Skill Feedback (Grade A) logo

Skill Feedback (Grade A)Security-tested data-ai skill for Claude AI. Grade A. Local-first self-assessment for Claude Code skills. After you use any skill (your own or someone else's), call `skill-feedback log <skill> --ratin

— (0)
Daniel NikulshynReviewed by Daniel Nikulshyn·Updated July 2026

Overview

Local-first self-assessment for Claude Code skills. This tool allows users to provide feedback on the skills they use, which can then be aggregated and reported on by the skill authors. The feedback is stored locally in a JSONL file and can be submitted to a GitHub issue body for the skill's source repository. The tool is designed to be used immediately after using another skill, and can also be triggered by explicit user requests. The feedback includes a rating, outcome, and optional friction and note fields. The tool does not send any telemetry data unless the user explicitly chooses to submit it.

Key features

  • Local-first self-assessment
  • Rating system (1-5)
  • Outcome tracking (success, partial, failure)
  • Optional friction and note fields
  • Aggregated reporting
  • GitHub issue body submission

Pricing

Model
Free
Category
Skills
Rating
No reviews yet

Use cases

Providing Feedback

Users provide feedback on skills they use, which is stored locally and can be reported on by skill authors.

Aggregating Feedback

Skill authors can aggregate feedback and report on it to improve skill effectiveness.

Pros & Cons

Pros

  • Provides valuable feedback to skill authors
  • Helps improve skill effectiveness
  • Local-first, no telemetry data sent by default

Cons

  • Requires manual effort to provide feedback
  • Limited functionality without explicit user requests

Reviews

Sign in to leave a review.

No reviews yet. Be the first!

Q&A

Can I avoid sending any telemetry when using Skill Feedback?

By default, the tool is local‑first and does not send telemetry. Telemetry is only sent if you explicitly run the `submit` command to create a GitHub issue.

Asked by Eva Horáková · Sep 14, 2025

Is Skill Feedback easy to use for new Claude skill developers?

Yes, the tool auto‑triggers after any skill use and can also be invoked manually. It requires only a simple command to log rating, outcome, and optional notes, making it straightforward for developers and users alike.

Asked by Nikolai Petrenko · Aug 4, 2025

How do I submit collected feedback to a skill’s GitHub repository?

Run `skill feedback submit <skill>` which bundles all log entries for that skill into a GitHub issue body. This only sends data if you choose to run the command.

Asked by Tomáš Novák · Jul 20, 2025

Where does Skill Feedback store the feedback data?

Feedback is stored locally in a JSONL file at ~/.agent\ plus/skill feedback/<skill>.jsonl. No data leaves the machine unless you explicitly submit it.

Asked by Noor Siddiqui · Jul 3, 2025

Ask a question

Skills alternatives

Manage Headers (Grade A) logo
Manage Headers (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. Inspects and configures the security headers a Power Pages site sends to browsers — Content Security Policy, frame and clickjacking protection

— (0)
Free
Using Git Worktrees (Grade A) logo
Using Git Worktrees (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktre

— (0)
Free
Ga4 Bigquery Schema (Grade A) logo
Ga4 Bigquery Schema (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. GA4 BigQuery Export Schema Reference — complete field reference, nested structures, query patterns, and performance tips

— (0)
Free
Meta Capi (Grade A) logo
Meta Capi (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Meta Conversions API (CAPI) Setup Reference — architecture, event types, customer information hashing, deduplication, implementation examples, AEM

— (0)
Free
Callees (Grade A) logo
Callees (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. Lista o que uma funcao/metodo chama (call graph direto)

— (0)
Free
Test Module Name (Grade A) logo
Test Module Name (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Name Haskell test modules after the module under test with a Spec suffix in the same namespace. Use when writing or reviewing Haskell test module

— (0)
Free
Board Of Directors (Grade A) logo
Board Of Directors (Grade A)Skills

Security-tested data-ai skill for Claude AI. Grade A. Simulate a 5-member expert board deliberation for major decisions. Use when evaluating plans, architecture choices, feature designs, or any decisi

— (0)
Free
Advpl Mvc Avancado (Grade A) logo
Advpl Mvc Avancado (Grade A)Skills

Security-tested development skill for Claude AI. Grade A. MVC avançado via PE (Pontos de Entrada) — adicionar grids customizadas em telas MVC padrão (CNTA300/MATA070/MATA440/MATA460/FINA040 via *STRU)

— (0)
Free