Skip to content
Agentmart
Submit a tool

value-ask

Use when a user describes a goal or question and wants to be pointed to the right value-boardroom command with a short explanation.

Skill by white-source

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/white-source-value-ask

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when a user describes a goal or question and wants to be pointed to the right value-boardroom command with a short explanation.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/value-ask

What's inside

Skill name
value-ask
Description
Use when a user describes a goal or question and wants to be pointed to the right value-boardroom command with a short explanation.
License
MIT
Instructions
50 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Value Ask

User-entry dispatcher. The user states a goal or question in natural language (any language); `value-ask` maps it to the most fitting `value-*` command and explains what it does. It recommends — it does not run the command itself.

## Command

| Command | Purpose |
|---|---|
| `/value-ask [your question or goal]` | Recommend the right value-boardroom command and explain it |

Examples:
- `/value-ask 我想看这家公司的现金流是怎么来的`
- `/value-ask I'm worried a price cut would hurt the business`
- `/value-ask where do I even start?`

## Behavior

1. **Read the intent.** Restate the user's goal in one line so they can confirm you understood.
2. **Match the catalog.** Find the best command from the decision table below.
3. **Recommend.** Output the top command first, then at most two alternatives. For each: the command, a one-line explanation, and when to use it.
4. **Offer to proceed.** Ask whether to run the top recommendation. The user runs it; `value-ask` must not invoke another entry skill on its own.
5. **Fallback.** If nothing matches, recommend `/value-boardroom [company]` as the default starting point.

Keep the answer short — a recommendation, not a lecture.

## Decision Table

Map the user's intent to a command:

| If the user wants to… | Recommend |
|---|---|
| Start studying a company, set up the boardroom, or switch company | `/value-boardroom [company]` |
| Switch role mode — reverse roles, "examine me", or play an executive yourself | `/value-mode [briefing\|examination]` |
| Hear from a specific department or executive (CFO, supply, sales…) | `/value-role-<role>` shortcut, e.g. `/value-role-cfo` (auto-completes — type `/value-role-` and pick) |
| Visit several roles, or tour the whole company without retyping | `/value-role ceo cfo ...` to chain, or `/value-next` to step through |
| Gather facts, filings, earnings, or verify a source | `/value-research [topic]` |
| Check or revise modelling inputs / assumptions | `/value-assumption` |
| See what evidence has been collected | `/value-evidence` |
| Connect operations to FCF, margin, working capital, CapEx, ROIC | `/value-cashflow` |
| Test a shock, or build bear/base/bull scenarios | `/value-stress-test [shock]` |
| Pre-mortem: how the business could break or run out of cash | `/value-kill [year]` |
| Wrap the session into a traceable board conclusion | `/value-board-summary` |

## Rules

- Recommend, never execute. The user runs the chosen command.
- Rank at most three commands; always include a one-line explanation for each.
- This is a research and learning framework — do not steer toward investment recommendations, target prices, or trade instructions.

From white-source/value-grill-skill, MIT.

More from white-source/value-grill-skill

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Jul 16, 2026 (3 months ago)
Last release
Jul 17, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from white-source

Cite this page

value-ask skill. Agent Mart. https://agentmart.dev/skills/white-source-value-ask (last updated 2026-10-24)