Agent skill

API Exploration

by sozercan in sozercan/kaset

A skill your agent uses when a task needs a new or modified YouTube Music API call, response parser validation, authenticated endpoint investigation, or fixture capture; explore endpoints with swift…

MITAuto-check passedMobile

Install API Exploration

skills CLI
$ npx skills add sozercan/kaset --skill api-exploration -a claude-code

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

GitHub CLI
$ gh skill install sozercan/kaset api-exploration --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/sozercan/kaset.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/api-exploration .claude/skills/api-exploration && 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
api-exploration
GitHub stars
2.4k
Token cost
~454 tokens
SKILL.md length
148 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when a task needs a new or modified YouTube Music API call, response parser validation, authenticated endpoint investigation, or fixture capture; explore endpoints with swift…

  • Works in 5 steps: Start with swift run api-explorer auth… → Check what already exists with swift run… → Probe the endpoint with browse, action,… → …
  • A task needs a new
  • SKILL.md covers Guardrails, Workflow, Common Commands and Landmarks
  • Calls swift

What it does

API Exploration is an agent skill from sozercan/kaset. Use when a task needs a new or modified YouTube Music API call, response parser validation, authenticated endpoint investigation, or fixture capture; explore endpoints with swift run api-explorer before changing production code.

Its SKILL.md is about 450 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 Mobile, covering iOS development. It works with YouTube and macOS. The repository describes itself as: 📼 The missing YouTube and YouTube Music macOS app. The licence is MIT.

When your agent uses it

  • A task needs a new
  • Modified YouTube Music API call
  • Response parser validation
  • Authenticated endpoint investigation

Example prompts

  • “/api-exploration”

Workflow steps

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

  1. Start with swift run api-explorer auth if the task touches sign-in-backed endpoints.
  2. Check what already exists with swift run api-explorer list.
  3. Probe the endpoint with browse, action, or continuation before touching production code.
  4. Save representative payloads with -o when parser work or regression tests need fixtures.
  5. Update docs/api-discovery.md if you confirm a new endpoint, parameter, or auth constraint.

What it can do on your machine

Read from SKILL.md and the folder at commit 4b74e9f. 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:

    • swift

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

  • Network

    No URLs in SKILL.md.

    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

API Exploration loads about 454 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 148 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~454

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 sozercan/kaset at commit 4b74e9f, republished under its MIT licence (© sozercan). 148 words, ~454 tokens.

Download SKILL.mdSave it as .claude/skills/api-exploration/SKILL.md (or your agent's skills folder).
name
api-exploration
description
Use when a task needs a new or modified YouTube Music API call, response parser validation, authenticated endpoint investigation, or fixture capture; explore endpoints with `swift run api-explorer` before changing production code.
metadata.short-description
Explore YouTube Music APIs

API Exploration

Use this skill when a task needs a new or modified YouTube Music API call, response parser validation, authenticated endpoint investigation, or fixture capture.

Guardrails

  • Always enhance Sources/APIExplorer/main.swift; do not write one-off scripts for endpoint exploration.
  • Never commit real cookies, SAPISID values, tokens, or account identifiers. Redact anything sensitive in notes, fixtures, and examples.
  • Prefer API endpoints over WebView whenever the functionality already exists in YTMusicClient.

Workflow

  1. Start with swift run api-explorer auth if the task touches sign-in-backed endpoints.
  2. Check what already exists with swift run api-explorer list.
  3. Probe the endpoint with browse, action, or continuation before touching production code.
  4. Save representative payloads with -o when parser work or regression tests need fixtures.
  5. Update docs/api-discovery.md if you confirm a new endpoint, parameter, or auth constraint.

Common Commands

bash
swift run api-explorer auth
swift run api-explorer list
swift run api-explorer browse FEmusic_home -v
swift run api-explorer browse FEmusic_liked_playlists -v
swift run api-explorer action search '{"query":"never gonna give you up"}'

Landmarks

  • Sources/APIExplorer/main.swift
  • docs/api-discovery.md
  • Tests/KasetTests/Fixtures/

Authenticated exploration reads the debug cookie export from ~/Library/Application Support/Kaset/cookies.dat.

© sozercan, 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 .agents/skills/api-exploration of sozercan/kaset.

Open the folder on GitHubat commit 4b74e9f

Compare with similar skills

API Exploration 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.

API Exploration compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
API Exploration this skillsozercan/kaset2.4k—~454Automated safety check: PassMIT
Hig Project Contextraintree-technology/hig-doctor1425 repos~1.2kAutomated safety check: PassMIT
Hig Components Contentraintree-technology/hig-doctor1425 repos~1.3kAutomated safety check: PassMIT
macOS Auto Updatefayazara/macos-app-skills672—~1.8kAutomated safety check: PassNone
App ItChristian-Katzmann/app-it216—~2.4kAutomated safety check: PassMIT
Hig Components Dialogsraintree-technology/hig-doctor1425 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Hig Project Context

    raintree-technology/hig-doctor

    Create or update a shared Apple design context document that other HIG skills use to tailor guidance.

    142 GitHub starsUsed in 5 repos~1.2k tokens
    MobileAuto-check passed
  • Hig Components Content

    raintree-technology/hig-doctor

    Apple Human Interface Guidelines for content display components.

    142 GitHub starsUsed in 5 repos~1.3k tokens
    MobileAuto-check passed
  • macOS Auto Update

    fayazara/macos-app-skills

    Add Sparkle auto-update support to a native macOS app. An agent skill from fayazara/macos-app-skills.

    672 GitHub stars~1.8k tokensUpdated 4 mo ago
    MobileAuto-check passed
  • App It

    Christian-Katzmann/app-it

    Turn a local project or a hosted web app (including a published Claude Artifact URL) into a macOS Dock-launchable .app.

    216 GitHub stars~2.4k tokensUpdated 7 days ago
    MobileAuto-check passed
  • Hig Components Dialogs

    raintree-technology/hig-doctor

    Apple HIG guidance for presentation components including alerts, action sheets, popovers, sheets, and digit entry views.

    142 GitHub starsUsed in 5 repos~1.1k tokens
    MobileAuto-check passed
  • Hig Components Menus

    raintree-technology/hig-doctor

    Apple HIG guidance for menu and button components including menus, context menus, dock menus, edit menus, the menu bar, toolbars, action buttons, pop-up buttons, pull-down buttons, disclosure…

    142 GitHub starsUsed in 5 repos~1.1k tokens
    MobileAuto-check passed

More from sozercan/kaset

  • Autoreview

    sozercan/kaset

    Run a structured code review (Codex default, Claude optional) as a closeout check on a local or PR branch before commit or ship.

    2.4k GitHub stars~3k tokensUpdated 4 days ago
    Auto-check passed
  • Dev Loop Packaging

    sozercan/kaset

    A skill your agent uses when you need a fresh packaged .app bundle, a fast build-package-relaunch loop, or a packaged runtime repro for Kaset instead of a compile-only verification.

    2.4k GitHub stars~388 tokensUpdated 4 days ago
    Auto-check passed
  • A skill your agent uses when playback, auth recovery, queue sync, or hidden WebView state diverges from native Swift state and you need to debug the DRM playback WebView, bridge events, or…

    2.4k GitHub stars~480 tokensUpdated 4 days ago
    Auto-check passed

Works with

Categories

Questions about API Exploration

What does API Exploration do?

A skill your agent uses when a task needs a new or modified YouTube Music API call, response parser validation, authenticated endpoint investigation, or fixture capture; explore endpoints with swift…. API Exploration is an agent skill from sozercan/kaset. Use when a task needs a new or modified YouTube Music API call, response parser validation, authenticated endpoint investigation, or fixture capture; explore endpoints with swift run api-explorer before changing production code.

When should I use API Exploration?

API Exploration fits situations like: A task needs a new; modified YouTube Music API call; response parser validation; authenticated endpoint investigation.

How do I install API Exploration in Claude Code?

Run `npx skills add sozercan/kaset --skill api-exploration -a claude-code`. Or copy the skill folder (.agents/skills/api-exploration in sozercan/kaset) into .claude/skills/api-exploration in your project. Claude Code loads it when a task matches its description.

How do I install API Exploration in Codex?

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

Can I use API Exploration 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 sozercan/kaset --skill api-exploration -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/api-exploration, .gemini/skills/api-exploration, .github/skills/api-exploration and .opencode/skills/api-exploration in your project.

What does API Exploration need to run?

Going by SKILL.md and its folder, API Exploration needs the command-line tools its instructions call (swift).

Does API Exploration access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is API Exploration 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 API Exploration use?

API Exploration is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does API Exploration use?

About 454 tokens (SKILL.md is roughly 1.8k 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 API Exploration?

Skills that share tags, products or a category with API Exploration: Hig Project Context (raintree-technology/hig-doctor, 142 stars), Hig Components Content (raintree-technology/hig-doctor, 142 stars), macOS Auto Update (fayazara/macos-app-skills, 672 stars) and App It (Christian-Katzmann/app-it, 216 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains API Exploration?

sozercan (a GitHub user) maintains it in sozercan/kaset, which has 2,356 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 3, 2026.

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