Agent skill

Btw

By-The-Way: capture improvement ideas the moment they surface, without derailing the task in progress.

Apache-2.0Auto-check: notes

Install Btw

skills CLI

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

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

GitHub CLI

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

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 btw -a codex

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

GitHub CLI

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

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

GitHub CLI

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

--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 btw -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 btw --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/btw .gemini/skills/btw && 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 "btw" agent skill from https://github.com/ww-w-ai/bkit-claude-code/tree/main/skills/btw into .gemini/skills/btw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "btw", 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 btw

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 btw -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/btw .github/skills/btw && 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 "btw" agent skill from https://github.com/ww-w-ai/bkit-claude-code/tree/main/skills/btw into .github/skills/btw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "btw", 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 btw -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 btw --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/btw .opencode/skills/btw && 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 "btw" agent skill from https://github.com/ww-w-ai/bkit-claude-code/tree/main/skills/btw into .opencode/skills/btw/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "btw", 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: btw
GitHub stars: 601
Token cost: ~1.7k tokens
SKILL.md length: 498 words
Files: 1
Skills in repo: 44
Repo updated: Sep 27, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

By-The-Way: capture improvement ideas the moment they surface, without derailing the task in progress.

Works in 6 steps: Read .bkit/btw-suggestions.json (create… → Generate next ID: btw-NNN (zero-padded,… → Create suggestion entry → …
SKILL.md covers Commands, Data File:…, Category Auto-Detection Rules and Integration Points, plus 1 more section
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Btw is an agent skill from ww-w-ai/bkit-claude-code. By-The-Way: capture improvement ideas the moment they surface, without derailing the task in progress. Triggers: /bkit:btw, /bkit:btw list, /bkit:btw analyze, /bkit:btw promote, /bkit:btw stats, btw, suggestion, improve, idea, feedback

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.

The repository describes itself as: bkit Vibecoding Kit - PDCA methodology + Claude Code mastery for AI-native development. The licence is Apache-2.0.

Example prompts

“/btw”

Requirements

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

Workflow steps

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

Read .bkit/btw-suggestions.json (create if not exists)
Generate next ID: btw-NNN (zero-padded, sequential)
Create suggestion entry
Auto-detect category from suggestion text
Update stats.total count
Respond: "Recorded btw-{NNN}: {truncated suggestion}. Use /btw list to view all."

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
- Write
- Edit
- Glob
- Grep
- Bash
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 json).
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

Btw loads about 1.7k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 498 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~60
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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
```
allowed-tools: Read, Write, Edit, Glob, Grep, Bash
```

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). 498 words, ~1,675 tokens.

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

name: btw
description: By-The-Way: capture improvement ideas the moment they surface, without derailing the task in progress. Triggers: /bkit:btw, /bkit:btw list, /bkit:btw analyze, /bkit:btw promote, /bkit:btw stats, btw, suggestion, improve, idea, feedback
allowed-tools: Read, Write, Edit, Glob, Grep, Bash
classification: workflow
classification-reason: Manages /btw command lifecycle: record, list, analyze, promote, stats. User-driven workflow with CRUD on btw-suggestions.json
deprecation-risk: none
effort: medium
argument-hint: /bkit:btw {suggestion} | /bkit:btw list | /bkit:btw analyze | /bkit:btw promote {id} | /bkit:btw stats
user-invocable: true

/btw - By-The-Way Suggestion Collector

작업 중 "이거 스킬로 만들면 좋겠다", "이 패턴 자동화하면 좋겠다" 등의 개선 제안을 즉시 기록하고 관리하는 도구.

Commands

`/btw {suggestion}` - Record a suggestion

Read .bkit/btw-suggestions.json (create if not exists)
Generate next ID: btw-NNN (zero-padded, sequential)

Create suggestion entry:

json

{
  "id": "btw-001",
  "timestamp": "ISO-8601",
  "suggestion": "{user input}",
  "context": {
    "file": "{current working file if identifiable}",
    "pdcaPhase": "{current PDCA phase from getPdcaStatusView() or null}",
    "feature": "{current feature or null}"
  },
  "category": "auto-detect",
  "status": "pending",
  "promotedTo": null,
  "priority": null,
  "teamContext": {
    "isTeamSession": false,
    "phase": "{PDCA phase or null}",
    "role": "{teammate role that discovered this, or 'user'}",
    "pattern": "{orchestration pattern or null}"
  }
}

Auto-detect category from suggestion text:
- skill-request: mentions "skill", "스킬", "자동화", "automate"
- bug-pattern: mentions "bug", "버그", "오류", "error", "fix"
- improvement: mentions "개선", "improve", "better", "refactor"
- documentation: mentions "문서", "doc", "설명", "explain"
- general: default
Update stats.total count
Respond: "Recorded btw-{NNN}: {truncated suggestion}. Use /btw list to view all."

`/btw list` - List all suggestions

Read .bkit/btw-suggestions.json

Display table:

ID       | Status   | Category       | Suggestion (truncated)
---------|----------|----------------|----------------------
btw-001  | pending  | skill-request  | @Flow 모델에서 옵션 목록을 자동...
btw-002  | promoted | improvement    | DataProxy 패턴에 검증 로직을...

Show summary: Total: N | Pending: N | Promoted: N | Dismissed: N

`/btw analyze` - Analyze suggestions for skill candidates

Read all pending suggestions from .bkit/btw-suggestions.json
Group by category and find patterns:
- Cluster similar suggestions (keyword overlap)
- Count frequency of similar topics
- Identify suggestions that map to existing bkit skills vs. new skill needs
For each skill candidate:
- Estimate skill classification: workflow vs capability
- Suggest skill name and description
- Reference source suggestion IDs

Output analysis:

Skill Candidates from /btw Analysis
=====================================

1. [NEW SKILL] hunikflow-validation (capability)
   Based on: btw-001, btw-005, btw-008
   Frequency: 3 mentions
   Description: Validation pattern guide for @Flow entities

2. [EXISTING SKILL ENHANCEMENT] code-review
   Based on: btw-003
   Suggestion: Add DataProxy-specific review rules

Save analysis timestamp to stats.lastAnalyzed

`/btw promote {id}` - Promote suggestion to skill creation

Find suggestion by ID in .bkit/btw-suggestions.json
Validate status is "pending" (cannot promote already promoted/dismissed)
Update suggestion:
- status: "promoted"
- promotedTo: skill name (derived from suggestion)
Trigger skill-create workflow with context from the suggestion:
- Pass suggestion text as skill description seed
- Pass context (file, feature) as project context
Respond: "Promoted btw-{id} -> skill-create pipeline. Run /skill-create to continue."

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

`/btw stats` - Show statistics

Read .bkit/btw-suggestions.json

Calculate and display:

/btw Statistics
===============
Total suggestions: 12
By status: pending=8, promoted=3, dismissed=1
By category: skill-request=5, improvement=4, bug-pattern=2, general=1
Promotion rate: 25.0%
Last analyzed: 2026-03-13T10:00:00Z
Top keywords: @Flow(3), DataProxy(2), validation(2)

Data File: `.bkit/btw-suggestions.json`

Initialize with this structure if file does not exist:

json

{
  "version": "1.0",
  "suggestions": [],
  "stats": {
    "total": 0,
    "promoted": 0,
    "dismissed": 0,
    "lastAnalyzed": null
  }
}

Category Auto-Detection Rules

Pattern	Category
skill, 스킬, automate, 자동화, command, 명령	skill-request
bug, 버그, error, 오류, fix, 수정	bug-pattern
improve, 개선, better, refactor, 리팩토링, optimize	improvement
doc, 문서, explain, 설명, readme, guide	documentation
(default)	general

Integration Points

PDCA Context: Reads the phase and feature through getPdcaStatusView() (lib/pdca/status.js), which covers a phase that only its documents evidence. .bkit/state/memory.json — the migrated .bkit-memory.json — carries the 9-phase pipeline status, not the PDCA phase.
skill-create: /btw promote triggers skill-create workflow
skill-needs-extractor: /btw analyze results feed into gap analysis
CTO Team: Phase transition triggers btw summary (see below)

CTO Team Integration

When /btw is used during a CTO Team session (/pdca team):

Auto-Detection

Check if team session is active via .bkit/runtime/agent-state.json
If active: set teamContext.isTeamSession = true and populate phase/role/pattern
If not active: set teamContext.isTeamSession = false (default behavior)

Phase Transition Hook

CTO Lead automatically reads btw-suggestions.json at every phase transition:

0 pending: Silent skip (no output, no turns spent)
1+ pending: Brief summary (top 3, category counts) in 1-2 turns
CTO does NOT auto-promote — user decides via /btw promote {id}

Session End

cto-stop.js hook outputs btw stats at session end:

Total suggestions collected during session
Category breakdown
Promotion rate

teamContext Field

Added to each suggestion entry when recorded during a team session:

json

"teamContext": {
  "isTeamSession": true,
  "phase": "do",
  "role": "user",
  "pattern": "swarm"
}

This enables /btw analyze to group suggestions by PDCA phase and identify phase-specific patterns.

Files

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

Open the folder on GitHubat commit 85b4913

Compare with similar skills

Btw 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.

Btw compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Btw this skillww-w-ai/bkit-claude-code	601	—	~1.7k	Automated safety check: Notes	Apache-2.0	13 days ago
Capturealirezarezvani/claude-skills	28k	1 repos	~2.8k	Automated safety check: Pass	MIT	1 mo ago
Idea Darwinsickn33/agentic-awesome-skills	47k	2 repos	~1.1k	Automated safety check: Pass	MIT	yesterday
Idea Refinementaddyosmani/agent-skills	104k	6 repos	~2k	Automated safety check: Pass	MIT	6 days ago
Workspace Surface Auditaffaan-m/ECC	276k	3 repos	~1.3k	Automated safety check: Notes	MIT	today
Skill Improversickn33/agentic-awesome-skills	47k	2 repos	~1.5k	Automated safety check: Pass	MIT	yesterday

Similar skills

Capture
alirezarezvani/claude-skills
Captures and organizes chaotic brain dumps into a structured, actionable system with zero information loss.
28k GitHub starsUsed in 1 repo~2.8k tokens
Agent WorkflowsAuto-check passed
Idea Darwin
sickn33/agentic-awesome-skills
Darwinian idea evolution engine — toss rough ideas onto an evolution island, let them compete, crossbreed, and mutate through structured rounds to surface your strongest concepts.
47k GitHub starsUsed in 2 repos~1.1k tokens
Auto-check passed
Idea Refinement
addyosmani/agent-skills
Guides a conversation that takes a vague idea through divergent and convergent thinking and ends in a markdown one-pager covering scope and assumptions.
104k GitHub starsUsed in 6 repos~2k tokens
Agent WorkflowsAuto-check passed
Workspace Surface Audit
affaan-m/ECC
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows.
276k GitHub starsUsed in 3 repos~1.3k tokens
Agent WorkflowsAuto-check: notes
Skill Improver
sickn33/agentic-awesome-skills
Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards.
47k GitHub starsUsed in 2 repos~1.5k tokens
Agent WorkflowsAuto-check passed
Same Idea Both Platforms
sickn33/agentic-awesome-skills
Write one idea as a Twitter/X post and a LinkedIn post that read as written separately, not pasted twice.
47k GitHub starsUsed in 1 repo~1.4k tokens
Writing & ContentAuto-check passed

Questions about Btw

What does Btw do?

By-The-Way: capture improvement ideas the moment they surface, without derailing the task in progress. Btw is an agent skill from ww-w-ai/bkit-claude-code. By-The-Way: capture improvement ideas the moment they surface, without derailing the task in progress.

How do I install Btw in Claude Code?

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

How do I install Btw in Codex?

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

Can I use Btw 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 btw -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/btw, .gemini/skills/btw, .github/skills/btw and .opencode/skills/btw in your project.

What does Btw need to run?

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

Does Btw 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 Btw safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Btw use?

Btw 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 Btw use?

About 1.7k tokens (SKILL.md is roughly 6.7k 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 Btw?

Skills that share tags, products or a category with Btw: Capture (alirezarezvani/claude-skills, 28k stars), Idea Darwin (sickn33/agentic-awesome-skills, 47k stars), Idea Refinement (addyosmani/agent-skills, 104k stars) and Workspace Surface Audit (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Btw?

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 Btw

Facts

At a glance

What it does

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

/btw - By-The-Way Suggestion Collector

Commands

/btw {suggestion} - Record a suggestion

/btw list - List all suggestions

/btw analyze - Analyze suggestions for skill candidates

/btw promote {id} - Promote suggestion to skill creation

/btw stats - Show statistics

Data File: .bkit/btw-suggestions.json

Category Auto-Detection Rules

Integration Points

CTO Team Integration

Auto-Detection

Phase Transition Hook

Session End

teamContext Field

Files

Compare with similar skills

Similar skills

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

Questions about Btw

`/btw {suggestion}` - Record a suggestion

`/btw list` - List all suggestions

`/btw analyze` - Analyze suggestions for skill candidates

`/btw promote {id}` - Promote suggestion to skill creation

`/btw stats` - Show statistics

Data File: `.bkit/btw-suggestions.json`