Skip to content
Agentmart
Submit a tool

read-existing-content

Routine: Show the content of an existing course/lesson/topic from a human reference (title or admin URL) — resolves IDs, then reads the actual topic bodies.

Skill by thoughtindustries

IndexedMIT
Write a review

Chalk Labs

Need help deploying read-existing-content?

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/thoughtindustries-read-existing-content

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

Routine: Show the content of an existing course/lesson/topic from a human reference (title or admin URL) — resolves IDs, then reads the actual topic bodies. No UUIDs required from the user.

Use cases: writing

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/read-existing-content

What's inside

Skill name
read-existing-content
Description
Routine: Show the content of an existing course/lesson/topic from a human reference (title or admin URL) — resolves IDs, then reads the actual topic bodies. No UUIDs required from the user.
License
MIT
Instructions
45 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Read Existing Content

This is a **Routine** skill — a reliable, repeatable sequence of Actions. Follow the steps exactly. Minimize judgment — the process is fixed.

## Purpose

Answer requests like **"show me the content of lesson X in course Y"** or **"what does this topic say"** when the user refers to content by **title or admin URL**, not by UUID. This routine resolves the IDs and returns the real HTML **body** of the topic(s) — the flow that previously failed when reads returned no content.

Use this whenever someone wants to *see* existing content. (To change it afterwards, hand off to **`rewrite-lesson`** or **`update-course-content`**.)

## Process

### Step 1 — Resolve the reference to IDs

Run the **`resolve-content`** action with whatever the user gave you (course title, slug, admin/catalog URL, or UUID), plus an optional lesson/topic name:

```bash
node "${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT/skills/actions/resolve-content/}resolve-content.js" --course="COURSE TITLE | slug | URL | UUID" [--lesson="LESSON NAME"] [--topic="TOPIC NAME"]
```

- If it returns `"resolved": true`, use `ids.courseId` (and any `ids.lessonId` / `ids.topics`).
- If it returns `candidates`, present them to the user and ask which one — **never guess a UUID**.
- If nothing matched, tell the user and offer to browse with `list-course-groups`.

### Step 2 — Read the actual content bodies

Run the **`get-full-content`** action with the resolved `courseId`. If a lesson was resolved, focus the tree on it:

```bash
node "${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT/skills/actions/get-full-content/}get-full-content.js" --id=COURSE_UUID [--lesson=LESSON_UUID]
```

Use the `_tree` view to line up each topic's `id`, `title`, and `body`.

> Do **not** try to read content with `get-topic` or `get-topics-by-lesson` — those return metadata only, never the `body`.

### Step 3 — Present the content

Show the requested topic(s) with their titles and rendered/plain body. If the user asked about a specific lesson or topic, filter to it. Keep the topic `id`s handy in case the user next asks to edit — a follow-up edit goes through `update-course-content` (see `rewrite-lesson`), and existing content **is** editable via the API (do not defer to manual TI editing for a plain body change).

<HARD-GATE>
This routine is read-only. Do not modify, create, delete, or publish any content.
</HARD-GATE>

From thoughtindustries/ti-admin-plugin, MIT.

More from thoughtindustries/ti-admin-plugin

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Aug 6, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from thoughtindustries

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 read-existing-content 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 read-existing-content?

CallGet help
Cite this page

read-existing-content skill. Agent Mart. https://agentmart.dev/skills/thoughtindustries-read-existing-content (last updated 2026-10-24)