groove-groovebook-publish
groove-groovebook-publish
Use $ARGUMENTS as the learning text if provided.
Outcome
A learning from the current project is published to the configured groovebook repo as a pull request, stripped of any project-specific context, ready for community review.
Acceptance Criteria
- Learning is published as a PR to
<groovebook>repo - PR uses the groovebook PR template format (Summary, Context, Learning, Groove skill area)
- File is written at
learned/<topic>/<YYYY-MM-DD>-<slug>.mdin the groovebook repo - PR URL is printed to the user
Steps
-
Read
groovebook:from.groove/index.md; if absent, exit with:groovebook is not configured. Add 'groovebook: <owner>/<repo>' to .groove/index.md to enable. -
Check
gh auth status; if not authenticated, exit with:Not authenticated with GitHub. Run: gh auth login -
Verify the groovebook repo is accessible:
gh repo view <groovebook>; if it fails, exit with a clear message. -
Get the learning text:
- If $ARGUMENTS is provided, use it as a starting point
- Otherwise: ask "What's the learning you'd like to publish? (paste it or describe briefly)"
- Ask for a one-sentence summary (used as PR title and filename slug)
-
Show a preview of the learning text and ask:
Does this contain any repo-specific context to redact? (file paths, internal names, product names)- If yes: help the user redact it — replace specific names with generic descriptions
- If no: proceed
-
Ask for topic (e.g.
patterns,tools,anti-patterns,workflow) and skill area (e.g.compound,plan,review,daily) -
Generate slug: lowercase the summary, replace spaces with hyphens, strip special characters, truncate to 40 chars. Construct:
- Branch name:
learning/<YYYY-MM-DD>-<slug> - File path:
learned/<topic>/<YYYY-MM-DD>-<slug>.md
- Branch name:
-
Fork the groovebook repo if not already forked:
gh repo fork <groovebook> --clone=false- If fork already exists, skip silently
-
Create the branch and file:
gh api repos/<user-fork>/git/refsto check if branch exists; if so, append a short unique suffix- Write the file content (see format below) and commit via
gh api - Or: use
gitoperations against the fork URL ifgh apiapproach is too complex — prefer the simpler path
-
Open the PR:
gh pr create --repo <groovebook> \ --title "<one-sentence summary>" \ --body "<formatted body>" \ --head "<fork-user>:<branch-name>" -
Print the PR URL
Learning file format
---
date: YYYY-MM-DD
topic: <topic>
skill-area: <skill-area>
source: groovebook-publish
---
# <One-sentence summary>
## Context
<What triggered this learning — what problem were you solving? Generic, no project specifics.>
## Learning
<The insight itself — what to do, what to avoid, or what pattern works.>
## Groove skill area
`<skill-area>` (e.g. `groove-work-compound`, `groove-work-plan`)
PR body format
## Summary
<one-sentence summary>
## Context
<what triggered this>
## Learning
<the insight>
## Groove skill area
`<skill-area>`
---
*Published via groove-groovebook-publish*
Constraints
- Never publish learning text that contains project-specific names, file paths, or internal identifiers without explicit user confirmation that it's intentional
- If the fork step fails due to permissions: suggest the user fork manually and set their fork as the
groovebook:value - Slug must be safe for use as a filename: lowercase, hyphens only, no path separators or special characters
- If branch already exists: append
-2,-3, etc. until a free name is found
More from andreadellacorte/groove
pdf-to-markdown
[Document Processing] Convert PDF files to Markdown with support for native text PDFs and scanned documents (OCR). Cross-platform.
254agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
251groove
Groove engineering workflow system. Top-level entry point. Use groove-daily-*, groove-work-*, groove-utilities-*, groove-admin-* for all workflow and admin commands.
248find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
245groove-utilities-memory-log-daily
Write the daily memory log entry. Use at end of day to record what happened.
235groove-daily-start
Start the workday: review yesterday, create today's daily memory, load tasks, prepare agenda. Use when beginning the day.
231