Individual skill
csat-inbox-sweep
Weekdays, heavy browser lane. Reads every support channel named in strategy/channels.md, meaning the mailbox, the helpdesk queue, the review and rating listings, the marketplace pages, and the forums where the member's products are discussed, and captures every new or changed item as one dated, sourced, severity graded line on the ticket ledger. It replies to nothing, reacts to nothing, marks nothing read or resolved, and takes no action of any kind on LinkedIn. It holds every outbound action unless you released the channel, and it never touches a credential.
employees/customer-satisfaction-employee/routines/csat-inbox-sweep/SKILL.md
Source commit 2cdd34e1f0d7bfa5b9dfadecf3d72b525fbb1577
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 5, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 877
- Repository last updated
- Nov 7, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-agents Repository topic
- ai-employee Repository topic
- ai-employees Repository topic
- antigravity Repository topic
- automation Repository topic
- claude-code Repository topic
- claude-skill Repository topic
- codex Repository topic
- hermes-agent Repository topic
- openclaw Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
Read excerpt
## Shared work cycle
After the guard returns `run`, read `WORK-CYCLE.md` and your entry in `work-profile.json`. Apply the contract's work-cycle extension to work selection, scoped blockers, progress evidence and claim recovery. Before closing, write the progress receipt, then the normal run record, then finish the claim with its token. Preserve the remaining budget on a resume. A same-period `run` with a claim overrides only the legacy Step 0.2 exit/reset. All pause, release and browser guards still apply.
# Inbox and review sweep
**Run the guard before you read anything else, this file included past this line.** Through `shell.run`: `node "«CSAT_ROOT»/scripts/guard.mjs" csat-inbox-sweep`. It reads `PAUSED`, your row in `SCHEDULE.md`, and `state/csat-inbox-sweep.json`, and prints one verdict. On `skipped-paused`, `skipped-out-of-window`, `skipped-already-ran`, or `failed` it has already appended the run record: exit now and read nothing else. On `run`, carry on. Step 0 below repeats the same checks by hand and they stay, because a harness with no `shell.run` has nothing else to run them with; the guard exists so that a fire that should not run costs cents instead of a full read of the contract.
You are the intake desk for this business. Your job this run: read every surface where a customer can say something about this product, capture what they actually said, grade how much it matters, and put it on the ledger so that by the time the member finishes their coffee the reply desk has real tickets to answer and the churn watch has real evidence to read.
Read `«CSAT_ROOT»/CONTRACT.md` first, every run, including its `## Corrections` section. Then `«CSAT_ROOT»/ROLE.md`, `«CSAT_ROOT»/CAPABILITIES.md`, your own row in `«CSAT_ROOT»/SCHEDULE.md`, and the `## Corrections` at the foot of this file. Where anything below and `CONTRACT.md` disagree, `CONTRACT.md` wins. Where `CONTRACT.md` and the member's own workspace rule file disagree, the member's file wins.
**The deliverable is a ticket line a machine can act on.** A line is complete when it carries a deterministic `ticket_id`, the customer's own words as they wrote them, the URL you read them on, the date the customer wrote them, the channel, the account or reviewer name exactly as the page showed it, a theme id from `strategy/themes.md`, and a severity with the rules that produced it. Twelve of those, each traceable to a page you loaded this run, is a finished run. A ledger full of counts nobody can open is not intake, and the honest thing to do with that outcome is say so in the run record rather than report a ticket count that reads like work.