AGENTS.md after a repeated verified failure. Do not use for one-off preferences or speculative rules.

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Read the relevant local and global instruction files.

    line 12
  2. Distinctive:

    Add the smallest durable instruction that would have prevented it.

    line 14
  3. Distinctive:

    Avoid duplicating existing rules.

    line 15
  4. Distinctive:

    Do not add secrets or environment-specific sensitive values.

    line 20
  5. Distinctive:

    Do not turn AGENTS.md into a skill body.

    line 21
  6. Distinctive:

    Prefer routing rules and validation commands over broad role prose.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

AGENTS.md Retrospective

Make instruction updates only when the pattern is durable.

Workflow

  1. Read the relevant local and global instruction files.
  2. Identify the exact repeated failure or missing rule.
  3. Add the smallest durable instruction that would have prevented it.
  4. Avoid duplicating existing rules.
  5. Validate by grepping the final instruction and checking for conflicts.

Rules

  • Do not add secrets or environment-specific sensitive values.
  • Do not turn AGENTS.md into a skill body.
  • Prefer routing rules and validation commands over broad role prose.
  • Respect scoped directory instructions.

Output

  • changed instruction file
  • rule added or changed
  • why it belongs there
  • validation command

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.

Reviews can't be read right now.

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.

Check your setup, free