feedback-pipeline SKILL.md skillA
feedback-pipeline from tekkiiiii/the-agency is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add tekkiiiii/the-agency/feedback-pipeline@git:20260722.dd9d64fPins git:20260722.dd9d64f in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- tekkiiiii/the-agency
- Path
skills/feedback-pipeline/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260722.dd9d64f, committed Jul 22, 2026
- First version recorded
- May 18, 2026
- Size
- 6,227 bytes
- Repository stars
- 6
- License
- none declared
Autonomous customer feedback intake pipeline: reads new submissions from a Google Sheet, routes each to the correct project owner via a routing table, sends a Slack/chat handoff, tracks response status, monitors SLA, escalates breaches, and emails the customer when resolved. Runs on a 4-hour cron cycle with a 2-hour escalation check. Use when feedback submissions need to reach the right person without manual triage, when SLA compliance is important, or when customer response loops are slow.…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Feedback Pipeline — Skill
## What this does
Autonomous customer feedback intake pipeline:
```
Customer fills Google Form → Sheet row (G=pending)
│
│ [Every 4h via cron, or anytime via /feedback-pipeline]
│
├─ 1. Read new "pending" rows from Feedback sheet
├─ 2. Route project name → PD slug (routing.json)
├─ 3. Assign row (G=assigned, H={slug}-pd)
├─ 4. SendMessage to PD + write NEXUS handoff
│
│ PD handles work normally
│
│ PD signals completion — DUAL MECHANISM:
│ ├─ SendMessage: "DONE feedback:{row}:{name} Response: {x}"
│ └─ Sheet col K: set to "DONE"
│
├─ 5. Detect DONE → sheet G=resolved, close row
├─ 6. gws gmail send to customer
├─ 7. Escalation check every 2h (SLA breach → G=escalated)
└─ 8. State written to state.json
Cron: 0 */4 * * * (main loop)
Cron: 0 */2 * * * (escalation only)
```
---
## Files
```
~/.claude/skills/feedback-pipeline/
├── SKILL.md ← this file
├── routing.json ← project → PD slug mapping
├── feedback-sheet.ts ← Google Sheets read/write (11-col schema)
├── feedback-pipeline.ts ← main orchestrator
└── scripts/
…Read the whole file at its exact version.
How to install
mdr add tekkiiiii/the-agency/feedback-pipeline@sha256:1a5fd90a7a856041The line at the top of this page pins the label git:20260722.dd9d64f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_k44vl7o7ylof2woa)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between May 18, 2026 and Jul 22, 2026, about one every 65 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260722.dd9d64f latest | 2026-07-22 | dd9d64f | 6,227 B | A | view · diff |
| git:20260518.19f48dd | 2026-05-18 | 19f48dd | 6,226 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6227 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
tekkiiiii/the-agency · 6 stars · license none declared · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_k44vl7o7ylof2woa GET https://markdownregistry.com/api/v1/resolve?ref=tekkiiiii/the-agency/feedback-pipeline GET https://markdownregistry.com/api/v1/blob/1a5fd90a7a8560410a25f262ea61a6d65cd81423433b29aa5927a2fbfd95f8df
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.