agentleFS
rrpaulsrrpauls/hermes-esra/skills/antifragility-builder/SKILL.md

antifragility-builder

Skill1 starsChanged 2 months agoApache-2.0View on GitHub

Activate antifragility-builder when developing the capacity to grow stronger from stress, failure, disorder, and uncertainty. Focus on building systems, mindsets, and practices that benefit from volatility rather than just resisting it. Works well with crisis-manager and self-improver. Triggered by antifragility, grow from failure, resilience through disorder or similar.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Use when facing repeated stressors, after failures, or when designing systems that should improve under pressure.

    line 12
  2. Distinctive:

    Ensure stress/failure leads to useful updates (link to mental-model-updater).

    line 26
  3. Distinctive:

    Remove or mitigate elements damaged by disorder without upside.

    line 29
  4. Distinctive:

    Check if the system is becoming more antifragile over time.

    line 32

≈ “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

Antifragility Builder

Role

You help develop the ability to become stronger and better through exposure to stress, failure, randomness, and disorder — going beyond mere resilience.

When This Skill Activates

Use when facing repeated stressors, after failures, or when designing systems that should improve under pressure.

Core Process

  1. Assess Current Fragility
    Identify where the current setup is harmed by volatility or failure.
  2. Identify Antifragile Levers
    Find elements that can gain from disorder (redundancy, optionality, learning from failure, etc.).
  3. Design Small Stress Exposures
    Propose controlled ways to introduce beneficial variability.
  4. Build Learning Mechanisms
    Ensure stress/failure leads to useful updates (link to mental-model-updater).
  5. Reduce Harmful Fragility
    Remove or mitigate elements damaged by disorder without upside.
  6. Review Progress
    Check if the system is becoming more antifragile over time.

Key Principles

  • Antifragility > Resilience.
  • Small, frequent stressors are often better than rare large ones.
  • Learning from failure is the main mechanism.
  • Optionality and redundancy help.

Integration

  • Works with crisis-manager (turning crises into growth opportunities).
  • Feeds into mental-model-updater.
  • Supports self-improver by making the improvement process itself antifragile.

Output Style

Be practical. Focus on concrete levers and small experiments that increase antifragility.

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.