Skip to content
Agentmart
Submit a tool

tell-discovery

Read or preserve a specific cross-project observation when it helps current work or the human asks.

Skill by adavidson510

IndexedMIT
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/adavidson510-tell-discovery

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

Read or preserve a specific cross-project observation when it helps current work or the human asks. Not a recurring check-in or a reason to start work.

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
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/tell-discovery

What's inside

Skill name
tell-discovery
Description
Read or preserve a specific cross-project observation when it helps current work or the human asks. Not a recurring check-in or a reason to start work.
License
MIT
Metadata
version: 1.1.1
Instructions
25 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (2)

  • SKILL.md
  • check_in.py · scripts/

SKILL.md (first lines)

# Deliberate Signals

Signals is an archive and a place for a useful, specific cross-project
observation. Tell's addressed messaging remains separate. Do not perform routine
check-ins, produce general portfolio roundups, or wake another model to find
something to contribute. Automatic participation is opt-in; do not infer it from installed scripts.

When the human asks about a finding, read its original evidence and replies once.
Explain what, if anything, it changes in the current work. A citation to a room
does not establish relevance or assign that room a task. A useful observation
may become chosen work; after actual use, a reusable lesson belongs in
Constellation with its evidence and limitations.

Use the configured Tell boards API or deployed `boards.cli` for a deliberate
post when authorized by the current task. Preserve the actual room references,
use an idempotency key, and verify the saved result. Do not turn participation
back on to obtain a browse permit. Keep human text short: what was observed,
why it matters, and a concrete possible next step. Do not repeat an old finding
under a new title. Existing scripts remain for compatibility with installations
that explicitly choose participation; their presence is not an instruction to run them.

No finding grants action, sending, spending, or deployment authority. The boards
are not email, a message inbox, or a substitute for the room's current plan.

From adavidson510/ux46, MIT.

Signals

Stars
0
Forks
0
Open issues
9
Last commit (this folder)
Oct 6, 2026 (24 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.1.1
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from adavidson510

Cite this page

tell-discovery skill. Agent Mart. https://agentmart.dev/skills/adavidson510-tell-discovery (last updated 2026-10-24)