Skip to content
Agentmart
Submit a tool

shared-learning

Opt-in anonymous aggregate false-positive / true-positive count emission for community calibration.

Skill by drumfiend21

IndexedApache-2.0
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/drumfiend21-shared-learning

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Opt-in anonymous aggregate false-positive / true-positive count emission for community calibration.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Shell scripts

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/shared-learning

What's inside

Skill name
shared-learning
Description
Opt-in anonymous aggregate false-positive / true-positive count emission for community calibration.
License
Apache-2.0
Instructions
22 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (3)

  • SKILL.md
  • emit.sh
  • show-defaults.sh

SKILL.md (first lines)

# Anonymous Shared-Learning Skill

Aggregate FP / TP counts only. Operator-hashed identifier (sha256 of user
string), no IP collection, no per-rule detail. Disabled by default. The
operator must explicitly pass `--opt-in` (typically wired through a profile
`shared_learning.enabled=true` setting and a one-time consent dialog).

## Privacy posture

- `aggregate-only`: only summed FP/TP counts are emitted; per-rule keys are
  stripped before egress.
- `no_ip_collection=true`: the egress path does not record client IP,
  X-Forwarded-For, or any other network identifier.
- `hashed_id`: a stable but un-reversible sha256 of the operator's local
  user string is used to de-duplicate emissions without identifying them.

## Triggers

`opt-in` only — never fires automatically. The skill exits with
`opt_in_required` if invoked without `--opt-in`.

From drumfiend21/claude-tdd-pro, Apache-2.0.

More from drumfiend21/claude-tdd-pro

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
May 20, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
Repository
github.com/drumfiend21/claude-tdd-pro
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from drumfiend21

Cite this page

shared-learning skill. Agent Mart. https://agentmart.dev/skills/drumfiend21-shared-learning (last updated 2026-10-24)