agentleFS
tusharagg1tusharagg1/aifolimizer/.claude/skills/health-check/SKILL.md

health-check

Skill2 starsChanged 5 months agoMITView on GitHub

Self-diagnostic for the aifolimizer harness wiring. Use when something is silently broken or before relying on the system - "is everything working?", "health check", "why is the MCP not responding?", "check my setup", "diagnose aifolimizer". Audits MCP server, services, WS token freshness, hooks. Catches stale-token / unregistered-MCP / broken-hook silent failures.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use testing.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • NVIDIASkill

    testing

    Run Python and Rust tests for physicsnemo-curator using uv + pytest with coverage reporting via pytest-cov, and cargo-nextest for Rust tests. Includes benchmark workflows with pytest-benchmark and criterion.

    Also in 3 projects that use this

The file

Files
SKILL.md

Health Check (Harness Self-Diagnostic)

Goal

Catch the silent-failure class a solo operator hits with no second pair of eyes: stale WS token, MCP server that won't import, a service import break, missing hooks. Output is a PASS/WARN/FAIL report with the one thing to fix.

How to run

Step 1 - Run the deterministic diagnostic:

backend/.venv/Scripts/python.exe backend/scripts/health_check.py

Reports: python version, mcp_server import + tool count, core service imports, WS session token freshness (vs WS_TOKEN_TTL_HOURS), settings.json hook events.

Step 2 - Live data-source check (only if Step 1 PASS):

  • mcp__aifolimizer__get_data_source_reliability - per-source success rate + latency over the trailing window. Flags providers degrading (yfinance / FRED / CoinGecko / SEC).

Step 3 - Optional backend reachability:

  • curl -s http://127.0.0.1:8000/health if the FastAPI backend is expected up.

Interpreting results

  • ws_session WARN (stale) → re-auth: delete ~/.aifolimizer/ws_session.json and re-run WS login, or run mcp_login.
  • mcp_server_import FAIL → a recent edit broke import; run py_compile mcp_server.py and read the traceback.
  • core_services FAIL → a service has a syntax/dependency error; the detail names the module + exception.
  • settings_hooks missing event → a hook didn't register; check ~/.claude/settings.json.
  • data_source low success rate → provider outage or rate-limit; the cached layer will serve stale data until it recovers.

Output

Relay the script's OVERALL line + any non-PASS rows, then the single highest-priority fix. Don't paste the full report unless asked.

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.