agent-launcher-orchest…
Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a…
/cs: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
$ npx -y skills add alirezarezvani/claude-skills --skill brief --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/briefContext preview
The summary Claude sees to decide when to auto-load this skill.
/cs: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
name: "brief" description: "/cs: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."
**Command:** `/cs:brief <topic>` or `/cs: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.
/cs:office-hours → /cs:brief → /cs:boardroom → /cs:decide → /cs:execute → /cs:post-mortem
↑ you are hereA single Markdown file under `~/.claude/briefs/YYYY-MM-DD-<slug>.md` with this structure:
# 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 /cs: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>
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 `/cs:boardroom` 7. Write success + kill criteria BEFORE the decision (this is the rigor moment) 8. Save to `~/.claude/briefs/`
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.
---
**Version:** 1.0.0
388 production-ready Claude Code skills, plugins, and agent skills for 13 AI coding tools. The most comprehensive open-source library of Claude Code skills and agent plugins — also works with OpenAI Codex, Gemini CLI, Cursor, and 9 more coding agents.
Repo: alirezarezvani/claude-skills
Use when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a…
Phase 3 of building a Claude Managed Agent — the bounded grade→iterate loop. Define a CMA outcome (a required markdown rubric graded by an isolated grader),…
Phase 1 of building a Claude Managed Agent — interview the founder about the one job the agent should do, then produce a build sheet (CMA primitives table +…
Phase 4 of building a Claude Managed Agent — make it run without you. Turn a graded agent into a recurring scheduled deployment (POSIX-cron), an event-driven…
Phase 2 of building a Claude Managed Agent — turn a validated build sheet into exact API payloads and a resumable BYOK curl launch script, then launch…
Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2…