Home / calle-ai / awesome-phone-call-agents · skills/call-rlhf-self-reflection-scorer/SKILL.md · GitHub

call-rlhf-self-reflection-scorer skillA

call-rlhf-self-reflection-scorer is agent-read markdown (skill) from calle-ai/awesome-phone-call-agents: Offline experimental post-call feedback scorer using supplied ratings and text heuristics. Use to demonstrate advisory review suggestions; no LLM inference, RLHF training, or memory integration is included..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# RLHF Self-Reflection Scorer

This skill demonstrates post-call QA with a small lexical scorer. It accepts a supplied transcript and optional rating, then returns predefined review suggestions. It does not collect user feedback, call an LLM, train a model, store RAG memories, or apply prompt changes. These are possible future host integrations, not delivered behavior.

## Scientific Foundation

| Paper / Concept | Relevance |
|---|---|
| **LLM-as-a-Judge** | Using a strong LLM to evaluate the outputs of an agentic LLM correlates highly with human CSAT (Customer Satisfaction). |
| **Self-Reflection (Reflexion)** | Agents that critique their own past transcripts and generate "verbal reinforcement" prompts perform significantly better on subsequent tasks. |
| **RLHF (Reinforcement Learning from Human Feedback)** | Incorporating explicit user scores (if provided post-call) alongside automated critiques bridges the gap between simulated and real-world quality. |

## How it works

1. The skill receives the transcript and any explicit CSAT score given by the user (if applicable).
2. If the user gave a high score (>= 4), the interaction is marked as successful.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add calle-ai/awesome-phone-call-agents/call-rlhf-self-reflection-scorer@v1.0.0
Exact content
mdr add calle-ai/awesome-phone-call-agents/call-rlhf-self-reflection-scorer@sha256:89445b7954b40488

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_c75wyh27a56dda5b.svg)](https://markdownregistry.com/a/art_c75wyh27a56dda5b)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v1.0.0 latest2026-09-18 d331b58 2,907 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2907 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

GitHub

calle-ai/awesome-phone-call-agents · 103 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_c75wyh27a56dda5b
GET https://markdownregistry.com/api/v1/resolve?ref=calle-ai/awesome-phone-call-agents/call-rlhf-self-reflection-scorer
GET https://markdownregistry.com/api/v1/blob/89445b7954b40488fe1b7adb37b5c053665ca9579cf7dffebcc7d40409839c2f

Your agent 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.

More from calle-ai/awesome-phone-call-agents

AGENTS.md agents
calle-ai/awesome-phone-call-agents · AGENTS.md
git:20260911.30d168b · audit A · 103 stars
AGENTS.md@apps/python/buddye agents
calle-ai/awesome-phone-call-agents · apps/python/buddye/AGENTS.md
git:20260917.2209027 · audit A · 103 stars
DESIGN.md@apps/python/buddye/docs design
calle-ai/awesome-phone-call-agents · apps/python/buddye/docs/DESIGN.md
git:20260917.2209027 · audit A · 103 stars
AGENTS.md@apps/python/callback-scam-screener agents
calle-ai/awesome-phone-call-agents · apps/python/callback-scam-screener/AGENTS.md
git:20260914.bd607da · audit A · 103 stars
DESIGN.md@apps/python/measureback design
calle-ai/awesome-phone-call-agents · apps/python/measureback/DESIGN.md · A kitchen instrument for reading recipe measurements and their source words.
git:20260914.3dfc38c · audit A · 103 stars
AGENTS.md@apps/python/quotewake agents
calle-ai/awesome-phone-call-agents · apps/python/quotewake/AGENTS.md
git:20260826.9ce0c85 · audit A · 103 stars
AGENTS.md@apps/typescript/arc-platform agents
calle-ai/awesome-phone-call-agents · apps/typescript/arc-platform/AGENTS.md
git:20260911.edc1937 · audit A · 103 stars
CLAUDE.md@apps/typescript/arc-platform claude
calle-ai/awesome-phone-call-agents · apps/typescript/arc-platform/CLAUDE.md
git:20260911.edc1937 · audit B · 103 stars
AGENTS.md@apps/typescript/fraud-ops-caller agents
calle-ai/awesome-phone-call-agents · apps/typescript/fraud-ops-caller/AGENTS.md
git:20260911.062b54b · audit A · 103 stars
CLAUDE.md@apps/typescript/fraud-ops-caller claude
calle-ai/awesome-phone-call-agents · apps/typescript/fraud-ops-caller/CLAUDE.md
git:20260911.062b54b · audit B · 103 stars
AGENTS.md@apps/typescript/tradecheck agents
calle-ai/awesome-phone-call-agents · apps/typescript/tradecheck/AGENTS.md
git:20260924.aec8672 · audit A · 103 stars
CLAUDE.md@apps/typescript/tradecheck claude
calle-ai/awesome-phone-call-agents · apps/typescript/tradecheck/CLAUDE.md
git:20260924.aec8672 · audit B · 103 stars

Every file in calle-ai/awesome-phone-call-agents

Browse by kind, by grade A, or by owner.