evaluate-system
Skill0 starsChanged 4 months agoMITView on GitHub
Run the reproducible evaluation suite and explain functional contract results separately from retrieval quality.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- run-demoSkill
- setup-environmentSkill
- update-salon-knowledgeSkill
- verify-projectSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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
- Distinctive: line 11
Start MCP-disabled app on port 8002:
- Distinctive: line 16
Start LLM-disabled app on port 8003 using placeholder model variables.
- Distinctive: line 35
Do not present pytest mock results as real integration results.
- Very specific: line 36
Keep Hermetic CI (EXTERNAL_CALL_POLICY=deny) separate from any explicitly allowed real Provider evaluation.
- Distinctive: line 37
Do not commit raw local reports.
- Distinctive: line 38
Do not print Provider credentials, authentication tokens, cookies or local runtime data.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Evaluate System
Pipeline
- Prepare the normal app on port 8000. When MCP is enabled, configure its interpreter, module, working directory and Collection; FastAPI lifespan starts the stdio child process.
- Start MCP-disabled app on port 8002:
RAG_MCP_ENABLED=false DATABASE_URL=sqlite:////tmp/salon_eval_8002.db \ python -m uvicorn app:app --host 127.0.0.1 --port 8002 --no-proxy-headers - Start LLM-disabled app on port 8003 using placeholder model variables.
- Run:
NO_PROXY=127.0.0.1,localhost python eval/run_evaluation.py \ --base-url http://127.0.0.1:8000 \ --mcp-unavailable-base-url http://127.0.0.1:8002 \ --llm-unconfigured-base-url http://127.0.0.1:8003 \ --timeout 120
Output
- Local summary report.
- Local per-case report.
- Functional contract counts.
- Retrieval quality metrics.
Rules
- Do not present pytest mock results as real integration results.
- Keep Hermetic CI (
EXTERNAL_CALL_POLICY=deny) separate from any explicitly allowed real Provider evaluation. - Do not commit raw local reports.
- Do not print Provider credentials, authentication tokens, cookies or local runtime data.
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.

