fleet-ladder
Skill2 starsChanged 10 days agoLicence not identifiedView on GitHub
Use before any work is handed to a model (building, grading, or a bounded worker job), when a provider is down and you need the fallback order, or when the rung is frontier/design/reason and must honor research-before-heavy-lift. States the desired selection discipline (task + evidence work the agent must do before dispatch) and points at the configured ladder file as the only place that knows actual routing. Does NOT itself rank, score, or filter candidates; the public pack ships no resolver and no Fleet executable. Trigger words: fleet, ladder, dispatch, fallback, model down, provider down, which model, availability, frontier research, research seams, rung policy, thinking floor, token efficiency, research before builder, capability, oauth, api, quota, essence, checkpoint.
In this repository62 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- absorbSkill
- agent-buildSkill
- architecture-engineerSkill
- backs-build-flowSkill
- backs-pack-syncSkill
- backs-session-rolloverSkill
- blind-evalSkill
- blind-tribunalSkill
- bounded-loopsSkill
- bughuntSkill
- building-with-backsSkill
- cam-iot-inventorySkill
- clean-code-gauntletSkill
- co-healthSkill
- conscientious-objectorSkill
- context-engineerSkill
- context-engineerSkill
- context-engineerSkill
- debugging-engineerSkill
- decision-barSkill
- design-critiqueSkill
- design-tasteSkill
- elite-buildSkill
- fix-shitSkill
- fleet-dispatchSkill
- gpu-dispatchSkill
- gradeSkill
- guided-stepsSkill
- harness-optimizerSkill
- human-calibrationSkill
- human-voiceSkill
- incident-closureSkill
- intent-compilerSkill
- invariant-floorSkill
- karpathySkill
- leap-protocolSkill
- live-researchSkill
- model-fusionSkill
- operator-essenceSkill
- operator-intent-deductionSkill
- operator-intent-deductionSkill
- optimusSkill
- osha-botSkill
- parallel-workSkill
- rea-investigationSkill
- red-firstSkill
- reload-vsc-and-verifySkill
- repair-loopSkill
- repo-mapSkill
- root-cause-firstSkill
- scrub-plugin-pack-literalsSkill
- seam-engineeringSkill
- secure-deliverySkill
- session-handoffSkill
- sniper-testingSkill
- tribunalSkill
- truth-auditSkill
- turn-and-burnSkill
- understanding-gatesSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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.