Skill
arsenal
Use when the user invokes Arsenal, needs help choosing an approach, or wants an end-to-end task handled with the installed Arsenal skills.
@mirkobozzettoView SkillDevelopment
Skill
/brief
Write a product brief and its task list when the user requests a product specification. Never implement it.
Install
$ npx -y skills add mirkobozzetto/arsenal --skill brief --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/brief
Context preview
The summary Claude sees to decide when to auto-load this skill.
Write a product brief and its task list when the user requests a product specification. Never implement it.
SKILL.md
brief.SKILL.mdname: brief
description: Write a product brief and its task list when the user requests a product specification. Never implement it.
argument-hint: "<idea> [-a] [-s] [--html]"
Brief
Clarify only missing product decisions: user, problem, scope, constraints and observable success. Do not repeat information already supplied or require a numeric business metric for a small usability change. Group related questions in plain prose; no start/proceed confirmations. -a/-s allow explicit assumptions, not invented certainty or external permissions.
Write docs/brief/<slug>/brief.md and tasks.md. Keep the existing frontmatter and structural headings Acceptance criteria, Success metrics, Out-of-scope, Relevant Files and Tasks. Derive outcome tasks from acceptance criteria; do not inflate them into a fixed number of phases. One feature, one folder.
Mark ready only when the brief is complete; never implement automatically. Render with scripts/render.py only for --html or an explicit request. No mandatory browser, commit, test run, or handoff menu. Report paths and the next action if requested. Existing files are updated, not duplicated.
Arsenal handoff
When called by Arsenal for an explicitly requested broader task, return the brief, its readiness and unresolved decisions to Arsenal. Do not launch ship yourself. Arsenal may continue an authorized implementation once the brief is ready; a request for a brief alone never authorizes implementation.
Execution policy
Work solo. Ask before any subagent or reviewer, even in auto mode. Explain the independent scope and expected benefit first. No hidden advisor, nested delegation, model retuning, repeated successful checks, or progress spam. Use existing context before asking questions. Stop when the requested result is delivered. User stops and scope changes override pending steps.
Read more
name: brief description: Write a product brief and its task list when the user requests a product specification. Never implement it. argument-hint: "<idea> [-a] [-s] [--html]"
Brief
Clarify only missing product decisions: user, problem, scope, constraints and observable success. Do not repeat information already supplied or require a numeric business metric for a small usability change. Group related questions in plain prose; no start/proceed confirmations. -a/-s allow explicit assumptions, not invented certainty or external permissions.
Write docs/brief/<slug>/brief.md and tasks.md. Keep the existing frontmatter and structural headings Acceptance criteria, Success metrics, Out-of-scope, Relevant Files and Tasks. Derive outcome tasks from acceptance criteria; do not inflate them into a fixed number of phases. One feature, one folder.
Mark ready only when the brief is complete; never implement automatically. Render with scripts/render.py only for --html or an explicit request. No mandatory browser, commit, test run, or handoff menu. Report paths and the next action if requested. Existing files are updated, not duplicated.
Arsenal handoff
When called by Arsenal for an explicitly requested broader task, return the brief, its readiness and unresolved decisions to Arsenal. Do not launch ship yourself. Arsenal may continue an authorized implementation once the brief is ready; a request for a brief alone never authorizes implementation.
Execution policy
Work solo. Ask before any subagent or reviewer, even in auto mode. Explain the independent scope and expected benefit first. No hidden advisor, nested delegation, model retuning, repeated successful checks, or progress spam. Use existing context before asking questions. Stop when the requested result is delivered. User stops and scope changes override pending steps.
Ships witharsenal
Portable workflow skills and controlled runtime for Pi, OMP, Codex, and Claude Code
Get the whole plugin
Stats
15
Stars
1
Forks
Active
Maintenance
Python
Language
MIT
License
9d ago
Last commit
3mo ago
Created
Repo: mirkobozzetto/arsenal
Other skills on arsenal.
@mirkobozzettoView SkillSkill
issue
Create, update or resume a GitHub issue as durable resolution memory when requested.
@mirkobozzettoView SkillSkill
next
Report unfinished work and the exact next action from existing artifact states. Never resume or implement automatically.
@mirkobozzettoView SkillSkill
propose
Design a concrete technical proposal with evidence and tradeoffs when a decision needs design. No implementation or automatic reviewer.
@mirkobozzettoView SkillSkill
ship
Implement a clear request or an approved brief/proposal. Work solo, make the smallest sufficient change, verify the changed behavior, and stop. Ask before any…
@mirkobozzettoView SkillSkill
trace
Read or explicitly record project progress using the existing deterministic trace script.
@mirkobozzettoView Skill