exp-write

Store and index experience and knowledge memories into spec context directories.

140|20|Updated Jan 8, 2026
One-click install
npx skills add https://github.com/HHU3637kr/skills --skill exp-write
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: exp-write
Source: https://github.com/HHU3637kr/skills/tree/main/exp-write
Command: npx skills add https://github.com/HHU3637kr/skills --skill exp-write

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The exp-write Skill addresses the need to persist and organize critical experiences and domain knowledge so they can be recalled and reused across sessions and projects.

Core Features & Use Cases

  • Writes experience memories to spec/context/experience/ and updates the experience index.
  • Writes knowledge memories to spec/context/knowledge/ and updates the knowledge index.
  • Generates deterministic file names and IDs, ensuring consistent retrieval and traceability.

Quick Start

Submit a memory entry with type=experience or type=knowledge to create and index a new memory file.

Frequently Asked Questions about exp-write

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I persist experience memories across different development sessions?

To persist experience memories across sessions, you write and index them into the spec context directory. This stores your learning in structured files with deterministic IDs, ensuring consistent retrieval and traceability for future projects.

What is the best way to automate knowledge memory indexing in a software engineering workflow?

Automating knowledge memory indexing involves submitting memory entries to update the spec context knowledge directory and its corresponding index files. This workflow handles both manual capture and automated generation, preserving domain knowledge with structured IDs.

Do I need specific directory structures to store experiential knowledge?

Yes, storing experiential knowledge requires access to spec/context/experience and spec/context/knowledge directories. The process validates IDs, creates new files with proper naming conventions, and updates the corresponding index files within these paths.

Can I capture both experience and knowledge memories using the same indexing process?

Yes, you can capture both experience and knowledge memories using the same indexing process by specifying type=experience or type=knowledge. This generates deterministic file names and updates the corresponding index files for consistent organization.

Why does memory indexing fail when writing new knowledge files to the spec context?

Memory indexing fails if the required spec/context directories are inaccessible or if ID validation encounters duplicates. The system relies on proper naming conventions and valid IDs to create files and update the corresponding index successfully.