brief · alirezarezvani — Claude Code skill: one-page strategy brief
Turns a strategic question or meeting notes into a one-page brief with options, assumptions and success criteria. Meant to run before deliberation.
/plugin marketplace add alirezarezvani/claude-skills
/plugin install c-level-agents@claude-code-skillsWhat brief does
The skill frames a raw question as a document the boardroom can argue over. Input is either a topic string or the output of /c-level-agents:office-hours. The result lands in ~/.claude/briefs/ as YYYY-MM-DD-<slug>.md, using a fixed layout: context from ~/.claude/company-context.md, the question in one sentence, at least two options, assumptions, limits on time and budget, affected roles, success criteria.
Two options is the floor, and doing nothing counts as one of them. Assumptions and constraints get spelled out. Success and kill criteria are written before the choice is made. Ticked roles decide the panel for /c-level-agents:boardroom.
Loading company-context.md goes through context-engine, so the file has to exist at that path — otherwise the context section stays empty. Feed it a bare topic and the agent asks for whatever is missing. The next command in the pipeline reads the saved file, not the session's memory.
What it helps with
- lock the question before arguing about implementation
- lay out options and a counterfactual for a pricing change
- state assumptions and constraints explicitly
- set success metrics up front
- hand the decision to the next pipeline step as a file
Example prompts for the agent
- Write a brief on the pricing change:
/c-level-agents:briefpricing model change - Turn my office-hours notes into a brief with
/c-level-agents:briefand paste the/c-level-agents:office-hoursoutput - Frame the market-entry decision:
/c-level-agents:briefentering a new market
How to install brief
1Plugin marketplace
/plugin marketplace add alirezarezvani/claude-skills/plugin install c-level-agents@claude-code-skillsThis installs the whole c-level-agents plugin with all its skills
2Skills CLI (Vercel)
npx skills add alirezarezvani/claude-skills --skill brief -a claude-code3Manually: put the files in place
~/.claude/skills/brief/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/brief/
Manually: put the files in place
.agents/skills/brief/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/brief/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install alirezarezvani/claude-skills brief2Manually: put the files in place
.github/skills/brief/SKILL.mdPlatform CLI
gemini skills install https://github.com/alirezarezvani/claude-skills --path c-level-agents/skills/briefManually: put the files in place
.devin/skills/brief/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about brief
How do I install brief in Claude Code?
From the marketplace: run /plugin marketplace add alirezarezvani/claude-skills, then /plugin install c-level-agents@claude-code-skills.
What does brief do?
It writes a one-page strategy brief covering the question, options, assumptions, time and budget limits, affected roles and success criteria. The file goes to ~/.claude/briefs/.
What does the skill need to run?
A ~/.claude/company-context.md file, which context-engine loads for the context section. Without it that part comes out empty.
Source text
SKILL.md · MIT
---
name: "brief"
description: "/c-level-agents:brief [topic] — Generate a one-page strategy brief from an office-hours intake. First step in the strategic sprint pipeline. Use when a strategic question needs to be framed before boardroom deliberation — e.g. locking options, assumptions, and success criteria for a pricing change or a market-entry decision."
---
# /c-level-agents:brief — One-Page Strategy Brief
**Command:** `/c-level-agents:brief <topic>` or `/c-level-agents:brief <office-hours-output>`
Turns intake (raw question or office-hours output) into a one-page strategy brief that the boardroom can deliberate on. This is **Step 1** of the strategic sprint pipeline.
## Pipeline Position
```
/c-level-agents:office-hours → /c-level-agents:brief → /c-level-agents:boardroom → /c-level-agents:decide → /c-level-agents:execute → /c-level-agents:post-mortem
↑ you are here
```
## Inputs
- A topic string, **or**
- An office-hours brief (preferred — more rigor)
- `~/.claude/company-context.md` (loaded automatically)
## Output
A single Markdown file under `~/.claude/briefs/YYYY-MM-DD-<slug>.md` with this structure:
```markdown
# Strategy Brief: <topic>
**Date:** YYYY-MM-DD
**Author:** cs-chief-of-staff
**Status:** DRAFT | UNDER REVIEW | APPROVED | RETIRED
## Context
[1-2 paragraphs: where the company sits today on this topic — pulled from company-context.md]
## Question
[The one sentence question the boardroom must answer]
## Options
1. **Option A:** <name> — <one-sentence summary>
2. **Option B:** <name> — <one-sentence summary>
3. **Option C:** <name> — <one-sentence summary>
(Minimum 2 options. "Do nothing" is always an option.)
## Assumptions
- <assumption 1 — explicit>
- <assumption 2>
- <assumption 3>
## Constraints
- Time: <by when must this decide>
- Money: <budget envelope>
- People: <who can / can't be reallocated>
- Reversibility: <one-way door | two-way door>
## Affected Roles
[Which cs-* advisors should weigh in. Used to route to /c-level-agents:boardroom panel composition.]
- [ ] cs-ceo-advisor
- [ ] cs-cfo-advisor
- [ ] cs-cto-advisor
- [ ] cs-cmo-advisor
- [ ] cs-cro-advisor
- [ ] cs-cpo-advisor
- [ ] cs-coo-advisor
- [ ] cs-chro-advisor
- [ ] cs-ciso-advisor
- [ ] cs-general-counsel-advisor
- [ ] cs-cdo-advisor
- [ ] cs-caio-advisor
- [ ] cs-cco-advisor
- [ ] cs-vpe-advisor
- [ ] cs-chief-of-staff
## Success Criteria
[Measurable outcomes that define success — set BEFORE the decision]
- <metric 1, threshold, timeframe>
- <metric 2, threshold, timeframe>
## Kill Criteria
[What signal would tell you in 90 days that this was the wrong call]
- <metric, threshold, action if missed>
```
## Workflow
1. Load company-context.md via context-engine
2. If input is office-hours output, parse the 6 answers
3. If input is a raw topic, prompt the founder for the missing pieces
4. Draft 2-3 options (never just one — every brief needs a counterfactual)
5. Make assumptions and constraints explicit
6. Identify affected roles → drives panel composition for `/c-level-agents:boardroom`
7. Write success + kill criteria BEFORE the decision (this is the rigor moment)
8. Save to `~/.claude/briefs/`
## Why This Step Exists
The biggest decision-making failure is debating implementation before agreeing on the question. The brief locks the question, options, and success criteria so the boardroom can deliberate without scope creep.
This is also the **artifact handoff** — the next command consumes this file, not your memory.
## Routing
- `/c-level-agents:boardroom <brief>` — multi-role deliberation
- `/c-level-agents:cross-eval <brief>` — multi-model sanity check before boardroom (for high-stakes)
- `/c-level-agents:freeze <brief>` — cooldown lock for irreversible decisions
## Related
- Agent: [`cs-chief-of-staff`](../../agents/cs-chief-of-staff.md)
- Skills: [`context-engine`](${CLAUDE_PLUGIN_ROOT}/vendor/c-level-advisor/context-engine/SKILL.md), [`board-meeting`](${CLAUDE_PLUGIN_ROOT}/vendor/c-level-advisor/board-meeting/SKILL.md)
---
**Version:** 1.0.0
© Alireza Rezvani · MIT · alirezarezvani/claude-skills
Similar skills
All skills for Agent setup: memory, context, orchestration →brief by other authors comes first.
