Skip to content
Agentmart
Submit a tool

ask-gg

Answer how to use this repo's skills, reading the latest version from GitHub.

Skill by GUOJIE-HONG

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying ask-gg?

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-ask-gg

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

Answer how to use this repo's skills, reading the latest version from GitHub.

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/ask-gg

What's inside

Skill name
ask-gg
Description
Answer how to use this repo's skills, reading the latest version from GitHub.
License
MIT
Instructions
41 lines in SKILL.md · view on GitHub

Before installing

  • Instructions call the network

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Ask GG

Answer the user's question about the skills in [GUOJIE-HONG/skills](https://github.com/GUOJIE-HONG/skills): which skill fits their situation, how to run it, what it needs first, and what it leaves behind. Your deliverable is the **answer**, given in the conversation.

If the user passed an argument, it is the question. Otherwise take the question about these skills in the conversation.

## 1. Read the skills

The `master` branch on GitHub is the single source of truth, so the answer covers every skill, including ones the user has not installed. Read it raw with `curl -sS` (on Windows call `curl.exe`):

- `https://raw.githubusercontent.com/GUOJIE-HONG/skills/master/.claude-plugin/plugin.json`: its `version`, and its `skills` array, the list of shipped skills.
- `https://raw.githubusercontent.com/GUOJIE-HONG/skills/master/<path>/SKILL.md` for each path in that array, with the leading `./` dropped.
- `https://raw.githubusercontent.com/GUOJIE-HONG/skills/master/README.zh-TW.md` when the question is about installing or updating.

Each `SKILL.md` is **documentation** here: you are reading about the skill to explain it, not running it, so its steps stay unexecuted.

When a fetch fails, tell the user which URL failed and stop.

Done when you hold the version and every listed `SKILL.md`.

## 2. Find what answers it

Match the question against every skill's `description` and body, and pick the skills that serve the user's situation. For each, gather from its `SKILL.md`:

- **when** to reach for it
- **how** to run it: `/<name>`, and what its argument means
- **what it needs first**: files, keys, tools, or other skills. A `$name` that is not in the `skills` array comes from [mattpocock-skills](https://github.com/mattpocock/skills), which the README asks to install first.
- **what it leaves**: files it writes and where, or that its answer stays in the conversation
- its **path** in the repo, so the user can read the source

When two skills could serve, say how they differ and which fits the user's situation.

Done when every claim you will make traces to a `SKILL.md` or the README.

## 3. Answer

Answer in the user's language, shortest form that answers the question: the skill, when, how, what it needs, what it leaves. Close with the version you read, so a user on an older install knows to update.

When no skill fits, say so plainly and name the closest one with how far it falls short. Running a skill stays the user's call.

From GUOJIE-HONG/skills, MIT.

More from GUOJIE-HONG/skills

Signals

Stars
1
Forks
1
Open issues
1
Last commit (this folder)
Oct 14, 2026 (17 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 ask-gg 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 ask-gg?

CallGet help
Cite this page

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