New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Alef

by xberg-io in xberg-io/alef

Use Alef correctly for Rust-to-polyglot binding generation. An agent skill from xberg-io/alef.

MITAuto-check passedDevelopment

Install Alef

skills CLI
$ npx skills add xberg-io/alef --skill alef -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install xberg-io/alef alef --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/xberg-io/alef.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/alef .claude/skills/alef && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
alef
GitHub stars
100
Token cost
~1.7k tokens
SKILL.md length
625 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Use Alef correctly for Rust-to-polyglot binding generation. An agent skill from xberg-io/alef.

  • Works in 6 steps: API reference docs from extracted Rust… → CLI reference docs from configured Clap… → MCP reference docs from configured… → …
  • Configuring alef.toml
  • SKILL.md covers Core Rules, Standard Consumer Workflow, Config Model and Generated Docs, llms.txt, and…, plus 4 more sections
  • Calls cargo, jq and git

What it does

Alef is an agent skill from xberg-io/alef. Use Alef correctly for Rust-to-polyglot binding generation. Trigger when configuring alef.toml, generating bindings, READMEs, API/CLI/MCP docs, llms.txt, agent skills, e2e suites, or debugging stale/missing generated output in Alef-powered repositories. Covers the safe command sequence, config ownership, generated-output rules, snippet validation, downstream smoke testing, and Alef development workflow.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering AI search optimization, Technical documentation and End-to-end testing. It works with Rust and Model Context Protocol. The repository describes itself as: Generate fully-typed, lint-clean language bindings for Rust libraries across 16 languages. The licence is MIT.

When your agent uses it

  • Configuring alef.toml
  • Generating bindings
  • API/CLI/MCP docs
  • Debugging stale/missing generated output in Alef-powered repositories

Example prompts

  • “/alef”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. API reference docs from extracted Rust API.
  2. CLI reference docs from configured Clap sources.
  3. MCP reference docs from configured rmcp-style sources.
  4. Snippet index and configured snippet validation.
  5. Template-rendered llms.txt.
  6. Template-rendered grouped skills.

What it can do on your machine

Read from SKILL.md and the folder at commit fc04366. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • cargo
    • jq
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Alef loads about 1.7k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 625 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~103
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from xberg-io/alef at commit fc04366, republished under its MIT licence (© xberg-io). 625 words, ~1,696 tokens.

Download SKILL.mdSave it as .claude/skills/alef/SKILL.md (or your agent's skills folder).
name
alef
description
Use Alef correctly for Rust-to-polyglot binding generation. Trigger when configuring alef.toml, generating bindings, READMEs, API/CLI/MCP docs, llms.txt, agent skills, e2e suites, or debugging stale/missing generated output in Alef-powered repositories. Covers the safe command sequence, config ownership, generated-output rules, snippet validation, downstream smoke testing, and Alef development workflow.
license
MIT
metadata.author
xberg-io
metadata.version
1.0
metadata.repository
https://github.com/xberg-io/alef

Alef

Alef extracts a Rust public API surface and generates language-native bindings, package scaffolding, type stubs, READMEs, docs, e2e tests, and release metadata from alef.toml.

Use this skill when working in Alef itself or in a downstream repo that uses Alef.

Core Rules

  • Treat Rust source plus alef.toml as the source of truth.
  • Read the local alef.toml before proposing config or generation changes.
  • Do not hand-edit Alef-managed generated files except when adopting an existing file into Alef management.
  • Preserve user changes in dirty worktrees. Stage and commit only the requested scope.
  • Prefer narrow commands while iterating, then run the broader verification command before committing.
  • For user-visible Alef behavior changes, update CHANGELOG.md.

Standard Consumer Workflow

From a repo that uses Alef:

bash
alef generate --format
alef scaffold
alef readme
alef docs
alef verify --exit-code

Use the combined command when a full refresh is expected:

bash
alef all --format

Use filters to keep iteration small:

bash
alef generate --lang python,node
alef docs --output docs/reference
alef test --lang python
alef verify --exit-code

When testing an unreleased local Alef from a sibling repo, run the binary through Cargo instead of using the installed version:

bash
cargo run -q --manifest-path ../alef/Cargo.toml -- docs
cargo run -q --manifest-path ../alef/Cargo.toml -- all --format

Config Model

Current Alef configs use:

  • [workspace] for shared languages, tools, DTO defaults, docs defaults, and pipeline defaults.
  • [[crates]] for each generated package/API surface.
  • [crates.<language>] or [workspace.<language>] for target-specific output, package names, feature flags, excludes, and stubs.
  • source_crates when a facade crate re-exports API from multiple Rust crates.
  • features when cfg-gated public fields/types must be considered present.

Use include for small curated APIs. Use exclude for large APIs where most public items should bind except known internal, generic, trait, or unsupported items.

Generated Docs, llms.txt, and Skills

Alef can generate docs in this order:

  1. API reference docs from extracted Rust API.
  2. CLI reference docs from configured Clap sources.
  3. MCP reference docs from configured rmcp-style sources.
  4. Snippet index and configured snippet validation.
  5. Template-rendered llms.txt.
  6. Template-rendered grouped skills.

Important rules:

  • llms.txt and skills are template-owned. Missing templates are hard errors.
  • Alef should not invent full prose for llms.txt or skills.
  • Existing unmanaged outputs require explicit adopt_existing = true.
  • Generated Markdown keeps frontmatter first, then Alef's managed hash marker.
  • Warn only for actionable skips: missing configured sources, configured extractors discovering nothing, missing configured snippet dirs, or unavailable snippet toolchains.

Common docs config shape:

toml
[workspace.docs]
reference_output = "docs/reference"

[workspace.docs.cli]
sources = ["crates/my-cli/src/main.rs"]

[workspace.docs.mcp]
sources = ["crates/my-lib/src/mcp/server.rs"]

[workspace.docs.llms]
template = "templates/docs/llms.txt.jinja"
output = "docs/llms.txt"
adopt_existing = true

[workspace.docs.skills]
template_dir = "templates/docs/skills"
outputs = [".codex/skills", ".agents/skills", ".claude/skills", ".github/skills"]
adopt_existing = true

[workspace.docs.snippets]
dirs = ["docs/snippets"]
docs_dirs = ["docs"]
required_languages = ["python", "rust"]
validation_level = "syntax"

Skill templates default to grouped api, cli, and mcp skills:

text
templates/docs/skills/
├── api/SKILL.md.jinja
├── cli/SKILL.md.jinja
└── mcp/SKILL.md.jinja
Show full SKILL.md (263 more words)Show less

Snippets

Use snippets as maintained examples, not generated filler. Configure validation instead of silently trusting examples:

  • dirs: snippet roots.
  • docs_dirs: docs/template roots to scan for includes.
  • required_languages: language variants every grouped snippet should have.
  • validation_level: syntax, typecheck, compile, or run.
  • include_base_paths: paths matching MkDocs snippet include roots.

Unreferenced snippets should normally warn, not fail. Missing references, missing required language variants, unknown languages, and skip annotations without reasons should fail.

Debugging

Missing type or function:

bash
alef extract -o /tmp/api.json
jq '.types | keys' /tmp/api.json

Then check:

  • Is the source file listed in sources or source_crates?
  • Is the item public and reachable from the configured source?
  • Is it excluded in config or with an Alef attribute?
  • Does it depend on an unsupported generic, trait object, or external type?
  • Does the target language need an FFI layer (ffi) or explicit type mapping?

Stale output:

bash
alef verify --exit-code
alef diff
alef generate --clean --format

Cache issues:

bash
rm -rf .alef
alef generate --clean --format

Docs generation issues:

  • Confirm template paths are relative to the workspace root.
  • Confirm configured CLI/MCP source paths exist.
  • Confirm generated outputs have Alef headers or adopt_existing = true.
  • Use -v/RUST_LOG when a warning is expected but not visible.

Working on Alef Itself

In the Alef repo, prefer focused checks while iterating:

bash
cargo fmt
cargo check -q
cargo test -q docs:: -- --nocapture
cargo test -q <module_or_test_name>

Before committing behavior changes, run the highest-signal relevant tests. For docs/template work, also smoke test downstream repos with the local binary:

bash
cargo run -q --manifest-path ../alef/Cargo.toml -- docs
git diff --check

Use the sibling repos that exercise Alef broadly:

  • ../crawlberg
  • ../html-to-markdown
  • ../liter-llm
  • ../tree-sitter-language-pack

Do not include ../xberg unless explicitly asked.

Release Notes and Commits

  • Update CHANGELOG.md under [Unreleased] for user-visible changes.
  • Keep release commits separate from feature/fix commits.
  • Do not add AI attribution to commits, tags, or release notes.
  • Use the existing release procedure skill when cutting a version.

© xberg-io, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/alef of xberg-io/alef.

Open the folder on GitHubat commit fc04366

Compare with similar skills

Alef next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Alef compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Alef this skillxberg-io/alef100—~1.7kAutomated safety check: PassMIT
Translate It Doc En Zhmxsm/rocketmq-rust1.5k—~1.2kAutomated safety check: PassApache-2.0
Rust Doc Comment Generatormxsm/rocketmq-rust1.5k—~1.1kAutomated safety check: PassApache-2.0
SlintMoosync/Moosync259—~2.4kAutomated safety check: PassGPL-3.0
Memorywhale Debuggingwuisabel-gif/MemWhale154—~370Automated safety check: PassMIT
Embedded DebuggerAdancurusul/embedded-debugger-mcp202—~1.4kAutomated safety check: PassMIT

Similar skills

  • Translate It Doc En Zh

    mxsm/rocketmq-rust

    Translate English IT and software engineering documents into professional, accurate Chinese.

    1.5k GitHub stars~1.2k tokensUpdated today
    DevelopmentAuto-check passed

  • Rust Doc Comment Generator

    mxsm/rocketmq-rust

    Generate idiomatic, production-grade Rust comments and documentation strictly following official Rustdoc and Rust API documentation conventions.

    1.5k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed

  • Slint

    Moosync/Moosync

    Expert guidance for building, debugging, and working with Slint GUI applications.

    259 GitHub stars~2.4k tokensUpdated 8 days ago
    DevelopmentAuto-check passed

  • Memorywhale Debugging

    wuisabel-gif/MemWhale

    MemoryWhale debugging; compiler failures; terminal diagnostics.

    154 GitHub stars~370 tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Embedded Debugger

    Adancurusul/embedded-debugger-mcp

    Embedded hardware debugging workflow for probe-rs targets using embedded-debugger-mcp.

    202 GitHub stars~1.4k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • Memorywhale

    wuisabel-gif/MemWhale

    Query and write durable debugging memory recorded by MemoryWhale.

    154 GitHub stars~765 tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

More from xberg-io/alef

  • Binding Audit

    xberg-io/alef

    Audit bindings for coverage gaps — verify every public Rust item is exposed across all generated language bindings.

    100 GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • Jinja Codegen

    xberg-io/alef

    Mechanics of alef's Minijinja template system: which templateenv module to call, how to register a template, inline-template rules, and engine settings.

    100 GitHub stars~735 tokensUpdated today
    Auto-check passed

  • Regen Audit

    xberg-io/alef

    Treat running alef generate/alef all/alef verify in a consumer repo as an audit, not a build step.

    100 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Release Procedure

    xberg-io/alef

    Cut, tag, and publish an alef release end-to-end. An agent skill from xberg-io/alef.

    100 GitHub stars~3k tokensUpdated today
    Auto-check passed

  • Two Generators Disagree

    xberg-io/alef

    Alef's dominant defect shape: two components read the same config or IR and act on it differently.

    100 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Alef

What does Alef do?

Use Alef correctly for Rust-to-polyglot binding generation. An agent skill from xberg-io/alef. Alef is an agent skill from xberg-io/alef. Use Alef correctly for Rust-to-polyglot binding generation.

When should I use Alef?

Alef fits situations like: configuring alef.toml; generating bindings; API/CLI/MCP docs; debugging stale/missing generated output in Alef-powered repositories.

How do I install Alef in Claude Code?

Run `npx skills add xberg-io/alef --skill alef -a claude-code`. Or copy the skill folder (skills/alef in xberg-io/alef) into .claude/skills/alef in your project. Claude Code loads it when a task matches its description.

How do I install Alef in Codex?

Run `npx skills add xberg-io/alef --skill alef -a codex`. Or copy the skill folder (skills/alef in xberg-io/alef) into .agents/skills/alef in your project. Codex loads it when a task matches its description.

Can I use Alef in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xberg-io/alef --skill alef -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/alef, .gemini/skills/alef, .github/skills/alef and .opencode/skills/alef in your project.

What does Alef need to run?

Going by SKILL.md and its folder, Alef needs the command-line tools its instructions call (cargo, jq and git). Our summary lists: Python 3.

Does Alef access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Alef safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Alef use?

Alef is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Alef use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Alef?

Skills that share tags, products or a category with Alef: Translate It Doc En Zh (mxsm/rocketmq-rust, 1.5k stars), Rust Doc Comment Generator (mxsm/rocketmq-rust, 1.5k stars), Slint (Moosync/Moosync, 259 stars) and Memorywhale Debugging (wuisabel-gif/MemWhale, 154 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Alef?

xberg-io (a GitHub organization) maintains it in xberg-io/alef, which has 100 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 9, 2026.

Source: xberg-io/alef on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.