langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-22 04:15:25 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[PR #4271] [MERGED] docs(oss): overhaul deepagents skills documentation #4256

New Issue
Closed
opened 2026-06-05 19:13:17 -04:00 by yindo · 0 comments
yindo commented 2026-06-05 19:13:17 -04:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/4271
Author: @colifran
Created: 6/2/2026
Status: ✅ Merged
Merged: 6/5/2026
Merged by: @npentrel

Base: main ← Head: colifran/skills-overhaul

📝 Commits (10+)

  • 22b2fa8 overhaul skills docs and improve content
  • 4ecfdc7 move interp skills section lower
  • a03e72f fix top level module in frontmatter
  • cd26657 fix broken link
  • eebb1cb address feedback, rework doc organization
  • ce8de55 write effective skills -> authoring best practices
  • 18445b6 rework structure, add dynamic skills
  • 7432e7d fix broken links
  • 09bbeb5 align memory and skills page
  • fb2d017 sandbox syncing

📊 Changes

3 files changed (+389 additions, -273 deletions)

View changed files

📝 src/oss/deepagents/code/memory-and-skills.mdx (+6 -5)
📝 src/oss/deepagents/interpreters.mdx (+2 -2)
📝 src/oss/deepagents/skills.mdx (+381 -266)

📄 Description

Overview

Rewrites the main Deep Agents skills page to improve clarity for newcomers and better align with the Agent Skills specification. Also addresses PR feedback and adds new content for dynamic skills and sandbox seeding.

  • Rewrote the intro to clearly articulate the problem skills solve: agents lack context, system prompts waste tokens, manual guidance across sessions does not scale
  • Overhauled "How skills work" with concrete discovery/read/execute stages showing how SkillsMiddleware actually handles progressive disclosure
  • Restructured examples to start with a minimal skill before progressing to scripts and advanced frontmatter
  • Added a "Writing effective skills" best practices section covering descriptions, sizing, instruction structure, and skill count management
  • Combined "Skills vs. memory" and "When to use skills and tools" into a single "Skills, memory, and tools" section with a comparison table, the skills-as-memory concept, and skill permissions
  • Reordered code execution section to lead with sandbox scripts, and aligned interpreter skills with the spec by replacing module with metadata.entrypoint
  • Added "Dynamic skills per run" section showing how to use StoreBackend namespace factories to serve different skills per user
  • Expanded sandbox scripts section with full seeding and syncing lifecycle (middleware before_agent/after_agent hooks)
  • Reorganized page structure: Usage now includes getting started, source precedence, skills for subagents, and dynamic skills per run as subsections
  • Updated CLI memory-and-skills page to reflect the updated skills-as-memory framing

Type of change

Type: Update existing documentation

Checklist

  • I have read the contributing guidelines, including the language policy
  • I have tested my changes locally using docs dev
  • All code examples have been tested and work correctly
  • I have used root relative paths for internal links
  • I have updated navigation in src/docs.json if needed

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/docs/pull/4271 **Author:** [@colifran](https://github.com/colifran) **Created:** 6/2/2026 **Status:** ✅ Merged **Merged:** 6/5/2026 **Merged by:** [@npentrel](https://github.com/npentrel) **Base:** `main` ← **Head:** `colifran/skills-overhaul` --- ### 📝 Commits (10+) - [`22b2fa8`](https://github.com/langchain-ai/docs/commit/22b2fa882c4bc536e0bbe9079681e065765e874f) overhaul skills docs and improve content - [`4ecfdc7`](https://github.com/langchain-ai/docs/commit/4ecfdc71552758fb457ade1a05f99807f60b62b5) move interp skills section lower - [`a03e72f`](https://github.com/langchain-ai/docs/commit/a03e72faad5109d23ffa0ebaa9fb1c3e3e39ef35) fix top level module in frontmatter - [`cd26657`](https://github.com/langchain-ai/docs/commit/cd2665779fc6d4bed654f2ce77cf0e731f489818) fix broken link - [`eebb1cb`](https://github.com/langchain-ai/docs/commit/eebb1cb65706b5d92b006d3206005e31f761ed4a) address feedback, rework doc organization - [`ce8de55`](https://github.com/langchain-ai/docs/commit/ce8de5541c0abcee726b2d88cc756a4f9c0ad35f) write effective skills -> authoring best practices - [`18445b6`](https://github.com/langchain-ai/docs/commit/18445b6dd21ce7db45626a296be39151efec694d) rework structure, add dynamic skills - [`7432e7d`](https://github.com/langchain-ai/docs/commit/7432e7d39b575ddd9751b94eca856316415dcdba) fix broken links - [`09bbeb5`](https://github.com/langchain-ai/docs/commit/09bbeb5310b181683ddea7c9372c8aeffd7cf9ee) align memory and skills page - [`fb2d017`](https://github.com/langchain-ai/docs/commit/fb2d017da3fe7d284b2d3853bbce1a154a02e1fb) sandbox syncing ### 📊 Changes **3 files changed** (+389 additions, -273 deletions) <details> <summary>View changed files</summary> 📝 `src/oss/deepagents/code/memory-and-skills.mdx` (+6 -5) 📝 `src/oss/deepagents/interpreters.mdx` (+2 -2) 📝 `src/oss/deepagents/skills.mdx` (+381 -266) </details> ### 📄 Description ## Overview Rewrites the main Deep Agents skills page to improve clarity for newcomers and better align with the Agent Skills specification. Also addresses PR feedback and adds new content for dynamic skills and sandbox seeding. - Rewrote the intro to clearly articulate the problem skills solve: agents lack context, system prompts waste tokens, manual guidance across sessions does not scale - Overhauled "How skills work" with concrete discovery/read/execute stages showing how SkillsMiddleware actually handles progressive disclosure - Restructured examples to start with a minimal skill before progressing to scripts and advanced frontmatter - Added a "Writing effective skills" best practices section covering descriptions, sizing, instruction structure, and skill count management - Combined "Skills vs. memory" and "When to use skills and tools" into a single "Skills, memory, and tools" section with a comparison table, the skills-as-memory concept, and skill permissions - Reordered code execution section to lead with sandbox scripts, and aligned interpreter skills with the spec by replacing module with metadata.entrypoint - Added "Dynamic skills per run" section showing how to use StoreBackend namespace factories to serve different skills per user - Expanded sandbox scripts section with full seeding and syncing lifecycle (middleware before_agent/after_agent hooks) - Reorganized page structure: Usage now includes getting started, source precedence, skills for subagents, and dynamic skills per run as subsections - Updated CLI memory-and-skills page to reflect the updated skills-as-memory framing ## Type of change **Type:** Update existing documentation ## Checklist <!-- Put an 'x' in all boxes that apply --> - [x] I have read the [contributing guidelines](README.md), including the [language policy](https://docs.langchain.com/oss/python/contributing/overview#language-policy) - [x] I have tested my changes locally using `docs dev` - [x] All code examples have been tested and work correctly - [x] I have used **root relative** paths for internal links - [x] I have updated navigation in `src/docs.json` if needed --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-06-05 19:13:17 -04:00
yindo closed this issue 2026-06-05 19:13:17 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
deepagents
docs-infra
external
external
help wanted
integration
internal
internal
javascript
js/ts
langchain
langgraph
langsmith
needs-title
pull-request
Mirrored from GitHub Pull Request
 python
reference
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#4256
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?