·done

Session retrospective and codification. Run at the end of any significant session to extract learnings, update documentation, and create artifacts that make future sessions smoother. Invoke when: - Finishing a multi-step implementation - After debugging a hard problem - End of any session with 3+ tool calls - "what did we learn?" / "wrap up" / "done" Subsumes /codify-learning (codification is one output, not the only one).

8Installs·0Trend·@phrazzld

Installation

$npx skills add https://github.com/phrazzld/claude-config --skill done

How to Install done

Quickly install done AI skill to your development environment via command line

  1. Open Terminal: Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.)
  2. Run Installation Command: Copy and run this command: npx skills add https://github.com/phrazzld/claude-config --skill done
  3. Verify Installation: Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code, Cursor, or OpenClaw

Source: phrazzld/claude-config.

SKILL.md

View raw

Structured reflection that produces concrete artifacts. Not a journal entry — every finding either becomes a codified artifact or gets explicitly justified as not worth codifying.

| Went well | What should we keep doing? | Module separation, lazy imports | | Friction | What slowed us down? | Guessed at API, wrong return types | | Bugs introduced | What broke and why? | Dict access on dataclass | | Missing artifacts | What docs/tools would have prevented friction? | Module API reference |

| Architecture insights | What design decisions proved right/wrong? | SQLite for persistence |

Session retrospective and codification. Run at the end of any significant session to extract learnings, update documentation, and create artifacts that make future sessions smoother. Invoke when: - Finishing a multi-step implementation - After debugging a hard problem - End of any session with 3+ tool calls - "what did we learn?" / "wrap up" / "done" Subsumes /codify-learning (codification is one output, not the only one). Source: phrazzld/claude-config.

Facts (cite-ready)

Stable fields and commands for AI/search citations.

Install command
npx skills add https://github.com/phrazzld/claude-config --skill done
Category
</>Dev Tools
Verified
First Seen
2026-03-01
Updated
2026-03-10

Browse more skills from phrazzld/claude-config

Quick answers

What is done?

Session retrospective and codification. Run at the end of any significant session to extract learnings, update documentation, and create artifacts that make future sessions smoother. Invoke when: - Finishing a multi-step implementation - After debugging a hard problem - End of any session with 3+ tool calls - "what did we learn?" / "wrap up" / "done" Subsumes /codify-learning (codification is one output, not the only one). Source: phrazzld/claude-config.

How do I install done?

Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/phrazzld/claude-config --skill done Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code, Cursor, or OpenClaw

Where is the source repository?

https://github.com/phrazzld/claude-config