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
In this repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- any-percentSkill
- judgeSkill
- showdownSkill
- turboSkill
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
- Very specific: line 38
STOP here: Do not fall back to Claude direct generation — the whole point of speed-run is hosted LLM.
≈ “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.
Files
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_statusIf 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 designsRouting:
- Option 1: Invoke
speed-run:turbo - Option 2: Invoke
speed-run:showdown - Option 3: Invoke
speed-run:any-percent
Skill Dependencies
| Subskill | Description |
speed-run:turbo | Direct hosted codegen via contract prompts |
speed-run:showdown | Parallel same-design competition via hosted LLM |
speed-run:any-percent | Parallel approach exploration via hosted LLM |
When to Use Speed-Run vs Test Kitchen
| Situation | Use |
| Want token savings on code generation | Speed-run |
| Generating algorithmic code (parsers, state machines) | Speed-run:turbo |
| Want parallel competition with fast generation | Speed-run:showdown |
| Want to explore approaches with fast generation | Speed-run:any% |
| No API key / don't want external LLM | Test Kitchen |
| CRUD / simple operations | Test Kitchen (Claude direct is cheaper) |
| Need 100% first-pass accuracy | Test Kitchen |
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.

