design-scoreboard

Designs what an improvement or optimizer loop should climb for a given project and goal, and what must not get worse while it does: goal metrics measured on…

Skill by fblissjr

IndexedApache-2.0★ 2

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/fblissjr-design-scoreboard

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.

About

Designs what an improvement or optimizer loop should climb for a given project and goal, and what must not get worse while it does: goal metrics measured on the real path, guardrails, and counter-checks aimed at the cheapest way to fake each gain, so no single number can be reward-hacked. Proves each proxy tracks the outcome it stands for, measures its noise, writes the scenarios as data in the loop state, and proposes the fill for AGENTS.md's Measurement section. Rerun in review mode when the goal changes. User-invoked only.

Use cases: design, data

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

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/design-scoreboard

What's inside

Skill name: design-scoreboard
Description: Designs what an improvement or optimizer loop should climb for a given project and goal, and what must not get worse while it does: goal metrics measured on the real path, guardrails, and counter-checks aimed at the cheapest way to fake each gain, so no single number can be reward-hacked. Proves each proxy tracks the outcome it stands for, measures its noise, writes the scenarios as data in the loop state, and proposes the fill for AGENTS.md's Measurement section. Rerun in review mode when the goal changes. User-invoked only.
License: Apache-2.0
Instructions: 29 lines in SKILL.md · view on GitHub

Files (2)

SKILL.md
scoreboard-loop.md · references/

SKILL.md (first lines)

# Design a scoreboard

<run>
This skill is a standing prompt. The procedure is in
`${CLAUDE_SKILL_DIR}/references/scoreboard-loop.md`. Read it now and execute
it as written.
</run>

<parameters>
Start from its `<parameters>` block and apply these overrides from the
invocation: $ARGUMENTS

An override that names no parameter goes under "Needs from me" rather than
being guessed into one.
</parameters>

<prerequisites>
The procedure reads the repo's AGENTS.md (North star, Where things live,
Commands, Measurement). If those sections are missing, the template is
`${CLAUDE_PLUGIN_ROOT}/templates/AGENTS.md`. Propose the missing parts under
"Needs from me" and work from the nearest thing the repo has.
</prerequisites>

<after_compaction>
Re-read the procedure file and the scenarios written so far before the next
action.
</after_compaction>

From fblissjr/fb-claude-skills, Apache-2.0.

Signals

Stars: 2
Forks: 1
Open issues: 0
Last commit (this folder): Sep 24, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License: Apache-2.0
Repository: github.com/fblissjr/fb-claude-skills
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from fblissjr

Cite this page

design-scoreboard skill. Agent Mart. https://agentmart.dev/skills/fblissjr-design-scoreboard (last updated 2026-10-24)