Skip to content
AI & Agents
Command

/cs-grill-commercial

Matt Pocock-style docs-anchored grilling for a Commercial plan, deal, pricing decision, or forecast. Walks the user's plan against the SaaS pricing canon (Skok, Tunguz, Bessemer, Ramanujam, ProfitWell, Winning by Design) one question at a time, recommends an answer per question,

From plugin
claude-skills
30k173 skills129 agents173 commands2 MCP
$ npx -y skills add alirezarezvani/claude-skills --agent claude-code

Command definition

cs-grill-commercial.md
disable-model-invocation: true
description: Matt Pocock-style docs-anchored grilling for a Commercial plan, deal, pricing decision, or forecast. Walks the user's plan against the SaaS pricing canon (Skok, Tunguz, Bessemer, Ramanujam, ProfitWell, Winning by Design) one question at a time, recommends an answer per question, and refuses to invoke any sub-skill until the lane-defining decisions are locked. Use before running /cs-commercial on a fuzzy plan.
argument-hint: "<plan, deal, pricing question, or fuzzy commercial problem>"

/cs-grill-commercial — Commercial grill against the SaaS pricing canon

Apply Matt Pocock's `grill-with-docs` discipline to this Commercial plan / problem:

**$ARGUMENTS**

Five rules (preserved from Matt Pocock, MIT)

1. **One question per turn.** Never bundle. 2. **Recommend an answer with each question.** 3. **Explore the workspace before asking** — check for deal records, pricing comps, RFP docs, MSA redlines. 4. **Walk depth-first.** 5. **Track dependencies** — pricing → packaging → deal → forecast.

The Commercial decision tree (depth-first)

Branch 1 — Which lane?

  • PRICING / DEAL / PARTNERSHIP / CHANNEL_ECON / POLICY / RFP / FORECAST

Branch 2 — The forcing question per lane

**PRICING:** "Is your customer paying for outcomes, seats, or usage?" Recommended: outcomes (value-based) if you can measure them; usage if marginal cost is variable; seats only if usage is roughly flat per user. Canon: Ramanujam 2016 *Monetizing Innovation* (the 9-mistake list). Anti-pattern: seat-based on a usage-variable product caps TAM at ~20% of WTP.

**DEAL:** "What's the gross margin at full discount, AND what does next quarter's pipeline look like at the same terms?" Recommended: model both. Refuse to approve until reps can articulate the precedent risk. Canon: Skok (For Entrepreneurs — discount math), Tunguz benchmarks. Anti-pattern: one 40% precedent reshapes 3 quarters of pipeline.

**PARTNERSHIP:** "Does the partner have independent demand, or are they reselling our pipeline?" Recommended: insist on independent-demand evidence (named accounts the partner sourced, not co-sold). Canon: Forrester channel research. Anti-pattern: channel-led deals from your own pipeline cost more than direct.

**CHANNEL_ECON:** "What's your fully-loaded cost-to-serve direct vs partner?" Recommended: model both with allocated overhead. Canon: Bessemer State of the Cloud channel benchmarks.

**POLICY:** "Is your current discount matrix backed by data, or by precedent?" Recommended: data — discount band vs. win rate vs. NRR. Canon: OpenView discount studies.

**RFP:** "Do you have proof points for each requirement, or are you writing aspirational claims?" Recommended: proof points only. Refuse to invent claims. Canon: APMP (Association of Proposal Management Professionals).

**FORECAST:** "Are you using stage-conversion from the last 4 quarters, or the last 12?" Recommended: last 4, weighted toward most recent. Canon: Skok, OpenView. Anti-pattern: 12-month equal-weight hides recent slowdown.

Branch 3 — Reversibility check

"If this commercial decision lands and we want to roll it back in 90 days, what does it cost?" Hard-to-reverse + surprising + real trade-off → ADR per Matt's grill-with-docs criteria.

Branch 4 — Approval chain

"Who is the human approver on the output?" Recommended: named role + named person, not "the team".

Branch 5 — Now invoke the sub-skill

Only after branches 1-4 are locked, invoke `/cs-commercial` with the synthesized inquiry.

Output format per turn

Q[i]/[total]: [precise question]
Recommended: [answer + canon-cited rationale]

(Confirm, or override?)

Stop conditions

  • All branches resolved → invoke `/cs-commercial <synthesized>`
  • User says "stop grilling, just run it" → invoke with whatever's resolved, flag unresolved branches in digest
  • User abandons → no sub-skill, save partial grill to `commercial-grill-{timestamp}.md`

Distinct from

  • `engineering/grill-me` (Matt Pocock) — generic
  • `engineering/grill-with-docs` (Matt Pocock) — codebase + ADR-anchored for engineering. This is **Commercial-domain grilling** against the SaaS pricing canon.
  • `/cs-commercial` — **executes** routing. This **interrogates** first.
Read more
@alirezarezvani
Ships withclaude-skills

415 production-ready skills for Claude Code and 12 other coding agents, covering engineering, product, marketing, compliance, finance and the C-suite. We test whether each skill loads when you ask in plain words, and publish the results.

30k200 skills129 agents2 MCP
Get the whole plugin

Stars on GitHub

Momentum

stars in total
29.8k
Star history of alirezarezvani/claude-skills on GitHub, a chart by star-history.com

Other commands on claude-skills.

focused-fix

focused-fix

Command

Deep-dive feature repair — systematically fix an entire feature/module across all its files and dependencies. Usage: /focused-fix…

plugin-audit

plugin-audit

Command

Comprehensive audit pipeline for skills, plugins, agents, and commands. Validates structure, quality, security, marketplace…

More commands from other plugins.

devbox-entrypoint

devbox-entrypoint

Command

Context: runloop resumes a devbox by re-running the same entrypoint script, which invokes `cn serve --id <agentId> ...`. Because…

@continuedev@continuedevInstall Command
c

c

Command

Shortcut for "continue working" — pick the work in flight back up exactly where it stopped and keep going until it is done or…

lifeos2w20k
@danielmiessler@danielmiesslerInstall Command
sidecar

sidecar

Command

Spawn a read-only sidecar subagent to investigate something in this checkout without editing files, moving branches, or touching…

@builderio@builderioInstall Command