agentleFS
Sign inStart free
ww-w-aiww-w-ai/bkit-gemini/skills/btw/SKILL.md

btw

Skill66 starsChanged 7 months agoApache-2.0View on GitHub

Collect improvement suggestions during work. By-The-Way captures ideas, observations, and suggestions without interrupting the current workflow. Stores entries in .bkit/btw.json for later review and promotion.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read .bkit/btw.json (create if it does not exist)

    line 59
  2. Very specific:

    Write the updated array back to .bkit/btw.json using write_file

    line 67
  3. Very specific:

    Read all entries from .bkit/btw.json

    line 94
  4. Distinctive:

    Read the specified entry by ID

    line 102
  5. Very specific:

    Create a new PDCA plan document: docs/01-plan/features/{slug}.plan.md

    line 103
  6. Very specific:

    Update the entry status to promoted

    line 105

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

BTW (By-The-Way) Skill

Capture improvement suggestions on the fly without disrupting your workflow

Commands

CommandDescriptionExample
/btw "text"Record a new suggestion/btw "Consider adding input validation to user form"
/btw listShow all collected suggestions/btw list
/btw analyzeAnalyze and categorize suggestions/btw analyze
/btw promote [id]Promote suggestion to PDCA feature/btw promote 3

How It Works

Recording a Suggestion

  1. Read .bkit/btw.json (create if it does not exist)
  2. Append a new entry with:
    • id: Auto-incrementing integer
    • text: The suggestion text
    • timestamp: ISO 8601 date string
    • context: Current file or feature being worked on
    • status: pending (default)
    • category: Auto-detected (perf, ux, refactor, security, docs, other)
  3. Write the updated array back to .bkit/btw.json using write_file

Storage Format

{
  "entries": [
    {
      "id": 1,
      "text": "Consider caching API responses for /users endpoint",
      "timestamp": "2026-04-09T14:30:00Z",
      "context": "src/api/users.js",
      "status": "pending",
      "category": "perf"
    }
  ]
}

Listing Suggestions

  1. Read .bkit/btw.json
  2. Display entries in a table sorted by newest first
  3. Show status indicators: pending, promoted, dismissed

Analyzing Suggestions

  1. Read all entries from .bkit/btw.json
  2. Group by category
  3. Identify patterns and recurring themes
  4. Suggest which items to prioritize
  5. Estimate effort for each (low/medium/high)

Promoting to PDCA Feature

  1. Read the specified entry by ID
  2. Create a new PDCA plan document: docs/01-plan/features/{slug}.plan.md
  3. Pre-fill the plan with the suggestion details
  4. Update the entry status to promoted
  5. Inform user to continue with /pdca design {slug}

Categories

CategoryDetection Keywords
perfcache, speed, optimize, slow, performance, latency
uxuser, UI, UX, interface, experience, accessibility
refactorrefactor, cleanup, simplify, DRY, extract, reorganize
securitysecurity, auth, validation, sanitize, XSS, CSRF
docsdocument, README, comment, explain, JSDoc
otherEverything else

Integration with PDCA

BTW feeds into the Act phase:

  1. Collect suggestions during Do phase with /btw "..."
  2. Review collected items with /btw list
  3. Analyze patterns with /btw analyze
  4. Promote actionable items with /btw promote [id]
  5. Continue with standard PDCA flow for promoted items

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free