What makes Brief Master notable?

982 downloads. Trust evidence available

How should Brief Master be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Brief Master

Write precise execution briefs for agents, cron jobs, reviewers, researchers, and delegated coding tasks.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

982

Updated

Oct 11, 2026

Version

0.2.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 982 downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 982 downloadsadoption · observed Oct 11, 2026
Latest release: 0.2.1release · observed May 24, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 0.2.1release
Document that Brief Master drafts briefs only, requires review before autonomous execution, and must not invent credentials, approvals, hosts, cron schedules, or elevated access.
Observed May 24, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s1754kcncc002avbhpwjnqgcr98728et:brief-master

Install using `clawhub skill install s1754kcncc002avbhpwjnqgcr98728et:brief-master` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/leostehlik/brief-master before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-leostehlik-brief-master/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

47,633 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: brief-master
description: "Write precise execution briefs for agents, cron jobs, reviewers, researchers, and delegated coding tasks."
metadata:
version: "0.2.1"
---
# Brief Master

Write agent briefs that agents actually execute correctly.

Every wasted token is a wasted API call. Every vague word is a future bug. Every missing acceptance criterion is a future rework cycle.

Read `references/9-dimensions.md` before extracting intent.
Read `references/brief-formats.md` for the right format per agent type.

## Safety Boundary

This skill writes briefs only. A generated brief can instruct another agent to edit code, run commands, schedule jobs, or use external services, so the user or orchestrator must review the final brief before execution.

Do not invent credentials, secret names, hostnames, destructive commands, cron schedules, repository permissions, or approval status. If a brief would require elevated access, remote execution, persistent automation, or public posting, mark that as requiring explicit approval in the brief.

## The Pipeline

1. **Detect the target** — which agent, what runtime (subagent, cron, sessions_spawn)?
2. **Extract 9 dimensions** — see `references/9-dimensions.md`
3. **Ask max 3 questions** — only if critical info is missing. Never more.
4. **Apply the right format** — see `references/brief-formats.md`
5. **Run token efficiency audit** — strip every word that doesn't change the output
6. **Deliver** — one clean brief, ready to use

## Token Efficiency Rule

"The best brief is not the longest. It's the one where every word is load-bearing."

Before delivering, ask: does removing this sentence change what the agent does? If not, cut it.

## What Makes a Bad Brief

- Vague task description ("improve the translation")
- No acceptance criteria (how does the agent know it's done?)
- Missing constraints (what must not break?)
- No non-goals (what's explicitly out of scope?)
- Too long (agent loses focus, context drifts)
- Tool-specific instructions missing (which host? which directory? which branch?)

## What Makes a Good Brief

- One clear task per brief
- Explicit ACs labelled AC1, AC2, AC3 (testable, not descriptions)
- Constraints listed
- Non-goals listed
- Correct status update blocks (start + end)
- 95% confidence gate instruction included
- Right tool commands with correct paths

## Mandatory Sections for Dev Agent Briefs

Every brief for a dev/build agent must include:

```
FIRST — update status to working with task description
...task...
LAST — update status to done + notify orchestrator
```

And the 95% confidence gate:
```
Before starting ANY work, ask clarifying questions until you are 95% confident
you can complete this task successfully. Do not start until you have that confidence.
```

See `references/brief-formats.md` for full templates.

examples/README.md

# Brief Master Examples

Start with [`messy-to-clean-brief.md`](messy-to-clean-brief.md).

It shows the core move of Brief Master: take a fuzzy request, preserve the intent, and turn it into an agent brief with scope, constraints, acceptance criteria, non-goals, and verification commands.

Use it when you want to see what changes between "please improve this" and a brief an implementation agent can actually execute.

README.md

# brief-master

![Validate](https://github.com/LeoStehlik/brief-master/actions/workflows/validate.yml/badge.svg)

Write sharp, precise agent briefs for OpenClaw. Zero wasted tokens. Zero vague instructions.

Brief Master is an agent brief writer for AI coding workflows. It extracts 9 dimensions of intent, asks max 3 clarifying questions, applies the right format for your target agent, runs a token efficiency audit, and delivers one clean brief ready to fire.

Built for OpenClaw's multi-agent workflow: dev agents, code reviewers, testers, researchers, and cron jobs.

Inspired by [prompt-master](https://github.com/nidhinjs/prompt-master). Built as our own OpenClaw-native implementation.

## Safety Boundary

Brief Master only drafts execution briefs. Review the generated brief before handing it to an autonomous agent, especially commands, file paths, credentials, scheduled jobs, external services, and anything that changes code or system state.

The skill must not invent access, approval, hostnames, secrets, destructive commands, or cron schedules. If execution needs elevated privileges or persistent automation, the brief should say that explicit approval is required.

## Use Cases

- turn a messy request into a precise agent brief
- make acceptance criteria explicit before an agent starts work
- capture constraints, non-goals, inputs, and verification steps
- reduce rework from vague prompts and missing context

---

## The Problem

Every wasted token is a wasted API call.
Every vague word is a future bug.
Every missing acceptance criterion is a future rework cycle.

"Improve the translation system" is not a brief.
"Fix formSchemaTranslated being NULL for German locale — AC1: all 50 prompt rows have formSchemaTranslated populated after running translate/de endpoint" is a brief.

---

## Credibility Artifact

See [`examples/README.md`](examples/README.md) for the example index, or jump straight to [`examples/messy-to-clean-brief.md`](examples/messy-to-clean-brief.md) for a concrete messy request -> clean agent brief example with ACs, constraints, non-goals, and verification commands.

## The Pipeline

1. Detect the target agent and runtime
2. Extract 9 dimensions of intent
3. Ask max 3 clarifying questions (only if critical info is missing)
4. Apply the right format for the target agent
5. Run token efficiency audit
6. Deliver one clean, ready-to-use brief

---

## The 9 Dimensions

1. **Task** - what exactly should be done (one verb, one outcome)
2. **Input** - what does the agent need to start (files, machines, branches)
3. **Output** - what should exist when done
4. **Constraints** - what must not break
5. **Context** - only what changes what the agent does
6. **Audience/Role** - which agent, what runtime
7. **Memory** - what files to read first
8. **Success Criteria** - AC1, AC2, AC3 (testable, specific)
9. **Examples** - reference points that clarify expected behaviour

---

## When To Use Which Repo

Use this repo when the task is still too

_meta.json

{
  "ownerId": "kn7d3r58cdxk8k0xg6jq6k65gs873c0c",
  "slug": "brief-master",
  "version": "0.2.1",
  "publishedAt": 1779616802661
}

references/9-dimensions.md

# 9 Dimensions of Intent

Extract only the dimensions needed to make the brief executable. Do not turn this into an interview script when context is already clear.

## 1. Task

What should the agent do?

- One verb, one outcome
- Split unrelated tasks into separate briefs
- Prefer "fix X" / "implement Y" / "review Z" over vague "work on"

## 2. Input

What does the agent need to start?

- Repo, files, URLs, datasets, credentials, or screenshots
- Runtime/host if relevant
- Branch, directory, service, or environment

Avoid vague location text like "in the repo" when the exact path or branch matters.

## 3. Output

What should exist when the agent is done?

- Files created or changed
- Tests/proof artifacts generated
- Commit, PR, report, or message expected
- Service or data state expected

## 4. Constraints

What must not break?

- Existing behaviours
- Files, data, credentials, or generated assets that must not be touched
- Backwards compatibility or performance limits
- Security/privacy boundaries

## 5. Context

What does the agent need to understand about why this task exists?

Keep it short. Include only context that changes the work.

## 6. Audience / Role

Who is the brief for?

- Builder / implementer
- Reviewer / verifier
- Researcher
- Cron or scheduled agent
- Human operator

Role determines autonomy, tool expectations, and output shape.

## 7. Prior Context

What should the agent read first?

- Specs, issue links, previous verdicts, relevant docs
- Existing implementation patterns
- Prior decisions or non-goals

## 8. Success Criteria

How does everyone know it is done?

- Use explicit AC1, AC2, AC3 where possible
- Each AC must be testable by a fresh verifier
- Include the exact verification command or manual check when known

If you cannot write a testable AC, the task is under-defined.

## 9. Examples

What examples clarify the intended result?

- Before/after screenshots
- Expected output format
- Similar accepted implementation
- Known-good command output

## Quick Extraction Prompt

Ask at most three questions in one round:

```text
I can write the brief, but I need three specifics:
1. [missing blocker]
2. [missing blocker]
3. [missing blocker]
```

If more than three answers are missing, ask the three that most affect correctness and note the remaining assumptions in the brief.

Github ReposUpdated 3d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular