Skip to content
Agentmart
Submit a tool

sib

Say it back — restate the user's goal and the problem they are solving in your own words, then wait for them to confirm before any work.

Skill by GUOJIE-HONG

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying sib?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/guojie-hong-sib

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

Say it back — restate the user's goal and the problem they are solving in your own words, then wait for them to confirm before any work.

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/sib

What's inside

Skill name
sib
Description
Say it back — restate the user's goal and the problem they are solving in your own words, then wait for them to confirm before any work.
License
MIT
Instructions
40 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Say It Back

Play back your understanding before the work starts, so the user can catch where you and they diverge. Your deliverable is the **playback**, given in the conversation.

If the user passed an argument, it is the request to restate. Otherwise restate the request currently in play.

## 1. Separate the ask from the goal

Work from the conversation and what the user pointed to. Open a file only when the request names it and its meaning depends on it.

Pull apart three things:

- the **ask**: what the user literally requested
- the **goal**: what is true for the user once this is done
- the **problem**: what is wrong or missing today, the reason the goal matters

The ask is often a means to the goal. When it is, the gap between them is an **XY problem** waiting to happen, and naming it is the most useful thing the playback can do.

## 2. Play it back

Write in the language the user is using, labels included. Use your own words: copied phrasing hides a misunderstanding, recast phrasing exposes it.

- **Goal**: one or two sentences, what done looks like. When the ask differs from the goal, name both: "You asked for X; what it serves is Y."
- **Problem**: one or two sentences, what hurts now.
- **Unsure**: each thing you could not tell, one short line each. Write "none" when nothing is.

End each sentence under Goal and Problem with its basis: a short quote of the user, a `path:line`, or `(inferred)`.

Close with one line asking whether this is right.

Done when every sentence under Goal and Problem carries a basis.

## 3. Wait for the verdict

End the turn on the playback; the task waits for the user.

- The user corrects it: revise and play back the whole thing again, so they confirm one complete picture.
- The user confirms: the confirmed goal and problem are the reference for the work that follows. If Unsure still holds points that would change how the work is done, say so in one line and suggest `$torture-gently`.

From GUOJIE-HONG/skills, MIT.

More from GUOJIE-HONG/skills

Signals

Stars
1
Forks
1
Open issues
1
Last commit (this folder)
Oct 7, 2026 (23 days ago)
Last release
Oct 23, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from GUOJIE-HONG

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get sib running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying sib?

CallGet help
Cite this page

sib skill. Agent Mart. https://agentmart.dev/skills/guojie-hong-sib (last updated 2026-10-24)