agentleFS
2389-research2389-research/speed-run/skills/speed-run/SKILL.md

speed-run

Skill1 starsChanged 4 months agoMITView on GitHub

Token-efficient code generation pipeline via Cerebras hosted LLM; requires CEREBRAS_API_KEY. Checks API key then routes to speed-run:turbo (direct codegen), speed-run:showdown (parallel competition), or speed-run:any-percent (parallel exploration). Use when the user says \"speed-run\", \"fast build\", \"turbo build\", \"use Cerebras\", or requests token-efficient code generation.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    STOP here: Do not fall back to Claude direct generation — the whole point of speed-run is hosted LLM.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Speed-Run

Token-efficient code generation pipeline. Uses hosted LLM (Cerebras) for fast, cheap first-pass generation. Claude handles architecture and surgical fixes.

Announce: "I'm using speed-run for token-efficient code generation."

Step 1: Check API Key (MANDATORY)

ALWAYS run this first:

mcp__speed-run__check_status

If status is error / key not set:

Speed-run requires a Cerebras API key for hosted code generation.

Setup (pick one):

Option A (recommended): Add to ~/.claude/settings.json:
  { "env": { "CEREBRAS_API_KEY": "your-key" } }

Option B: Add to ~/.zshrc:
  export CEREBRAS_API_KEY="your-key"

Get a free key at: https://cloud.cerebras.ai

Then restart Claude Code.

STOP here. Do not fall back to Claude direct generation — the whole point of speed-run is hosted LLM. If the user wants Claude direct, they should use test-kitchen instead.

Step 2: Route

If check_status returned OK, present options:

Speed-run ready! Cerebras API connected.

How would you like to proceed?

1. Turbo - Direct code generation (single task, fast)
   → Best for: one feature, algorithmic code, boilerplate
2. Showdown - Parallel competition (same design, multiple runners)
   → Best for: medium-high complexity, want best implementation
3. Any% - Parallel exploration (different approaches)
   → Best for: unsure of architecture, want to compare designs

Routing:

  • Option 1: Invoke speed-run:turbo
  • Option 2: Invoke speed-run:showdown
  • Option 3: Invoke speed-run:any-percent

Skill Dependencies

SubskillDescription
speed-run:turboDirect hosted codegen via contract prompts
speed-run:showdownParallel same-design competition via hosted LLM
speed-run:any-percentParallel approach exploration via hosted LLM

When to Use Speed-Run vs Test Kitchen

SituationUse
Want token savings on code generationSpeed-run
Generating algorithmic code (parsers, state machines)Speed-run:turbo
Want parallel competition with fast generationSpeed-run:showdown
Want to explore approaches with fast generationSpeed-run:any%
No API key / don't want external LLMTest Kitchen
CRUD / simple operationsTest Kitchen (Claude direct is cheaper)
Need 100% first-pass accuracyTest Kitchen

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.