Agent skill

Explain Codebase Concept

Onboard to how one Ahentic concept, feature, or subsystem is wired — chat summary plus visual HTML walkthrough (optional durable copy under docs/walkthroughs/).

GPL-3.0Auto-check passed

Install Explain Codebase Concept

skills CLI

$ npx skills add gambitph/Stackable --skill explain-codebase-concept -a claude-code

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

GitHub CLI

$ gh skill install gambitph/Stackable explain-codebase-concept --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/gambitph/Stackable.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/explain-codebase-concept .claude/skills/explain-codebase-concept && 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/

Paste into Claude Code

Install the "explain-codebase-concept" agent skill from https://github.com/gambitph/Stackable/tree/develop/.cursor/skills/explain-codebase-concept into .claude/skills/explain-codebase-concept/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explain-codebase-concept", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/gambitph/Stackable/tree/develop/.cursor/skills/explain-codebase-concept

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add gambitph/Stackable --skill explain-codebase-concept -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install gambitph/Stackable explain-codebase-concept --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/gambitph/Stackable.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.cursor/skills/explain-codebase-concept .agents/skills/explain-codebase-concept && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "explain-codebase-concept" agent skill from https://github.com/gambitph/Stackable/tree/develop/.cursor/skills/explain-codebase-concept into .agents/skills/explain-codebase-concept/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explain-codebase-concept", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add gambitph/Stackable --skill explain-codebase-concept -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install gambitph/Stackable explain-codebase-concept --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/gambitph/Stackable.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.cursor/skills/explain-codebase-concept .cursor/skills/explain-codebase-concept && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "explain-codebase-concept" agent skill from https://github.com/gambitph/Stackable/tree/develop/.cursor/skills/explain-codebase-concept into .cursor/skills/explain-codebase-concept/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explain-codebase-concept", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/gambitph/Stackable.git --path .cursor/skills/explain-codebase-concept

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add gambitph/Stackable --skill explain-codebase-concept -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install gambitph/Stackable explain-codebase-concept --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/gambitph/Stackable.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.cursor/skills/explain-codebase-concept .gemini/skills/explain-codebase-concept && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "explain-codebase-concept" agent skill from https://github.com/gambitph/Stackable/tree/develop/.cursor/skills/explain-codebase-concept into .gemini/skills/explain-codebase-concept/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explain-codebase-concept", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install gambitph/Stackable explain-codebase-concept

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add gambitph/Stackable --skill explain-codebase-concept -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/gambitph/Stackable.git skills-src && mkdir -p .github/skills && cp -r skills-src/.cursor/skills/explain-codebase-concept .github/skills/explain-codebase-concept && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "explain-codebase-concept" agent skill from https://github.com/gambitph/Stackable/tree/develop/.cursor/skills/explain-codebase-concept into .github/skills/explain-codebase-concept/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explain-codebase-concept", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add gambitph/Stackable --skill explain-codebase-concept -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install gambitph/Stackable explain-codebase-concept --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/gambitph/Stackable.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.cursor/skills/explain-codebase-concept .opencode/skills/explain-codebase-concept && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "explain-codebase-concept" agent skill from https://github.com/gambitph/Stackable/tree/develop/.cursor/skills/explain-codebase-concept into .opencode/skills/explain-codebase-concept/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "explain-codebase-concept", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: explain-codebase-concept
GitHub stars: 350
Token cost: ~1.4k tokens
SKILL.md length: 702 words
Files: 3
Skills in repo: 18
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: GPL-3.0

At a glance

Onboard to how one Ahentic concept, feature, or subsystem is wired — chat summary plus visual HTML walkthrough (optional durable copy under docs/walkthroughs/).

Works in 5 steps: Scope → Explore → Write the HTML walkthrough → …
SKILL.md covers Process and Collision guard
Calls git

What it does

Explain Codebase Concept is an agent skill from gambitph/Stackable. Onboard to how one Ahentic concept, feature, or subsystem is wired — chat summary plus visual HTML walkthrough (optional durable copy under docs/walkthroughs/).

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `HTML-REPORT.md` and `agents/openai.yaml`).

The repository describes itself as: Page Builder Blocks for WordPress. An Amazing Block Library for the new WordPress Block Editor (Gutenberg). The licence is GPL-3.0.

Example prompts

“/explain-codebase-concept”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Scope
Explore
Write the HTML walkthrough
Chat handoff
Durable docs (optional)

What it can do on your machine

Read from SKILL.md and the folder at commit 5c13d80. 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:
- 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

Explain Codebase Concept loads about 1.4k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 702 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~46
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

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 gambitph/Stackable at commit 5c13d80, republished under its GPL-3.0 licence (© gambitph). 702 words, ~1,369 tokens.

Download SKILL.mdSave it as .claude/skills/explain-codebase-concept/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.

name: explain-codebase-concept
description: Onboard to how one Ahentic concept, feature, or subsystem is wired — chat summary plus visual HTML walkthrough (optional durable copy under docs/walkthroughs/).
disable-model-invocation: true

Explain Codebase Concept

Onboard a repo / Ahentic beginner (stack-literate: WP/JS assumed) to one concept, feature, or subsystem so they can contribute — extend, fix bugs, or add related behavior — without inventing a second architecture doc.

Deliverables (every run): chat summary and a self-contained HTML walkthrough (Tailwind + Mermaid).
Authority: compose and cite the doc ladder + live code. PRD / CONTRACT win on disagreement. Flag drift; offer doc fixes — do not auto-write product law.
Not this skill: deepening/refactor candidates (improve-codebase-architecture), bug hunts (diagnosing-bugs), or a whole-product tour (point at docs/architecture.md and offer a menu of slices).

See HTML-REPORT.md for the report scaffold and section rules. Human index: docs/agents/explain-concept.md.

Process

1. Scope

Done when: one coherent slice is named in a single sentence (concept / flow / subsystem), or the user picked from a short menu.

If the ask maps cleanly to CONTEXT.md, docs/architecture.md, or a CONTRACT.md → state the assumed scope and proceed.
If several slices fit → offer a short menu (A / B / C), not a full grill.
If they ask to “explain all of Ahentic” → point at docs/architecture.md; offer 3–5 high-value follow-on concepts. Do not generate a mega-walkthrough.

Normalize subsystem / filename asks into the runtime path that makes the concept real (sidebar → REST → orchestrator → …), not a folder dump.

2. Explore

Done when: glossary terms for the slice are loaded, the relevant CONTRACT + how-it-works are read, the live path is traced, and any doc↔code drift is noted.

Docs-first ladder (skip missing files silently): CONTEXT.md → docs/architecture.md → relevant src/**/CONTRACT.md + colocated how-it-works → PRD/ADR only if the slice is about intended behavior or a recorded trade-off.
Code trace — use the Agent tool with subagent_type=Explore to follow the runtime path end-to-end. Neighbors that are not load-bearing stay black boxes with pointers to their CONTRACT / how-it-works.
Collect primary files and key symbols for the Cast and Step-through (prefer a tight set over exhaustiveness).
Note contribution hooks: usual touch path, ability-checklist / tests / catalogues that must stay in sync when this slice changes.

Use CONTEXT.md vocabulary for domain names. Use codebase-design terms (module, seam, interface, …) only in Neighbors / Change map when they help a contributor locate a change. Keep ELI5 in plain English.

3. Write the HTML walkthrough

Done when: the file exists, opens in the browser, and contains all nine mandatory sections in order (see HTML-REPORT.md).

Resolve temp dir from $TMPDIR, else /tmp (or %TEMP% on Windows).
Write $TMPDIR/concept-walkthrough-<slug>-<timestamp>.html (slug from the concept name; kebab-case).
Open it: open <path> (macOS), xdg-open <path> (Linux), start <path> (Windows).
Tell the user the absolute path.

Empty sections still appear as a one-liner (e.g. “No doc drift found”) so the shape stays recognizable.

Show full SKILL.md (269 more words)Show less

4. Chat handoff

Done when: the user has a short summary in-thread and clear next offers.

In chat (≈5–8 lines):

What the concept is (one sentence)
The runtime path in plain words
Where to look first (2–4 primary files)
How you’d usually change it (one sentence)
Absolute path to the HTML file

Then offer:

(a) zoom a black-boxed neighbor into its own walkthrough
(b) walk a related concept
(c) fix doc drift (if any were listed)
(d) save a durable copy under docs/walkthroughs/ for humans (see below)

5. Durable docs (optional)

Done when: either the user declined, or docs/walkthroughs/<slug>.html is written, the folder README index lists it, and the HTML banner states it is pedagogical — not product law.

Default output stays in temp. When the user asks to keep / commit / add as docs:

Write (or refresh) docs/walkthroughs/<slug>.html with the same mandatory outline and a visible banner: pedagogical walkthrough; PRD / CONTRACT / how-it-works win; regenerate when the slice drifts.
Update docs/walkthroughs/README.md index (slug, title, one-line summary, date).
Do not git commit unless the user explicitly asks. Do not invent product “should” in the walkthrough — cite PRDs; absorb real product gaps via domain-modeling / PRD edits only when the user accepts that offer.
Do not replace or duplicate CONTRACT.md / colocated how-it-works as the source of truth; the walkthrough points at them.

Walkthroughs are supporting orientation maps (cross-stack, beginner-shaped). They are not a fourth product-law surface (see ADR-0001 / PRD index).

Collision guard

Ask	Skill
How does X work / onboard me on X	This skill
Deepen / shallow modules / architecture review	`improve-codebase-architecture`
Something’s broken / failing	`diagnosing-bugs`
Whole-system map only	`docs/architecture.md` (no mega-HTML)

Files

SKILL.md and 2 other files in .cursor/skills/explain-codebase-concept of gambitph/Stackable.

SKILL.md
HTML-REPORT.md
agents/openai.yaml

Open the folder on GitHubat commit 5c13d80

Compare with similar skills

Explain Codebase Concept 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.

Explain Codebase Concept compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Explain Codebase Concept this skillgambitph/Stackable	350	—	~1.4k	Automated safety check: Pass	GPL-3.0	today
Concept Explaineraipoch/medical-research-skills	2k	—	~1.9k	Automated safety check: Pass	MIT	20 days ago
Onboardalirezarezvani/claude-skills	28k	—	~1.3k	Automated safety check: Pass	MIT	1 mo ago
Codebase Onboardingaffaan-m/ECC	274k	3 repos	~2k	Automated safety check: Pass	MIT	2 days ago
Onboardingsickn33/agentic-awesome-skills	47k	1 repos	~1.8k	Automated safety check: Pass	MIT	yesterday
Contributor Onboarding DocDonchitos/Claude-Code-Game-Studios	26k	—	~1.4k	Automated safety check: Pass	MIT	8 days ago

Similar skills

Concept Explainer
aipoch/medical-research-skills
Uses analogies to explain complex medical concepts in accessible terms.
2k GitHub stars~1.9k tokensUpdated 20 days ago
EducationAuto-check passed
Onboard
alirezarezvani/claude-skills
/cs:onboard — Founder interview that populates ~/.claude/company-context.md using the canonical 7-dimension cs-onboard schema.
28k GitHub stars~1.3k tokensUpdated 1 mo ago
Auto-check passed
Codebase Onboarding
affaan-m/ECC
Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md.
274k GitHub starsUsed in 3 repos~2k tokens
DevelopmentAuto-check passed
Onboarding
sickn33/agentic-awesome-skills
When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value.
47k GitHub starsUsed in 1 repo~1.8k tokens
Auto-check passed
Contributor Onboarding Doc
Donchitos/Claude-Code-Game-Studios
Writes an onboarding document for a new contributor or agent, covering project state, conventions and priorities relevant to a chosen role.
26k GitHub stars~1.4k tokensUpdated 8 days ago
DevelopmentAuto-check passed
RuView Onboarding Path Picker
ruvnet/RuView
Zero-to-sensing path picker for RuView (WiFi-DensePose) — pick docker-demo, repo-build, or live-esp32 and run the next concrete step.
97k GitHub stars~333 tokensUpdated today
DevelopmentAuto-check passed

More from gambitph/Stackable

All 18 skills in this repo

Wp Block Development
gambitph/Stackable
A skill your agent uses when developing WordPress (Gutenberg) blocks: block.json metadata, registerblocktype(frommetadata), attributes/serialization, supports, dynamic rendering…
350 GitHub starsUsed in 3 repos~1.6k tokens
Auto-check passed
Wp Block Themes
gambitph/Stackable
A skill your agent uses when developing WordPress block themes: theme.json (global settings/styles), templates and template parts, patterns, style variations, and Site Editor troubleshooting (style…
350 GitHub starsUsed in 3 repos~985 tokens
Auto-check passed
Wp Performance
gambitph/Stackable
A skill your agent uses when investigating or improving WordPress performance (backend-only agent): profiling and measurement (WP-CLI profile/doctor, Server-Timing, Query Monitor via REST headers)…
350 GitHub starsUsed in 3 repos~1.5k tokens
Auto-check passed
Wp Plugin Development
gambitph/Stackable
A skill your agent uses when developing WordPress plugins: architecture and hooks, activation/deactivation/uninstall, admin UI and Settings API, data storage, cron/tasks, security…
350 GitHub starsUsed in 3 repos~999 tokens
Auto-check passed
Wp Project Triage
gambitph/Stackable
A skill your agent uses when you need a deterministic inspection of a WordPress repository (plugin/theme/block theme/WP core/Gutenberg/full site) including tooling/tests/version hints, and a…
350 GitHub starsUsed in 3 repos~371 tokens
Auto-check passed
Wp Plugin Directory Guidelines
gambitph/Stackable
A skill your agent uses when reviewing WordPress plugins for GPL compliance, checking license headers or compatibility, evaluating upsell/freemium/trialware patterns, validating plugin naming or…
350 GitHub starsUsed in 1 repo~1.6k tokens
Auto-check passed

Questions about Explain Codebase Concept

What does Explain Codebase Concept do?

Onboard to how one Ahentic concept, feature, or subsystem is wired — chat summary plus visual HTML walkthrough (optional durable copy under docs/walkthroughs/). Explain Codebase Concept is an agent skill from gambitph/Stackable. Onboard to how one Ahentic concept, feature, or subsystem is wired — chat summary plus visual HTML walkthrough (optional durable copy under docs/walkthroughs/).

How do I install Explain Codebase Concept in Claude Code?

Run `npx skills add gambitph/Stackable --skill explain-codebase-concept -a claude-code`. Or copy the skill folder (.cursor/skills/explain-codebase-concept in gambitph/Stackable) into .claude/skills/explain-codebase-concept in your project. Claude Code loads it when a task matches its description.

How do I install Explain Codebase Concept in Codex?

Run `npx skills add gambitph/Stackable --skill explain-codebase-concept -a codex`. Or copy the skill folder (.cursor/skills/explain-codebase-concept in gambitph/Stackable) into .agents/skills/explain-codebase-concept in your project. Codex loads it when a task matches its description.

Can I use Explain Codebase Concept 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 gambitph/Stackable --skill explain-codebase-concept -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/explain-codebase-concept, .gemini/skills/explain-codebase-concept, .github/skills/explain-codebase-concept and .opencode/skills/explain-codebase-concept in your project.

What does Explain Codebase Concept need to run?

Going by SKILL.md and its folder, Explain Codebase Concept needs the command-line tools its instructions call (git).

Does Explain Codebase Concept 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 Explain Codebase Concept 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 Explain Codebase Concept use?

Explain Codebase Concept 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 Explain Codebase Concept use?

About 1.4k tokens (SKILL.md is roughly 5.5k 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 Explain Codebase Concept?

Skills that share tags, products or a category with Explain Codebase Concept: Concept Explainer (aipoch/medical-research-skills, 2k stars), Onboard (alirezarezvani/claude-skills, 28k stars), Codebase Onboarding (affaan-m/ECC, 274k stars) and Onboarding (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Explain Codebase Concept?

gambitph (a GitHub organization) maintains it in gambitph/Stackable, which has 350 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 7, 2026.

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

Install Explain Codebase Concept

Facts

At a glance

What it does

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Explain Codebase Concept

Process

1. Scope

2. Explore

3. Write the HTML walkthrough

4. Chat handoff

5. Durable docs (optional)

Collision guard

Files

Compare with similar skills

Similar skills

More from gambitph/Stackable

Questions about Explain Codebase Concept