tldr
Skill2 starsChanged 2 months agoMITView on GitHub
Quick plain-language brief — skip the explanation, get the point.
40 other projects use a version of this.
Adopted by
Most recently taken up by
- annatomka/skillstheir own version, first seen Nov 8, 2026
- zazencodes/skillstheir own version, first seen Nov 8, 2026
- MarkPhamm/claude-skillstheir own version, first seen Nov 8, 2026
- nirberko/skillstheir own version, first seen Nov 8, 2026
- richkuo/rk-skillstheir own version, first seen Nov 8, 2026
- LaansDole/my-hermes-skillstheir own version, first seen Nov 7, 2026
Used with
Projects with it also use explain, handoff and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
sunnyclinches44Skillexplain
Explains code using real-world analogies and ASCII diagrams
Also in 3 projects that use this
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 6 projects that use this
Google CloudSkilltriage
Gather context on a change or bug and plan the implementation.
Also in 3 projects that use this
GoogleSkillgrill-me
A relentless interview to sharpen a plan or design.
Also in 3 projects that use this
Other versions40 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 40
- earlyaidopters/second-brain★ 193same name
- saksham10arora-dotcom/everything-claude-codex★ 74same name
- richkuo/rk-skills★ 50same name
- gsarig/skills★ 30same name
- peterpme/skills★ 28same name
- Vesely/skills★ 28same name
- nirberko/skills★ 19same name
- r13i/skills★ 17same name
- SurefireStudios/tldr★ 9same name
- jamesblackwell/falcondeck★ 7same name
30 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- 3wSkill
- catchupSkill
- clear-viewSkill
- decisionSkill
- first-principleSkill
- impactSkill
- one-lineSkill
- scopeSkill
- tradeoffSkill
- visSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 35 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 23
No section headers — at this length they'd cost more lines than they buy.
- Distinctive: line 24
No diagrams, no analogies, no history.
- Distinctive: line 25
Every word earns its place.
- Very specific: line 72
Don't write 一句話解釋 JWT 是什麼意思 as the headline — that's the user's question, not the topic.
- Distinctive: line 75
Don't stretch to four bullets because the topic feels rich.
- Distinctive: line 78
Don't let the bottom line repeat the opening sentence in different words.
- Distinctive: line 81
If no request was supplied, ask: "Quick brief on what?"
“Common” is measured: kept by at least 6 in 10 of the 35 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
TL;DR
Goal: user reads this in 10 seconds and knows what to do.
Rules
- Respond in the same language the user wrote in. If they write in Chinese, reply in Chinese. Technical terms (JWT, Redis, API…) stay in English.
- Max 5 lines. Hard limit. That is exactly: headline, one sentence, two bullets, bottom line.
- The headline is the topic, not the question. Turn whatever the user typed into a short noun phrase —
**JWT**,**one-line 的粗體**. Never echo their raw question back as the heading. - No section headers — at this length they'd cost more lines than they buy.
- No diagrams, no analogies, no history.
- Every word earns its place.
- No emoji.
Output format
**[Topic as a short noun phrase]**
[One sentence. What it is or does, in plain language.]
- [First of the two things that matter]
- [Second of the two things that matter]
- **Bottom line:** [direct recommendation or verdict]Pick the two middle bullets from the question
- Definition ("what is X", "explain X briefly") → the two key facts a user needs to not misuse it
- Decision ("should I use X", "X vs Y", "is X worth it") →
Use it when: [≤8 words]/Skip it when: [≤8 words] - State of something ("is X done", "does X do Y") → the two observations that settle it
The bottom line is never optional. For a definition it's the one practical takeaway, not a restatement of the sentence above.
Examples
/tldr JWT
**JWT**
A signed token the client carries so the server can verify who they are without storing a session.
- Use it when: stateless auth across services
- Skip it when: you need instant server-side revocation
- **Bottom line:** use it, keep expiry at 15min/tldr Redis 拿來幹嘛
**Redis**
把讀取頻繁但變動不多的資料放在記憶體裡,避免每次都打 database。
- 讀取延遲從幾十 ms 降到 1ms 以下
- 資料會過期、也可能掉,不能當唯一來源
- **Bottom line:** 當 cache 用,永遠假設它是空的也要能跑Anti-examples
Don't write **一句話解釋 JWT 是什麼意思** as the headline — that's the user's question,
not the topic. It should be **JWT**.
Don't stretch to four bullets because the topic feels rich. If two facts can't carry it, the user asked for the wrong skill — answer at this length anyway.
Don't let the bottom line repeat the opening sentence in different words. It has to tell them what to do.
If no request was supplied, ask: "Quick brief on what?"
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

