agentleFS
Boxline-devBoxline-dev/examples/skills/learn/SKILL.md

learn

Skill1 starsChanged 35 days agoMITView on GitHub

Learn a library, framework or API from its current official docs and save it as a Claude Code skill (.claude/skills/<topic>/SKILL.md), so later work uses today's APIs instead of stale training data. Searches and reads the docs with Boxline. Usage /learn <topic>, /learn batch <topic> <topic> …, add --global for ~/.claude/skills.

  • Reads credentials

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-anydoc, add-clidash and 10 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.
  • TomGranotSkill

    add-anydoc

    Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.

    Also in 5 projects that use this

  • TomGranotSkill

    add-clidash

    Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.

    Also in 5 projects that use this

  • seek888Skill

    open-gstack-browser

    Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".

    Also in 11 projects that use this

  • Saqlain-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 6 projects that use this

  • MicrosoftSkill

    add-codex

    Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).

    Also in 6 projects that use this

  • MicrosoftSkill

    add-deltachat

    Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.

    Also in 6 projects that use this

  • +5 more from TomGranot
  • +1 more from microsoft

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 2

    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:

    Search for a topic's official documentation, read it in a real browser (Boxline), and write a skill from it.

    line 8
  2. Distinctive:

    Only what the sources say.

    line 77

“Common” is measured: kept by at least 6 in 10 of the 170 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

/learn: a skill from today's docs

Search for a topic's official documentation, read it in a real browser (Boxline), and write a skill from it.

Usage

  • /learn <topic>: one topic, read in depth (3 to 5 pages).
  • /learn batch <topic> <topic> …: several topics, quickly (2 pages each).
  • --global: save to ~/.claude/skills/ instead of the project's .claude/skills/.

Without a topic, show the usage with examples (/learn hono, /learn batch zod drizzle-orm) and stop. Topic names become kebab-case folder names.

Boxline tools

  • The Boxline MCP server: web_search (with fetch for the top pages as Markdown), web_fetch.
  • Or the CLI (BOXLINE_API_KEY set, or npx @boxline/cli login):

    npx @boxline/cli search "<topic> official documentation" --limit 8 --json
    npx @boxline/cli search "<topic> official documentation getting started" --limit 5 --fetch 2 --json   # results and pages in one call
    npx @boxline/cli fetch <url>                                                                         # Markdown

Steps

  1. Find the sources. One search per topic: <topic> official documentation; one more for the API reference when the first finds none. Prefer the official docs site, then the official GitHub repository (README, docs folder), then official announcements. Skip tutorials, aggregators, forums and Q&A sites. Pick 3 to 5 pages (batch: 2). With none credible, ask the user for a URL.
  2. Read them. Fetch each as Markdown. Skip a page over 80,000 characters or one that fails; do not retry. Note each page's date read. Keep: installation, core concepts, the main APIs with signatures, common patterns with code, version notes, warnings.
  3. Write the skill. In the format below; under 300 lines (batch: 200). Imperative ("Use X to …"). Version numbers when the docs give them. Where sources disagree, say so.
  4. Save it to .claude/skills/<topic>/SKILL.md (or ~/.claude/skills/… with --global). If it exists, say so and ask before replacing it.
  5. Report: the skill's name, the sources read, where it was saved. In batch mode one line per topic, then N/M skills written.

Format

---
name: <topic-in-kebab-case>
description: <What it is and when to use this skill, with the words that should trigger it. At most 1024 characters.>
---

# <Topic>

<What it is and when to use it: 1 to 3 sentences. Version: …>

## Quick start
<Install and the smallest working example>

## Core concepts

## Common patterns
<Short code examples>

## API reference
<The main functions, methods or endpoints, with signatures> (skip in batch mode: link the reference instead)

## Gotchas

## Sources
- <url> (read <YYYY-MM-DD>)

Rules

  • Only what the sources say. Never invent an API, option or behavior; a gap is a gap.
  • name: lowercase letters, digits and hyphens, at most 64 characters.
  • Public documentation only; no pages behind a sign-in.
  • No emojis.

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.

Reviews can't be read right now.

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.