self-learning

A skill that researches a library, framework, or other technology on the web and turns the findings into a reusable skill. It uses sources such as official documentation, guides, API references, and repositories.

In plain words
What is it for?
Use it with `/learn <topic>` to study a new technology, clarify an ambiguous topic, collect authoritative sources, and create a reusable skill from the results.
Why use it?
It helps when you need reliable working guidance for technology you do not know yet, instead of researching and documenting it manually.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/philschmid/self-learning-skill/self-learning
Any agent
npx skills add philschmid/self-learning-skill --skill self-learning
Clone the repo
git clone --depth 1 https://github.com/philschmid/self-learning-skill

Made for: Claude Code, Codex.

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 979 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00081 $0.00979
Opus 5 $0.00041 $0.00490
Sonnet 5 $0.00016 $0.00196
Haiku 4.5 $0.00008 $0.00098

Measured 2d ago against content hash d2d9d1d3b2cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

self-learning scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/self-learning/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Learning Skill Generator

Autonomously research and learn new technologies from the web, then generate a reusable skill.

Usage

/learn <topic>

If <topic> is missing, show usage. If topic is ambiguous, ask to clarify:

  • "react" → "React for web, React Native, or a specific library like react-query?"
  • "apollo" → "Apollo GraphQL client, Apollo Server, or Apollo Federation?"
  • "aws" → "Which AWS service? (S3, Lambda, DynamoDB, etc.)"

Normalize to kebab-case for filenames.

2. Discover Sources (Web Search)

Use web search tool to find authoritative documentation:

Search queries to try:

  1. <topic> official documentation
  2. <topic> getting started guide
  3. <topic> API reference
  4. <topic> GitHub repository

Source prioritization:

  1. Official docs sites (e.g., docs.*, *.dev)
  2. Official GitHub repositories (README, /docs)
  3. Official blogs/announcements

Select 3–5 high-quality URLs maximum.

If no credible sources found, ask user to provide a URL.


3. Extract Content (URL Reading)

For each selected URL, read the content:

Extract only relevant sections:

  • Installation / setup
  • Core concepts
  • API reference / key functions
  • Common patterns / examples
  • Version information

Skip irrelevant content:

  • Navigation, ads, login prompts
  • Unrelated sidebar content
  • Comments, forums

If reading the content fails (JavaScript-heavy sites), fall back to browser agent:

Task: Navigate to <URL> and extract the main content including:
- Installation instructions
- Core concepts and API reference
- Code examples
Return the extracted content as markdown.

Record scrape timestamp for each source (use current date: YYYY-MM-DD format).


4. Generate Skill

Skills are modular, self-contained packages. Every skill consists of a required SKILL.md file and optional bundled resources:

skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter metadata (required)
│   │   ├── name: (required)
│   │   └── description: (required)
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/          - Executable code (Python/Bash/etc.)
    ├── references/       - Documentation intended to be loaded into context as needed
    └── assets/           - Files used in output (templates, icons, fonts, etc.)

Read the full file on GitHub · 134 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 134 lines · 81 tokens per session scan A d2d9d1d3b2cf

Subscribe to this mod's changes

self-learning is a skill published in the GitHub repository philschmid/self-learning-skill (93 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 81 tokens to every session and 979 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens