Menu
Lightweight skill to capture solved problems and learnings into simple markdown files
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Prepare a finished feature for review — clean the worktree, rebase on the base branch, resolve conflicts, and open or update a GitHub pull request linked to the Linear issue. Use as the final shipping step once implementation is complete and the user wants to raise or update a PR.
Autonomously execute an approved implementation plan from a Linear issue — write code, run tests, commit changes, and check off tasks in Linear. Use when the plan is ready and the user wants to build the feature or fix end to end, isolating the work in a dedicated git worktree.
Refine a rough feature request or bug report into a structured PRD or Bug Brief inside a Linear issue. Use at the start of the engineering workflow to define and clarify what to build before any planning or coding — e.g. when the user wants to write a PRD, draft requirements, or turn an idea or ticket into a spec in Linear.
Generate a detailed implementation plan with parent tasks and atomic sub-tasks from the PRD in a Linear issue, syncing it to a
Generate a narrative summary and visual storyboard (browser screenshots) of completed changes and sync it to the Linear issue. Use after implementation to produce a human-readable walkthrough and visual proof of what was built for reviewers and stakeholders.
Manages Git worktrees for isolated parallel development. Creates branches (linking ticket IDs if available), copies local environment files, and pushes changes to the remote.
| name | document-learnings |
| description | Lightweight skill to capture solved problems and learnings into simple markdown files |
| disable-model-invocation | true |
| allowed-tools | ["Read","Write","Bash"] |
Purpose: A lightweight, frictionless way to automatically document solved problems, bug fixes, and new learnings into searchable markdown files.
This skill captures learnings immediately after confirming a solution, creating simple, structured documentation that serves as a searchable knowledge base. All learnings are saved in a flat directory structure with basic YAML frontmatter.
Auto-invoke after phrases:
OR manual: /learn command
Extract the following from the conversation history:
If context is completely missing, briefly ask the user: "What was the key learning or fix you'd like to document?"
Generate a simple, sanitized filename: docs/learnings/YYYY-MM-DD-[short-topic].md
Sanitization rules:
Ensure the directory exists:
mkdir -p docs/learnings
Write the documentation file populated with the context gathered in Step 1. Use the following simple template:
---
date: [YYYY-MM-DD]
topic: [Short Topic]
---
# [Topic/Symptom]
## The Problem / Context
[Clear description of the issue or what was being attempted]
## The Solution / Learning
[Explanation of how it was fixed or the key takeaway]
Once the file is created, present a simple confirmation to the user:
✓ Learning documented!
Saved to: docs/learnings/[filename].md
Return control to the user. No complex decision menus or cross-referencing required.
</critical_sequence>
MUST do:
docs/learnings/ directory before writing (mkdir -p).MUST NOT do: