agentleFS
danielmarbachdanielmarbach/turtleneck/skills/turtleneck-stress/SKILL.md

turtleneck-stress

Skill2 starsChanged 44 days agoMITView on GitHub

Run the residuality pass alone against an existing design: generate random business and technical stressors including absurd ones, record what breaks and survives per component, find the stressors that break the same components, and propose where a boundary wants to be. For designs that already exist and need stress, not a fresh decision. Use when the user says "stress this design", "what breaks", "find the hidden coupling", "residuality", "what happens when", or invokes /turtleneck-stress.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Leave a labeled slot: stressors only the owner can add.

    line 38
  2. Very specific:

    No recommendation. This skill stresses.

    line 59
  3. Distinctive:

    Do not soften stressors because they seem unlikely.

    line 63

≈ “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

Turtleneck stress

Rung 3 of the protocol, on its own, against a design that already exists. Input is a description, a diagram, a repo layout, or a doc. Read it fully. List the components you see before generating anything.

Procedure and vocabulary in references/residuality.md.

Steps

  1. List components as the design names them. Do not rename or regroup yet.
  2. Generate stressors: 8 to 12 at full, 20 or more at deep. Spread across market, regulation, organization, technology. At least two absurd. No probabilities.
  3. Per stressor, one line: what breaks, what survives, what you would change.
  4. Find attractors: stressors that break the same components. Name the coupling each attractor reveals, and say whether it is visible in the code or runs through the business environment.
  5. At deep: incidence matrix, then contagion trace for the top two stressors across the proposed or existing boundaries.
  6. Propose boundary changes derived from the residues only. Mark each as "from residues" and note if the existing boundary came from the org chart instead.
  7. Leave a labeled slot: stressors only the owner can add. State that it is empty.

Output

Components: <list as named>

| # | Stressor | Breaks | Survives | Change |
|---|----------|--------|----------|--------|
...

Attractors:
- <stressors n, m, k> → <components> : <coupling, visible or hyperliminal>

Boundary candidates (from residues):
- <where, why, what contagion it would stop>

Owner stressors: empty. Add the ones from your market before trusting this.

No recommendation. This skill stresses; /turtleneck decides.

Boundaries

Do not soften stressors because they seem unlikely. Do not drop the absurd ones. Do not propose technology. If the input has no components you can name, ask for the design rather than inventing one.

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.