Skip to content
Agentmart
Submit a tool

prompt-briefing

Use when turning a short user request into a complete prompt, preparing a Codex/Claude/subagent handoff, rewriting an ambiguous task brief, or asking the user…

Skill by fabiocantone

IndexedMIT
Write a review

Chalk Labs

Need help deploying prompt-briefing?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/fabiocantone-prompt-briefing

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

Use when turning a short user request into a complete prompt, preparing a Codex/Claude/subagent handoff, rewriting an ambiguous task brief, or asking the user to approve or edit the execution prompt before work starts

Use cases: writing, productivity, agent-building

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/prompt-briefing

What's inside

Skill name
prompt-briefing
Description
Use when turning a short user request into a complete prompt, preparing a Codex/Claude/subagent handoff, rewriting an ambiguous task brief, or asking the user to approve or edit the execution prompt before work starts
License
MIT
Instructions
101 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Prompt Briefing

## Overview

Users should be able to write short, natural requests. The agent should expand them into an execution-ready prompt when the task is broad, risky, multi-step, delegated to another agent, or likely to suffer from missing context.

This skill is a prompt compiler: preserve the user's intent, add the methodology gates, expose assumptions, and ask for approval when the rewritten prompt will steer significant work.

## Auto Activation

Use this skill automatically when the user asks to write, improve, rewrite, generate, prepare, translate into a better prompt, or hand off a prompt for Codex, Claude, another model, a subagent, a reviewer, or a benchmark. The user should not need to say "Use CoderSteroids" for prompt rewriting.

When generating a prompt for another agent, include "Use CoderSteroids" only if the target environment has CoderSteroids available. Otherwise include the portable CoderSteroids operating rules directly.

If Superpowers or another methodology plugin is also installed, prompt rewriting remains a CoderSteroids-primary workflow unless the user explicitly asks for that other methodology. Do not lead with Superpowers for prompt rewriting just because its bootstrap skill exists.

## Language

Write the explanation, assumptions, and approval request in the user's language. Keep the draft prompt in the user's language unless the target agent, repository, or user explicitly requires another language.

## When To Use

Use this skill when:

- The user asks for a prompt, handoff, Claude/Codex instruction, or subagent task.
- The user asks to rewrite, improve, strengthen, structure, or generate a prompt.
- The user gives a short brief for a non-trivial task.
- The task needs project memory, docs lookup, benchmarks, logging, or verification discipline.
- The next step may be run in a different chat, model, tool, or agent.

Do not force this gate for tiny direct edits or commands where the user's intent is already precise.

## Required Output

For prompt rewriting, produce:

```markdown
## Draft Prompt

...

## Assumptions

- ...

## Missing Context

- ...

## Approval Needed

Reply with `approve`, edits, or constraints to change before execution.
```

If there is no meaningful missing context, say `None critical`.

## Prompt Requirements

The draft prompt should include, when relevant:

- Target agent or tool: Codex, Claude, subagent, reviewer, benchmark runner.
- Instruction to load project memory instead of relying on chat history.
- Scope and non-scope.
- Files, folders, docs, or artifacts to inspect.
- Required research sources, including Context7, official docs, web, or GitHub checks.
- Observability/logging requirements for runtime problems.
- Planning, verification, and memory-update requirements.
- Explicit stop conditions for missing data, risky assumptions, or unavailable tools.
- Expected output format.

## Approval Rules

Ask for approval before execution when:

- The rewritten prompt changes the user's scope materially.
- The task is expensive, destructive, production-facing, security-sensitive, or architecture-level.
- The prompt will be sent to a separate agent or external tool.
- Missing context could change the recommended plan.

If the user already says to proceed autonomously, create the prompt internally and execute, but still preserve the prompt or summary in the plan or handoff when useful.

## Quality Bar

Good prompt briefs:

- Keep the user's language and intent.
- Add only constraints that improve outcome quality.
- Mark assumptions instead of hiding them.
- Keep prompts executable, not essay-like.
- Avoid over-constraining creative or exploratory tasks.
- Prevent lazy work by requiring sources, logs, tests, and memory updates where they matter.

## Common Mistakes

- Rewriting every small request into a long ritual.
- Executing a broad ambiguous task without showing the prompt first.
- Adding invented context or fake file names.
- Omitting verification and durable memory for long-running work.
- Asking for approval without giving a concrete draft to approve.

From fabiocantone/codersteroids, MIT.

More from fabiocantone/codersteroids

Signals

Stars
0
Forks
0
Open issues
1
Last commit (this folder)
May 27, 2026 (5 months ago)
Last release
May 27, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from fabiocantone

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get prompt-briefing running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying prompt-briefing?

CallGet help
Cite this page

prompt-briefing skill. Agent Mart. https://agentmart.dev/skills/fabiocantone-prompt-briefing (last updated 2026-10-24)