agentleFS
LaansDoleLaansDole/my-hermes-skills/skills/productivity/tldr/SKILL.md

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

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.
  • sunnyclinches44Skill

    explain

    Explains code using real-world analogies and ASCII diagrams

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 6 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 3 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 3 projects that use this

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
  1. Distinctive:

    If nothing changed (e.g. "no action taken"), say so in the TL;DR line and skip the table.

    line 30

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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)

  1. One-line TL;DR — the whole thing in a single sentence: what was done, on what, end state.
  2. 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.
  3. 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.

AspectBEFOREAFTER
Upload pathApp -> GCS -> backend file_idApp POSTs multipart straight to backend
API5 old endpoints/recordings CRUD contract
Tests197 unit229 unit + e2e integration
Securitypath traversal + arbitrary writeallowlist + containment (review-verified)
Remotenothing pushedboth 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.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.