Best use case

tldr is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Teams using tldr should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/tldr/SKILL.md --create-dirs "https://raw.githubusercontent.com/agenticnotetaking/eidos/main/skills/tldr/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/tldr/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How tldr Compares

Feature / AgenttldrStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

This skill provides specific capabilities for your AI agent. See the About section for full details.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# /eidos:tldr

Get the gist fast.
Bullet-point summary — as short as possible without losing core ideas.

## Usage

```
/eidos:tldr [target]           — default granularity (minimal)
/eidos:tldr [target] detailed  — more granularity, still concise
```

Target can be a file path, glob pattern, topic name, spec, or "this conversation".

## Instructions

1. Read the target (file, files, spec, or conversation)
2. Distill to **5–10 bullet points** at default granularity
   - Each bullet: one core idea, one line
   - If the source genuinely needs more bullets to avoid losing meaning, go up to ~15
   - With `detailed` arg: allow more bullets, sub-bullets for nuance, but still earn every line
3. Output directly in chat — no file created
4. Use this structure:

```
**TL;DR: [target name]**

- [core idea 1]
- [core idea 2]
- ...
```

## Principles

- Default to **fewer bullets, not more** — the user wants the gist, not a rewrite
- Each bullet should stand alone — no "see above" or forward references
- Prefer concrete over abstract ("uses wiki links for cross-referencing" over "has a linking system")
- If the target is multiple files, give one unified summary, not per-file summaries (unless the user asks)
- Skip boilerplate, imports, config — focus on what the thing *does* and *why*

## Output

- No files created — purely informational
- Displayed directly in chat