tldr
Skill3 starsChanged 10 days agoMITView on GitHub
Use when the user says tldr / TL;DR or asks for a before/after summary.
39 other projects use a version of this.
Adopted by
Most recently taken up by
- richkuo/rk-skillstheir own version, first seen Nov 14, 2026
- 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
- beCyborg/jadlis-tldrtheir own version, first seen Nov 6, 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 versions39 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 39
- earlyaidopters/second-brain★ 193same name
- saksham10arora-dotcom/everything-claude-codex★ 96same 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
- zazencodes/skills★ 15same name
- SurefireStudios/tldr★ 9same name
29 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 repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- covidence-full-text-reviewSkill
- covidence-full-text-retrievalSkill
- covidence-screeningSkill
- impeccableSkill
- ilearning-autoadvanceSkill
- oh-my-piSkill
- auditing-worktreesSkill
- camofox-browserSkill
- demo-runbookSkill
- hermes-deepseek-cacheSkill
- i-have-adhdSkill
- memory-uiSkill
- multi-repo-pr-review-merge-roundSkill
- oh-my-ghosttySkill
- writing-reportsSkill
- sci-hub-accessSkill
- slack-mention-watchSkill
- slack-scanSkill
- superpowers-using-superpowersSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 34 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
If nothing changed (e.g. "no action taken"), say so in the TL;DR line and skip the table.
“Common” is measured: kept by at least 6 in 10 of the 34 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 — Structured Summary with Before/After Table
When the user asks "TL;DR", "summarize what you did", "what changed", "recap", or "before/after" — deliver a SCANNABLE structured summary, never a wall of prose. The user's baseline complaint (observed): TL;DRs came out as long text dumps; what they want is a compact summary plus a side-by-side comparison table.
Format (follow exactly)
- One-line TL;DR — the whole thing in a single sentence: what was done, on what, end state.
- Before/After table — one row per meaningful axis of change. Columns:
| Aspect | BEFORE | AFTER |. Use concrete facts (endpoint names, test counts, branch SHAs), not vague labels. Rows: 6-12 for a multi-part task; 2-4 for a small change. Column-aligned (padded) pipe table — required. The terminal doesn't render markdown, so pad every cell with spaces to its column's widest value, and make each dash run in the separator row span the full padded cell (cell width + 2). Every row must have the same total length. When cells are long, build the table in code (max width per column,ljust) instead of by eye. - Open items / follow-ups (only if non-empty) — short bullet list of what's still pending, so the reader knows the edge.
Rules
- CONCISE: the user rejects long dumps. If the TL;DR + table exceeds ~40 lines, it's too long — cut rows, merge axes.
- Concrete over generic: "POST /recordings, GET /recordings/{id}" beats "new API endpoints". "229 tests pass (was 197)" beats "tests pass".
- Facts only: never invent numbers or states; if you didn't verify it, omit or mark it (e.g. "not verified on device").
- Terminal-friendly: plain text, pipe-table or aligned columns; no heavy markdown nesting, no MEDIA: tags.
- Security/breaking changes get their own row or a bolded line — those matter most to the reader.
- If nothing changed (e.g. "no action taken"), say so in the TL;DR line and skip the table.
Example (shape)
TL;DR: Closed the mobile-app gap — defined one API contract, implemented it on both ends, code-reviewed, fixed 3 security holes, pushed both branches.
| Aspect | BEFORE | AFTER |
| Upload path | App -> GCS -> backend file_id | App POSTs multipart straight to backend |
| API | 5 old endpoints | /recordings CRUD contract |
| Tests | 197 unit | 229 unit + e2e integration |
| Security | path traversal + arbitrary write | allowlist + containment (review-verified) |
| Remote | nothing pushed | both feature branches pushed |
Open: HF_TOKEN for gated models; device UI verification (no Android SDK on this Mac).
Common Mistakes
- Prose dump — exactly what the user rejected. If you catch yourself writing paragraphs, restructure into the table.
- Unaligned table —
|---|---|---|separators and unpadded cells look ragged in a terminal. Always pad to column width. - Too many rows — every row must be a real axis of change; merge cosmetic rows.
- Vague cells — "improved", "fixed stuff", "better" are forbidden; state what concretely.
- Inventing verification — a test count or SHA you didn't confirm goes in the table only if actually run/verified.
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.

