support-l1
Skill0 starsChanged 2 months agoMITView on GitHub
Triage a customer question with wiki/SOP answers and draft a reply. Use for L1 tickets. Draft only — never send without approval; never invent policy.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- eng-prSkill
- market-researchSkill
- sales-outboundSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
Search wiki/ and sops/support-*.md.
- Very specific: line 26
If known answer: draft reply into artifacts/ with send_status: awaiting_approval.
- Distinctive: line 27
If bug: write repro (env, steps, expected, actual) for eng.
- Distinctive: line 28
If billing/legal: escalate to human.
≈ “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
When to use
- Incoming support ticket / email / chat
- Need a grounded draft reply or escalation packet
Models
- Actor:
worker(Flash-Lite or Groq Qwen for speed) - Verifier:
planner(Flash + SOP checker) - Resolve:
./scripts/resolve-model.sh support-l1
Steps
- Classify: question / bug / billing / abuse.
- Search
wiki/andsops/support-*.md. - If known answer: draft reply into
artifacts/withsend_status: awaiting_approval. - If bug: write repro (env, steps, expected, actual) for eng.
- If billing/legal: escalate to human; do not invent refunds.
- Verifier checks SOP citation and no invented policy.
Tools allowed
- Wiki / SOP read
- Draft write under
artifacts/ - No send
Definition of done
- Classification + draft or escalation packet
- Policy claims cite an SOP path
- Verifier pass
Never do
- Invent refunds or legal commitments
- Paste secrets or raw PII into wiki
Escalation
- Angry enterprise / legal threat → human immediately
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.

