live-check
Skill1 starsChanged 20 days agoMITView on GitHub
Run the MCP server locally against the real coursesu.com site and call its tools read-only, to verify a change end to end. Use when asked to test, verify or try a tool "for real", "en vrai", or against the live site.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- NahumLitvin/prismantistheir own version, first seen Nov 13, 2026
- nadavnaveh/skillstheir own version, first seen Nov 1, 2026
- markneonin/panelinetheir own version, first seen Nov 1, 2026
- iamrohithrnair/mermantheir own version, first seen Nov 1, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- NahumLitvin/prismantis★ 426same name
- iamrohithrnair/merman★ 42same name
- markneonin/paneline★ 10same name
- nadavnaveh/skills★ 3same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 12
Read-only. Never call a write tool (cart, list, slot, order) without the maintainer's explicit approval for that call.
- Distinctive: line 14
Never click or solve a Cloudflare challenge.
- Very specific: line 16
Keep the default pacing (DELAY_MS), or at least 1500-3000.
- Very specific: line 30
Run it in the background and keep its PID.
- Very specific: line 33
If the log says human action required with needs_login, ask the maintainer to sign in in the Chromium window that opened (on macOS there is …
- Distinctive: line 37
Call tools with the bundled client:
- Very specific: line 46
Check the answers against what the tool promises (fields present, no nulls where data is expected), and the log for task failed lines.
- Very specific: line 49
Stop the server with kill -TERM <pid> on the Node PID itself (not pkill -f, which also hits the wrapping shell).
≈ “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
Live check
Verifies the server against the real site, read-only, on the developer's machine.
Rules
- Read-only. Never call a write tool (cart, list, slot, order) without the maintainer's explicit approval for that call.
- Never click or solve a Cloudflare challenge. On a challenge, a login wall or an HTTP 403/429, stop and report.
- Keep the default pacing (
DELAY_MS), or at least1500-3000. A live check is a handful of calls, not a loop. - Tool output contains personal data (orders, receipts, lists): read it, summarise it, never write
it into the repository. Scratch files go to a scratch directory or
.local/.
Steps
Build-free start, with a throwaway token and the local data directory (git-ignored):
MCP_TOKEN=local-check-0123456789abcdef HOST=127.0.0.1 PORT=8765 DELAY_MS=1500-3000 \ node src/server.ts > "$SCRATCH/server.log" 2>&1 &Run it in the background and keep its PID. Wait for the
startup probeortaskline with"label":"probe"in the log.- If the log says
human action requiredwithneeds_login, ask the maintainer to sign in in the Chromium window that opened (on macOS there is no noVNC). The server logssession restoredon its own once signed in; do not poll the site yourself. Call tools with the bundled client:
export MCP_URL=http://127.0.0.1:8765/mcp MCP_TOKEN=local-check-0123456789abcdef node scripts/call.ts # list tools node scripts/call.ts session_status node scripts/call.ts search_products '{"query":"lessive liquide"}'- Check the answers against what the tool promises (fields present, no nulls where data is
expected), and the log for
task failedlines. - Stop the server with
kill -TERM <pid>on the Node PID itself (notpkill -f, which also hits the wrapping shell). Expect exit code 0 and a freshdata/session.json.
After the check
data/holds a live session of the maintainer's account: mention it, and offer to delete it when the session is no longer needed.- Report what was verified live and what was not.
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.

