Deep Agents docs release skill
Use this skill when the product is Deep Agents Python (langchain-ai/deepagents, tags deepagents==...). For TypeScript releases from langchain-ai/deepagentsjs, use the deepagentsjs skill. For Deep Agents Code, use deepagents-code. Do not use this skill for Managed Deep Agents.
Sources of truth
- Releases: GitHub
langchain-ai/deepagents via get_eligible_release / get_release_notes
- Important: that repo publishes several packages. For this product, only tags that start with
deepagents== count (not deepagents-code==, deepagents-acp==, or langchain-quickjs==).
- Docs paths in
langchain-ai/docs:
src/oss/deepagents/ library pages
- Exclude
src/oss/deepagents/code/ (Deep Agents Code is a separate product)
- Navigation for Deep Agents in
src/docs.json
- Docs style authority: root
AGENTS.md in langchain-ai/docs (read via get_docs_file before drafting)
- Changelog entry pages:
src/oss/deepagents/changelog-py.mdx
src/oss/deepagents/changelog-js.mdx
What usually needs docs
Prioritize user-facing changes:
- New public APIs, middleware, backends, tools, or config options
- New or changed CLI / SDK behavior that readers rely on
- New capabilities (subagents, sandboxes, streaming, HITL, skills, memory)
- Behavior changes that make existing docs wrong
- New minimum package versions that docs should call out
Usually skip docs for:
- Internal refactors with no user-visible change
- Dependency bumps with no behavior change
- Pure bug fixes that do not change documented behavior
- Changes that belong only to Deep Agents Code (
deepagents-code==... releases)
When a release note is Python-only or JS-only, edit the matching language-fenced sections (:::python / :::js) rather than inventing parity.
When unsure, open a small clarifying ticket/PR only if a reader of the current docs would be misled.
Workflow for one Deep Agents release
The main agent must run phase 1 through the release-research subagent first (diff + source investigation). This skill guides phase 2 shipping and judgment details the subagent also uses.
- After research returns features with
needs_docs: true, read /memories/agent/deepagents-releases.md and skip any already recorded for that tag.
- Call
get_docs_file on AGENTS.md and read it in full. Then call get_docs_file for Deep Agents pages named in the research report. Stay out of src/oss/deepagents/code/.
- For each remaining feature:
- Edit surgically from the page
get_docs_file content, following the docs repo AGENTS.md. Prefer :::python sections; leave :::js alone unless the change is shared.
- Prefer updating the owning page over creating a new page. If a new page is required, also plan the
src/docs.json navigation update.
- Load the
ship-docs-update skill and ship that feature alone with the research report's evidence as evidence_json.
- After shipping, append the release tag, feature name, Linear URL, and PR URL to
/memories/agent/deepagents-releases.md.
- Keep
/memories/agent/AGENTS.md short: last processed Deep Agents tag and date, alongside other products.
Memory format
Use cold memory file /memories/agent/deepagents-releases.md:
# Deep Agents release tracking
## deepagents==0.7.24
- feature: async subagent fork mode
- linear: https://linear.app/...
- pr: https://github.com/langchain-ai/docs/pull/...
1---2name: deepagents3description: Analyze Deep Agents Python library releases against LangChain Deep Agents docs and prepare one-feature documentation updates.4metadata:5 source: https://skillmd.com/skills/langchain-ai/deepagents6---78# Deep Agents docs release skill910Use this skill when the product is Deep Agents Python (`langchain-ai/deepagents`, tags `deepagents==...`). For TypeScript releases from `langchain-ai/deepagentsjs`, use the `deepagentsjs` skill. For Deep Agents Code, use `deepagents-code`. Do not use this skill for Managed Deep Agents.1112## Sources of truth1314- Releases: GitHub `langchain-ai/deepagents` via `get_eligible_release` / `get_release_notes`15- Important: that repo publishes several packages. For this product, only tags that start with `deepagents==` count (not `deepagents-code==`, `deepagents-acp==`, or `langchain-quickjs==`).16- Docs paths in `langchain-ai/docs`:17 - `src/oss/deepagents/` library pages18 - Exclude `src/oss/deepagents/code/` (Deep Agents Code is a separate product)19 - Navigation for Deep Agents in `src/docs.json`20 - Docs style authority: root `AGENTS.md` in `langchain-ai/docs` (read via `get_docs_file` before drafting)21- Changelog entry pages:22 - `src/oss/deepagents/changelog-py.mdx`23 - `src/oss/deepagents/changelog-js.mdx`2425## What usually needs docs2627Prioritize user-facing changes:2829- New public APIs, middleware, backends, tools, or config options30- New or changed CLI / SDK behavior that readers rely on31- New capabilities (subagents, sandboxes, streaming, HITL, skills, memory)32- Behavior changes that make existing docs wrong33- New minimum package versions that docs should call out3435Usually skip docs for:3637- Internal refactors with no user-visible change38- Dependency bumps with no behavior change39- Pure bug fixes that do not change documented behavior40- Changes that belong only to Deep Agents Code (`deepagents-code==...` releases)4142When a release note is Python-only or JS-only, edit the matching language-fenced sections (`:::python` / `:::js`) rather than inventing parity.4344When unsure, open a small clarifying ticket/PR only if a reader of the current docs would be misled.4546## Workflow for one Deep Agents release4748The main agent must run **phase 1** through the `release-research` subagent first (diff + source investigation). This skill guides **phase 2** shipping and judgment details the subagent also uses.49501. After research returns features with `needs_docs: true`, read `/memories/agent/deepagents-releases.md` and skip any already recorded for that tag.512. Call `get_docs_file` on `AGENTS.md` and read it in full. Then call `get_docs_file` for Deep Agents pages named in the research report. Stay out of `src/oss/deepagents/code/`.523. For each remaining feature:53 - Edit surgically from the page `get_docs_file` content, following the docs repo `AGENTS.md`. Prefer `:::python` sections; leave `:::js` alone unless the change is shared.54 - Prefer updating the owning page over creating a new page. If a new page is required, also plan the `src/docs.json` navigation update.55 - Load the `ship-docs-update` skill and ship that feature alone with the research report's `evidence` as `evidence_json`.564. After shipping, append the release tag, feature name, Linear URL, and PR URL to `/memories/agent/deepagents-releases.md`.575. Keep `/memories/agent/AGENTS.md` short: last processed Deep Agents tag and date, alongside other products.5859## Memory format6061Use cold memory file `/memories/agent/deepagents-releases.md`:6263```md64# Deep Agents release tracking6566## deepagents==0.7.2467- feature: async subagent fork mode68 - linear: https://linear.app/...69 - pr: https://github.com/langchain-ai/docs/pull/...70```