skill-feedback

Name: skill-feedback
Availability: InStock
Author: osouthgate

Log skill usage feedback to local JSONL files and generate reports.

4|Updated Apr 23, 2026

Search Tags:#feedback #logging #cli #privacy #local-storage #skill-feedback

Ready to run

npx skills add https://github.com/osouthgate/agent-plus --skill skill-feedback-osouthgate

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-feedback
Source: https://github.com/osouthgate/agent-plus/tree/main/skill-feedback/skills/skill-feedback
Command: npx skills add https://github.com/osouthgate/agent-plus --skill skill-feedback-osouthgate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Local-first self-assessment for Claude Code skills. After you use any skill (your own or someone else's), call skill-feedback log <skill> --rating N --outcome ... [--friction "..."] to append one entry to .agent-plus/skill-feedback/<skill>.jsonl. The skill author can then run skill-feedback report for an aggregate, or skill-feedback submit <skill> to bundle entries into a GitHub issue body for the skill's source repo. No telemetry leaves the machine unless the user explicitly runs submit.

Core Features & Use Cases

Append-only log of skill usage to a per-skill JSONL file stored locally.
Generate reports and aggregates for skill usage; submit to upstream repos when desired.
Privacy-first design: no network calls unless the user explicitly runs a submit flow.

Quick Start

After using a skill, run a log command to record your rating and outcome locally.

Frequently Asked Questions about skill-feedback

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I log local skill usage feedback without sending telemetry?▼

You can log local skill usage feedback without sending telemetry by running a CLI command to append an entry with your rating and outcome to a local per-skill JSONL file.

How does privacy-preserving usage logging work for local CLI tools?▼

Privacy-preserving usage logging works by storing feedback data strictly in local storage files, ensuring absolutely no network calls or telemetry leave your machine unless you explicitly run a submit command.

How do I generate an aggregate report from local skill feedback logs?▼

You generate an aggregate report from local skill feedback logs by executing a report command, which reads the append-only local JSONL files and aggregates the stored usage data.

Can I submit local usage logs to a GitHub issue from the command line?▼

Yes, you can submit local usage logs to a GitHub issue from the command line by running a submit command that bundles your locally stored feedback entries into a formatted issue body for the upstream repository.

Is local-first self-assessment suitable for measuring team skill effectiveness?▼

Yes, local-first self-assessment is suitable for measuring team skill effectiveness because developers can log outcomes and friction locally, then aggregate the data to review effectiveness without forced telemetry.

What are the limitations of local storage for skill feedback logging?▼

The main limitation of local storage for skill feedback logging is that data remains siloed on each individual machine until a user explicitly executes a submit command to bundle entries upstream.