Agent skill

Bkit Explore

Browse installed bkit skills, agents, and evals via lib/discovery/explorer.js (filesystem scan, no subprocess).

Apache-2.0Auto-check passedAI & LLM Engineering

Install Bkit Explore

skills CLI

$ npx skills add ww-w-ai/bkit-claude-code --skill bkit-explore -a claude-code

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

GitHub CLI

$ gh skill install ww-w-ai/bkit-claude-code bkit-explore --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/ww-w-ai/bkit-claude-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/bkit-explore .claude/skills/bkit-explore && 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 "bkit-explore" agent skill from https://github.com/ww-w-ai/bkit-claude-code/tree/main/skills/bkit-explore into .claude/skills/bkit-explore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bkit-explore", 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/ww-w-ai/bkit-claude-code/tree/main/skills/bkit-explore

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 ww-w-ai/bkit-claude-code --skill bkit-explore -a codex

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

GitHub CLI

$ gh skill install ww-w-ai/bkit-claude-code bkit-explore --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/ww-w-ai/bkit-claude-code.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/bkit-explore .agents/skills/bkit-explore && 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 "bkit-explore" agent skill from https://github.com/ww-w-ai/bkit-claude-code/tree/main/skills/bkit-explore into .agents/skills/bkit-explore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bkit-explore", 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 ww-w-ai/bkit-claude-code --skill bkit-explore -a cursor

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

GitHub CLI

$ gh skill install ww-w-ai/bkit-claude-code bkit-explore --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/ww-w-ai/bkit-claude-code.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/bkit-explore .cursor/skills/bkit-explore && 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 "bkit-explore" agent skill from https://github.com/ww-w-ai/bkit-claude-code/tree/main/skills/bkit-explore into .cursor/skills/bkit-explore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bkit-explore", 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/ww-w-ai/bkit-claude-code.git --path skills/bkit-explore

--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 ww-w-ai/bkit-claude-code --skill bkit-explore -a gemini-cli

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

GitHub CLI

$ gh skill install ww-w-ai/bkit-claude-code bkit-explore --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/ww-w-ai/bkit-claude-code.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/bkit-explore .gemini/skills/bkit-explore && 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 "bkit-explore" agent skill from https://github.com/ww-w-ai/bkit-claude-code/tree/main/skills/bkit-explore into .gemini/skills/bkit-explore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bkit-explore", 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 ww-w-ai/bkit-claude-code bkit-explore

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 ww-w-ai/bkit-claude-code --skill bkit-explore -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/ww-w-ai/bkit-claude-code.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/bkit-explore .github/skills/bkit-explore && 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 "bkit-explore" agent skill from https://github.com/ww-w-ai/bkit-claude-code/tree/main/skills/bkit-explore into .github/skills/bkit-explore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bkit-explore", 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 ww-w-ai/bkit-claude-code --skill bkit-explore -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 ww-w-ai/bkit-claude-code bkit-explore --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/ww-w-ai/bkit-claude-code.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/bkit-explore .opencode/skills/bkit-explore && 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 "bkit-explore" agent skill from https://github.com/ww-w-ai/bkit-claude-code/tree/main/skills/bkit-explore into .opencode/skills/bkit-explore/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bkit-explore", 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: bkit-explore
GitHub stars: 601
Token cost: ~1.1k tokens
SKILL.md length: 312 words
Files: 1
Skills in repo: 44
Repo updated: Sep 27, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Browse installed bkit skills, agents, and evals via lib/discovery/explorer.js (filesystem scan, no subprocess).

Works in 3 steps: Call explorer.listAll() to read… → Render category-grouped table: skill… → Footer: Total: N skills · M agents · K…
Tasks that involve LLM evaluation
SKILL.md covers Arguments, Behavior, Output Layout (Design §5.1) and Security, plus 4 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Bkit Explore is an agent skill from ww-w-ai/bkit-claude-code. Browse installed bkit skills, agents, and evals via lib/discovery/explorer.js (filesystem scan, no subprocess). Triggers: bkit explore, list skills, skill discovery, browse skills

Its SKILL.md is about 1.1k 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 AI & LLM Engineering, covering LLM evaluation and Skill management. The repository describes itself as: bkit Vibecoding Kit - PDCA methodology + Claude Code mastery for AI-native development. The licence is Apache-2.0.

When your agent uses it

Tasks that involve LLM evaluation
Tasks that involve Skill management

Example prompts

“/bkit-explore”

Requirements

Pre-approved tools (allowed-tools): Read, Glob, Grep

Workflow steps

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

Call explorer.listAll() to read skills/*/SKILL.md + agents/*.md.
Render category-grouped table: skill name + first-sentence description.
Footer: Total: N skills · M agents · K evals.

What it can do on your machine

Read from SKILL.md and the folder at commit 85b4913. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
- Read
- Glob
- Grep
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
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

Bkit Explore loads about 1.1k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 312 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: ~1.1k

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 ww-w-ai/bkit-claude-code at commit 85b4913, republished under its Apache-2.0 licence (© ww-w-ai). 312 words, ~1,053 tokens.

Download SKILL.mdSave it as .claude/skills/bkit-explore/SKILL.md (or your agent's skills folder).

name: bkit-explore
description: Browse installed bkit skills, agents, and evals via lib/discovery/explorer.js (filesystem scan, no subprocess). Triggers: bkit explore, list skills, skill discovery, browse skills
allowed-tools: Read, Glob, Grep
classification: capability
classification-reason: Discovery surface — independent of bkit's PDCA workflow
deprecation-risk: none
effort: low
argument-hint: [category] | evals | --level <Starter|Dynamic|Enterprise>
user-invocable: true
task-template: [Explore] {target}

bkit Explore — Skill / Agent / Eval Discovery

v2.1.11 Sprint β FR-β1. Wraps lib/discovery/explorer.js to give Yuki + first-run users a single-command surface that answers "what's actually installed and how do I find it?"

Arguments

Argument	Description	Example
(none)	Show all categories with counts + first-line description	`/bkit-explore`
`<category>`	One of `starter`, `dynamic`, `enterprise`, `pdca-core`, `utility`	`/bkit-explore dynamic`
`evals`	List skills with an `evals/{cls}/{skill}/eval.yaml` definition	`/bkit-explore evals`
`--level <L>`	Filter by Starter / Dynamic / Enterprise (cumulative)	`/bkit-explore --level Starter`

Behavior

Default (no args) — full tree

Call explorer.listAll() to read skills/*/SKILL.md + agents/*.md.
Render category-grouped table: skill name + first-sentence description.
Footer: Total: N skills · M agents · K evals.

`<category>` — single bucket

Validate category against explorer.CATEGORIES.
Render skill table + agent table for that bucket only.
Suggest /bkit-explore --level Starter if user looks lost.

`evals` — eval coverage

Call explorer.listEvals() and group by classification (workflow, capability, hybrid).
Render counts + skill names per group.
Tip: /bkit-evals run <skill> to execute one.

`--level <L>` — Starter / Dynamic / Enterprise filter

Starter returns starter + pdca-core + utility.
Dynamic adds dynamic (cumulative).
Enterprise adds enterprise.

Output Layout (Design §5.1)

bkit Explore — 39 Skills · 36 Agents · K Evals
─────────────────────────────────────────────────
📂 starter (1 skill / 2 agents)
   /starter         — Static web kit
   🤖 starter-guide — Beginner agent
   🤖 pipeline-guide — Phase walk-through

📂 dynamic (8 skills / 2 agents)
   /dynamic           — bkend.ai fullstack
   /bkend-auth        — Authentication patterns
   ...
─────────────────────────────────────────────────
Footer: Try /bkit-explore --level Starter

Security

Pure filesystem scan — no child_process, no network.
category argument is validated against explorer.CATEGORIES (5-tuple whitelist); anything else returns null and renders a usage hint.
--level <L> validated against explorer.LEVELS (Starter / Dynamic / Enterprise).
Agent/skill descriptions read from local *.md files only — no remote fetch.

Module Dependencies

Module	Function	Usage
`lib/discovery/explorer.js`	`listAll()`	Default tree
`lib/discovery/explorer.js`	`listByCategory(cat)`	Single bucket
`lib/discovery/explorer.js`	`listByLevel(level)`	Cumulative filter
`lib/discovery/explorer.js`	`listEvals()`	`evals/` scan

Categories (Design §3.2)

Category	Scope
`starter`	Static web + beginner-onboarding skills/agents
`dynamic`	bkend.ai fullstack + Phase 1~6 build pipeline
`enterprise`	Architecture + Phase 7~9 deployment + audit
`pdca-core`	PDCA cycle + QA + PM agents
`utility`	Cross-cutting (bkit, control, audit, evals)

Examples

bash

# Full tree
/bkit-explore

# One category
/bkit-explore dynamic

# Cumulative level filter
/bkit-explore --level Starter

# Evals coverage
/bkit-explore evals

/bkit-evals run <skill> — execute eval suite for one skill
/control trust — trust score informs which categories you can self-serve
/pdca status — find your active feature

ARGUMENTS:

Files

Just SKILL.md in skills/bkit-explore of ww-w-ai/bkit-claude-code.

Open the folder on GitHubat commit 85b4913

Compare with similar skills

Bkit Explore 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.

Bkit Explore compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Bkit Explore this skillww-w-ai/bkit-claude-code	601	—	~1.1k	Automated safety check: Pass	Apache-2.0	12 days ago
Agent Skillsmagnus919/agent-skills	116	—	~3k	Automated safety check: Pass	MIT	today
Looperksimback/looper	710	—	~2.7k	Automated safety check: Notes	MIT	2 mo ago
Context Auditundefined-ui/second-brain-os	1k	—	~802	Automated safety check: Pass	MIT	yesterday
Benchflowbenchflow-ai/benchflow	355	—	~1.9k	Automated safety check: Notes	Apache-2.0	3 days ago
Add Benchmarkai-twinkle/Eval	117	—	~1.8k	Automated safety check: Pass	MIT	23 days ago

Similar skills

Agent Skills
magnus919/agent-skills
A skill your agent uses when creating, reviewing, or editing Agent Skills-format skills, or when implementing skill discovery and loading in an agent client.
116 GitHub stars~3k tokensUpdated today
AI & LLM EngineeringAuto-check passed
Looper
ksimback/looper
Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council.
710 GitHub stars~2.7k tokensUpdated 2 mo ago
AI & LLM EngineeringAuto-check: notes
Context Audit
undefined-ui/second-brain-os
Audit an agent's context layout against the four places: system prompt, tools, history, tail.
1k GitHub stars~802 tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed
Benchflow
benchflow-ai/benchflow
Run agent benchmarks, create tasks, analyze results, and manage agents using BenchFlow.
355 GitHub stars~1.9k tokensUpdated 3 days ago
AI & LLM EngineeringAuto-check: notes
Add Benchmark
ai-twinkle/Eval
為 Twinkle Eval 新增一個評測 benchmark（IFEval、BFCL、RAGAS、Text2SQL、Vision MCQ 之類）。涵蓋 CLAUDE.md §6 的完整強制流程：先建 Milestone 與 6 個 Issue、準備 example dataset、實作 Extractor + Scorer 並註冊 PRESETS、與參考框架做分數與速度對比、撰寫…
117 GitHub stars~1.8k tokensUpdated 23 days ago
AI & LLM EngineeringAuto-check passed
Email Evals
tokencanopy/e2a
Author and safely run deterministic email-agent evaluation suites with dedicated e2a test agents.
193 GitHub stars~2.1k tokensUpdated 3 days ago
AI & LLM EngineeringAuto-check passed

Questions about Bkit Explore

What does Bkit Explore do?

Browse installed bkit skills, agents, and evals via lib/discovery/explorer.js (filesystem scan, no subprocess). Bkit Explore is an agent skill from ww-w-ai/bkit-claude-code.js (filesystem scan, no subprocess).

When should I use Bkit Explore?

Bkit Explore fits situations like: tasks that involve LLM evaluation; tasks that involve Skill management.

How do I install Bkit Explore in Claude Code?

Run `npx skills add ww-w-ai/bkit-claude-code --skill bkit-explore -a claude-code`. Or copy the skill folder (skills/bkit-explore in ww-w-ai/bkit-claude-code) into .claude/skills/bkit-explore in your project. Claude Code loads it when a task matches its description.

How do I install Bkit Explore in Codex?

Run `npx skills add ww-w-ai/bkit-claude-code --skill bkit-explore -a codex`. Or copy the skill folder (skills/bkit-explore in ww-w-ai/bkit-claude-code) into .agents/skills/bkit-explore in your project. Codex loads it when a task matches its description.

Can I use Bkit Explore 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 ww-w-ai/bkit-claude-code --skill bkit-explore -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bkit-explore, .gemini/skills/bkit-explore, .github/skills/bkit-explore and .opencode/skills/bkit-explore in your project.

What does Bkit Explore need to run?

SKILL.md names no scripts, command-line tools or credentials: Bkit Explore is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Glob, Grep.

Does Bkit Explore 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 Bkit Explore 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 Bkit Explore use?

Bkit Explore is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bkit Explore use?

About 1.1k tokens (SKILL.md is roughly 4.2k 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 Bkit Explore?

Skills that share tags, products or a category with Bkit Explore: Agent Skills (magnus919/agent-skills, 116 stars), Looper (ksimback/looper, 710 stars), Context Audit (undefined-ui/second-brain-os, 1k stars) and Benchflow (benchflow-ai/benchflow, 355 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bkit Explore?

ww-w-ai (a GitHub organization) maintains it in ww-w-ai/bkit-claude-code, which has 601 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on September 27, 2026.

Source: ww-w-ai/bkit-claude-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Bkit Explore

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

bkit Explore — Skill / Agent / Eval Discovery

Arguments

Behavior

Default (no args) — full tree

<category> — single bucket

evals — eval coverage

--level <L> — Starter / Dynamic / Enterprise filter

Output Layout (Design §5.1)

Security

Module Dependencies

Categories (Design §3.2)

Examples

Related

Files

Compare with similar skills

Similar skills

More from ww-w-ai/bkit-claude-code

Related

Questions about Bkit Explore

`<category>` — single bucket

`evals` — eval coverage

`--level <L>` — Starter / Dynamic / Enterprise filter