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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/tldr/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How tldr Compares
| Feature / Agent | tldr | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/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 chatRelated Skills
spec
This skill guides an AI agent to collaboratively think through and create a detailed technical specification document via structured Q&A. It clarifies target, behavior, and design before generating the spec file.
worktree
No description provided.
wish
No description provided.
weave
No description provided.
video
No description provided.
true-name
No description provided.
toskill
No description provided.
toscript
No description provided.
tomd
No description provided.
toeidos
No description provided.
todo
No description provided.
toclaude
No description provided.