mcpField
F
feedback

feedback

github.com/yonatangrossAgent workflows299180 installsUpdated today
Repository

About feedback

A Claude skill for inspecting and controlling OrchestKit’s usage-based feedback and learning system. It covers learning controls, privacy choices, data exports, and bug reports.

Key features

  1. 01View system status and learned patterns
  2. 02Pause or resume learning
  3. 03Reset learned patterns
  4. 04Export feedback and analytics data
  5. 05Manage consent and privacy settings
  6. 06File GitHub bug reports

Use cases

  1. 01Check learned patterns and agent performance
  2. 02Pause learning without deleting data
  3. 03Review exported analytics before sharing
  4. 04Report a bug with collected context

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/yonatangross/orchestkit --skill feedback

After installing, type/feedbackin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

test-cases.json
references/
bug-report-reference.md
file-locations.md
privacy-policy.md
subcommand-reference.md
rules/
_sections.md
consent-and-security.md

Details

From the project README

Feedback - Manage Learning System

View and manage the OrchestKit feedback system that learns from your usage.

Overview

  • Checking feedback system status
  • Pausing/resuming learning
  • Resetting learned patterns
  • Exporting feedback data
  • Managing privacy settings
  • Enabling/disabling anonymous analytics sharing
  • Viewing privacy policy
  • Filing bug reports as GitHub issues

Usage

/ork:feedback                    # Same as status
/ork:feedback status             # Show current state
/ork:feedback pause              # Pause learning
/ork:feedback resume             # Resume learning
/ork:feedback reset              # Clear learned patterns
/ork:feedback export             # Export feedback data
/ork:feedback settings           # Show/edit settings
/ork:feedback opt-in             # Enable anonymous sharing
/ork:feedback opt-out            # Disable anonymous sharing
/ork:feedback privacy            # View privacy policy
/ork:feedback export-analytics   # Export anonymous analytics for review
/ork:feedback bug                # File a bug report as a GitHub issue
/ork:feedback bug [description]  # File with pre-filled description

Subcommands

SubcommandDescription
status (default)Show current feedback system state, learned patterns, agent performance
pauseTemporarily pause learning without clearing data
resumeResume paused learning
resetClear all learned patterns (requires "RESET" confirmation)
exportExport all feedback data to .claude/feedback/export-{date}.json
settingsShow/edit settings (usage: /ork:feedback settings <key> <value>)
opt-inEnable anonymous analytics sharing (GDPR-compliant consent)
opt-outDisable anonymous analytics sharing (revokes consent)
privacyDisplay the full privacy policy
export-analyticsExport anonymous analytics to file for review before sharing
bugFile a bug report as a GitHub issue with auto-collected context

Output: Each subcommand displays formatted status, confirmation prompts, or exported file paths. Load Read("${CLAUDE_SKILL_DIR}/references/subcommand-reference.md") for detailed actions and expected output for each subcommand. Load Read("${CLAUDE_SKILL_DIR}/references/bug-report-reference.md") for the bug filing workflow.

Consent and Security

Load Read("${CLAUDE_SKILL_DIR}/rules/consent-and-security.md") for GDPR consent management, security restrictions, and analytics data sharing policies.

Related Skills

  • ork:skill-evolution: Evolve skills based on feedback

File Locations

Load Read("${CLAUDE_SKILL_DIR}/references/file-locations.md") for storage details.

Load Read("${CLAUDE_SKILL_DIR}/references/privacy-policy.md") for full privacy documentation.

Comments

Markdown supported