Agent skill

Feature Overview

by skybrush-io in skybrush-io/live

Write concise architecture overview documents for features. An agent skill from skybrush-io/live.

GPL-3.0Auto-check passed

Install Feature Overview

skills CLI
$ npx skills add skybrush-io/live --skill feature-overview -a claude-code

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

GitHub CLI
$ gh skill install skybrush-io/live feature-overview --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/skybrush-io/live.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/feature-overview .claude/skills/feature-overview && 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
feature-overview
GitHub stars
122
Token cost
~704 tokens
SKILL.md length
369 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
GPL-3.0

At a glance

Write concise architecture overview documents for features. An agent skill from skybrush-io/live.

  • Works in 4 steps: Study the actual implementation — diffs,… → Ask the user clarifying questions. Don't… → Once you and the user have a shared… → …
  • Updating docs about feature structure
  • SKILL.md covers When to create one, File, Purpose and Content rules, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Feature Overview is an agent skill from skybrush-io/live. Write concise architecture overview documents for features. Use when creating or updating docs about feature structure, design rationale, extension points for agents and humans

Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: An open-source drone show and drone swarm ground control station GUI frontend. The licence is GPL-3.0.

When your agent uses it

  • Updating docs about feature structure
  • Design rationale
  • Extension points for agents and humans

Example prompts

  • “/feature-overview”

Workflow steps

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

  1. Study the actual implementation — diffs, current code, how things are wired. Understand the feature thoroughly before writing.
  2. Ask the user clarifying questions. Don't assume; don't guess. The user knows what the feature does and why decisions were made.
  3. Once you and the user have a shared understanding, write the overview.
  4. Trim aggressively. Every sentence must earn its place.

What it can do on your machine

Read from SKILL.md and the folder at commit e104a06. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Feature Overview loads about 704 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 369 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~704

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 skybrush-io/live at commit e104a06, republished under its GPL-3.0 licence (© skybrush-io). 369 words, ~704 tokens.

Download SKILL.mdSave it as .claude/skills/feature-overview/SKILL.md (or your agent's skills folder).
name
feature-overview
description
Write concise architecture overview documents for features. Use when creating or updating docs about feature structure, design rationale, extension points for agents and humans

Feature overview documents

When to create one

When a feature spans multiple files and has non-obvious design decisions, relationships, or invariants that an agent working on related changes would need to understand but cannot easily discover by reading a single file

File

.agents/docs/<feature-slug>/overview.md

Purpose

Give agents the mental model — structure, relationships, rationale, invariants

Not a catalog of what each file contains

The goal is to save context and time: an agent reads this, then knows where to look and what to watch for

Content rules

Include
  • Purpose — what problem the feature solves. One paragraph.
  • Architecture at a glance — layers, components, their relationships. What depends on what. What knows about what.
  • Key abstractions — concepts that span files, described in terms of their role and interactions, not their implementation.
  • Design decisions and rationale — especially non-obvious ones: why two backends, why state lives outside Redux, why broadcast is deliberately unsupported on a path, etc.
  • Invariants and gotchas — constraints that must hold (e.g. "resume callbacks must never enter Redux", "this slice is not persisted"). Things agents could break if they don't know.
  • Extension points — patterns for adding new variants of the thing (new task type, new mass op, etc.). Brief, not tutorial.
  • Deliberate gaps — what was intentionally left out and why (no cancellation, no persistence).
Show full SKILL.md (158 more words)Show less
Exclude
  • Implementation details discoverable by reading one file (how a key is constructed, what a function returns)
  • Copy-pasted code snippets
  • File indexes / directory listings
  • Consumer/UI component lists (unless a specific integration point is architecturally significant)
  • Anything an agent can find with a quick grep or by reading the file referenced
Style
  • Dense, no filler, ~80 lines is a good target
  • Inline file references with concepts (e.g. "the active-operations Map in actions/uav-test.ts") — agents shouldn't need to search for the file
  • Tables only for comparing alternatives or backends
  • Headings for navigation, not hierarchy for its own sake

Process

  1. Study the actual implementation — diffs, current code, how things are wired. Understand the feature thoroughly before writing.
  2. Ask the user clarifying questions. Don't assume; don't guess. The user knows what the feature does and why decisions were made.
  3. Once you and the user have a shared understanding, write the overview.
  4. Trim aggressively. Every sentence must earn its place.

© skybrush-io, GPL-3.0. 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/feature-overview of skybrush-io/live.

Open the folder on GitHubat commit e104a06

Compare with similar skills

Feature Overview 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.

Feature Overview compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Feature Overview this skillskybrush-io/live122—~704Automated safety check: PassGPL-3.0
Overviewonsi/gomega2.4k—~1.1kAutomated safety check: PassMIT
Concise Planningdavila7/claude-code-templates32k8 repos~328Automated safety check: PassMIT
Overviewaiblueprinthq/ai-blueprint463—~3.8kAutomated safety check: PassMIT
Tldr Overviewparcadei/Continuous-Claude-v33.9k1 repos~470Automated safety check: PassMIT
Room OverviewNxcoreAI/EverRoom3k—~375Automated safety check: PassCustom licence

Similar skills

  • Overview

    onsi/gomega

    The Gomega mental model for writing assertions in Go — the Expect/Ω notation, matchers-are-values, the multi-return error idiom, synchronous vs asynchronous (Eventually/Consistently) assertions, and…

    2.4k GitHub stars~1.1k tokensUpdated 14 days ago
    DevelopmentAuto-check passed
  • Concise Planning

    davila7/claude-code-templates

    A skill your agent uses when a user asks for a plan for a coding task, to generate a clear, actionable, and atomic checklist.

    32k GitHub starsUsed in 8 repos~328 tokens
    Auto-check passed
  • Overview

    aiblueprinthq/ai-blueprint

    Validate and normalize project-plan.md and build-plan.md, then generate the durable project-overview.md used by agents.

    463 GitHub stars~3.8k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Tldr Overview

    parcadei/Continuous-Claude-v3

    Get a token-efficient overview of any project using the TLDR stack

    3.9k GitHub starsUsed in 1 repo~470 tokens
    Writing & ContentAuto-check passed
  • Room Overview

    NxcoreAI/EverRoom

    Generate a source-grounded Context Room overview from Room facts and applied user corrections.

    3k GitHub stars~375 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Writing Clearly And Concisely

    JanDeDobbeleer/oh-my-posh

    Apply whenever writing content a human will read — emails, documents, reports, documentation, messages, UI copy, commit messages, explanations, or any other prose.

    24k GitHub stars~1k tokensUpdated today
    DevelopmentAuto-check passed

More from skybrush-io/live

  • Changelog

    skybrush-io/live

    Update the changelog from recent changes. An agent skill from skybrush-io/live.

    122 GitHub stars~341 tokensUpdated yesterday
    Auto-check passed
  • What Went Wrong

    skybrush-io/live

    Diagnose what went wrong in the session, why it was inefficient, or where the session derailed

    122 GitHub stars~282 tokensUpdated yesterday
    Auto-check passed
  • Learn

    skybrush-io/live

    Reflect on user corrections and propose AGENTS.md or skill updates

    122 GitHub stars~107 tokensUpdated yesterday
    Auto-check passed

Questions about Feature Overview

What does Feature Overview do?

Write concise architecture overview documents for features. An agent skill from skybrush-io/live. Feature Overview is an agent skill from skybrush-io/live. Write concise architecture overview documents for features.

When should I use Feature Overview?

Feature Overview fits situations like: updating docs about feature structure; design rationale; extension points for agents and humans.

How do I install Feature Overview in Claude Code?

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

How do I install Feature Overview in Codex?

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

Can I use Feature Overview 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 skybrush-io/live --skill feature-overview -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/feature-overview, .gemini/skills/feature-overview, .github/skills/feature-overview and .opencode/skills/feature-overview in your project.

What does Feature Overview need to run?

SKILL.md names no scripts, command-line tools or credentials: Feature Overview is instructions for the agent only.

Does Feature Overview 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 Feature Overview 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 Feature Overview use?

Feature Overview is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Feature Overview use?

About 704 tokens (SKILL.md is roughly 2.8k 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 Feature Overview?

Skills that share tags, products or a category with Feature Overview: Overview (onsi/gomega, 2.4k stars), Concise Planning (davila7/claude-code-templates, 32k stars), Overview (aiblueprinthq/ai-blueprint, 463 stars) and Tldr Overview (parcadei/Continuous-Claude-v3, 3.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Feature Overview?

skybrush-io (a GitHub organization) maintains it in skybrush-io/live, which has 122 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 8, 2026.

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