turtleneck-help
Skill2 starsChanged 43 days agoMITView on GitHub
Quick-reference card for turtleneck levels, skills, and commands. One-shot display, not a persistent mode. Trigger: /turtleneck-help, "turtleneck help", "what turtleneck commands", "how do I use turtleneck".
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- turtleneck-reviewSkill
- turtleneckSkill
- turtleneck-stressSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
No level named: the gate picks napkin for cheap-ish undos and first cuts, full for expensive undos and multi-team boundaries, and says why.
- Very specific: line 47
If the ponytail skill is installed: turtleneck decides where the boundary goes, ponytail decides how little code goes inside it.
≈ “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.
Files
Turtleneck Help
Display this card when invoked. One-shot. Do not change level or persist anything.
Levels
| Level | Use when |
napkin | First cut, or cheap-ish to undo. Ten lines: options, pick, trade-off, one flip, one owner question. |
full | The six rungs, 8 to 12 stressors, both cross-exam passes, one-page record. |
deep | Expensive to undo, or a boundary several teams will live behind. Adds incidence matrix, attractors, contagion. |
No level named: the gate picks napkin for cheap-ish undos and first cuts,
full for expensive undos and multi-team boundaries, and says why. Deep is
always explicit. Switch: /turtleneck napkin|full|deep; an explicit level
wins. Off: "stop turtleneck".
Skills
| Command | Does |
/turtleneck [level] | Run the protocol on the decision at hand. Output is a decision record. |
/turtleneck-review | Gap list over an existing ADR, design doc, RFC, or PR description. Tags what was skipped. |
/turtleneck-stress | Residuality pass alone: stressors, residues, attractors, boundary candidates. No recommendation. |
/turtleneck-help | This card. |
The six rungs
- Ride the elevator: penthouse and engine room, both floors.
- Open the solution space: three options that differ in kind, plus defer, plus buy.
- Stress it: 8 to 12 stressors, two absurd, no probabilities.
- Price the options: build, run and who pays, undo, keeps open.
- Cross-examine: elevator pass, residuality pass.
- Decide or defer: "we give up X to get Y", flip conditions, owner decisions.
With ponytail
If the ponytail skill is installed: turtleneck decides where the boundary goes, ponytail decides how little code goes inside it. Either way, local code choices are outside turtleneck's gate.
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
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.