Official agent skill

Update Integrations PRs

by langchain-ai in langchain-ai/docs

Process open LangChain docs integration PRs against the hosted-guide featuring policy (50K monthly downloads or maintainer feature override).

OfficialMITAuto-check passedAI & LLM Engineering

Install Update Integrations PRs

skills CLI
$ npx skills add langchain-ai/docs --skill update-integrations-prs -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install langchain-ai/docs update-integrations-prs --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/langchain-ai/docs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/update-integrations-prs .claude/skills/update-integrations-prs && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
update-integrations-prs
GitHub stars
426
Token cost
~1.7k tokens
SKILL.md length
677 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

Process open LangChain docs integration PRs against the hosted-guide featuring policy (50K monthly downloads or maintainer feature override).

  • Works in 4 steps: Inspect the current branch → Measure downloads → Rebase → …
  • Tasks that involve Building AI agents
  • SKILL.md covers Policy, Workflow checklist, Hard rules and Common pitfalls, plus 1 more section
  • Calls git, curl and gh; reaches pypistats.org and api.npmjs.org

What it does

Update Integrations PRs is an agent skill from langchain-ai/docs, published by the product's own GitHub organization. Process open LangChain docs integration PRs against the hosted-guide featuring policy (50K monthly downloads or maintainer feature override). Rebase an integration PR, convert to external YAML, feature an integration, or check package downloads for docs eligibility.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Building AI agents. It works with LangChain and npm. The repository describes itself as: Unified LangChain documentation. The licence is MIT.

When your agent uses it

  • Tasks that involve Building AI agents

Example prompts

  • “/update-integrations-prs”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Inspect the current branch
  2. Measure downloads
  3. Rebase
  4. Commit and handoff

What it can do on your machine

Read from SKILL.md and the folder at commit be3028f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • curl
    • gh
    • python3
    • make

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • pypistats.org
    • api.npmjs.org

    Also links to:

    • docs.langchain.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Update Integrations PRs loads about 1.7k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 677 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from langchain-ai/docs at commit be3028f, republished under its MIT licence (© langchain-ai). 677 words, ~1,742 tokens.

Download SKILL.mdSave it as .claude/skills/update-integrations-prs/SKILL.md (or your agent's skills folder).
name
update-integrations-prs
description
Process open LangChain docs integration PRs against the hosted-guide featuring policy (50K monthly downloads or maintainer feature override). Rebase an integration PR, convert to external YAML, feature an integration, or check package downloads for docs eligibility.

Update integrations PRs

Process contributor integration docs PRs in langchain-ai/docs so they match the hosted-guide eligibility rules from #4865.

For new listings filed as GitHub issues (issue form + integration-submission label), use the submit-integration skill instead. That path creates listing changes for CI to open a PR.

Policy

CaseAction
≥50K monthly downloads (PyPI or npm) or maintainer feature overrideKeep hosted MDX. Ensure correct integration: frontmatter. May set highlight: true in packages.yml and regenerate overview via partner_pkg_table (never hand-edit overview.mdx).
Under 50K, not featuredRemove hosted pages. Add YAML to scripts/data/integration_external_docs.yaml. Surface via downloads tables / all_providers. Prefer partner docs URLs. Keep packages.yml when there is a public LangChain-related package.

Policy source: src/oss/contributing/publish-langchain.mdx and src/oss/contributing/integrations-langchain.mdx.

Workflow checklist

Copy and track:

- [ ] Identify PR + package name(s)
- [ ] Report monthly downloads (PyPI and/or npm)
- [ ] Decide: hosted/feature vs external
- [ ] Rebase onto upstream/main (keep contributor commits)
- [ ] Apply conversion in a **separate** commit
- [ ] Verify net diff vs main
- [ ] Report result; do **not** push unless asked
1. Inspect the current branch
bash
git branch --show-current
gh pr view --json number,title,url,author,maintainerCanModify,files,body
git diff --stat upstream/main...HEAD

Find the LangChain-related package name(s) from packages.yml, MDX install snippets, or registry metadata. Ignore unrelated packages with similar names.

2. Measure downloads

PyPI (last ~30 days, no mirrors):

bash
curl -s "https://pypistats.org/api/packages/<pkg>/overall?mirrors=false" \
  | python3 -c "import sys,json; d=json.load(sys.stdin); data=d.get('data',[]); last30=data[-30:] if len(data)>=30 else data; print(sum(x.get('downloads',0) for x in last30))"
curl -s "https://pypistats.org/api/packages/<pkg>/recent"

npm (last month):

bash
curl -s "https://api.npmjs.org/downloads/point/last-month/<pkg>"

Report the number to the user before converting when they asked for downloads only.

3. Rebase
bash
git fetch upstream main
git rebase upstream/main
  • Keep contributor commits; put the conversion in a new commit after rebase.
  • On heavy merge history, cherry-pick content commits onto upstream/main, then convert.
  • Drop obsolete Card grids that main replaced with IntegrationDownloads.
  • Drop redirects for pages that were never on main.
  • Drop unrelated packages.yml download-count churn from bot commits.
4a. External conversion (under 50K)
  1. Delete hosted MDX (component page and provider page if present).

  2. Add YAML under the correct language + component in scripts/data/integration_external_docs.yaml:

    yaml
    - name: ClassOrDisplayName
      pypi: langchain-example   # or npm: "@org/pkg" under javascript:
      docs_url: https://partner.example/docs

    Prefer partner docs, then public GitHub/GitLab README, then PyPI/npm.

  3. Downloads snippet (sort by data-sort-value): add a row to the matching src/snippets/oss/*-*-downloads.mdx (for example python-sandboxes-downloads.mdx). Match existing badge markup.

  4. all_providers: card with external href (alphabetical). Use icon="link" or an existing provider icon.

  5. packages.yml: append only for a public LangChain-related package. Ensure a trailing newline before appending. Omit path: .. Skip if the source repo is private or not a normal public VCS listing.

  6. Nav / redirects: remove docs.json entries and redirects for deleted never-on-main pages. Do not add redirects for pages that never shipped.

  7. Deep Agents / indexes: if the PR added provider cards that main no longer uses, prefer downloads tables and index grids; keep brief mentions only when main already lists providers that way.

Align listings with partner docs, not stale PR page counts.

Show full SKILL.md (294 more words)Show less
  1. Keep (or fix) hosted MDX; test code examples when touching them.
  2. Frontmatter: follow templates under src/oss/*/integrations/**/TEMPLATE.mdx. Do not set featured: true unless a maintainer asked.
  3. Prefer langchain imports over langchain_core when editing kept pages.
  4. For featuring: set highlight: true in packages.yml only when asked; regenerate overview with the partner package table tool, do not hand-edit overview.mdx.
  5. Update src/docs.json if adding a page that should stay.
5. Commit and handoff
  • Conversion commit message focuses on why (threshold / external listing / feature).
  • Show git diff --stat upstream/main...HEAD and downloads in the summary.
  • Note maintainerCanModify for push later.
  • Do not push unless the user asks. Use force-with-lease after rebase when pushing to the PR head.
  • If maintainerCanModify: false, say so and ask whether to open a replacement PR.

Hard rules

  • Ask for clarification rather than assuming package identity or feature overrides.
  • Never fabricate download counts, docs URLs, or package names.
  • Never edit build/.
  • Never hand-edit generated overview tables.
  • When appending to packages.yml, ensure a trailing newline first.
  • Run make lint_prose FILES="..." on changed MDX before handoff when prose changed.
  • Follow repo git safety: no bare git push; no force to main; no commit unless asked (except when the user said "go" / "next branch" for this workflow, commit the conversion).

Common pitfalls

PitfallFix
Wrong package (similar name on PyPI)Confirm against install snippets and partner repo
Re-adding Card grids removed on mainUse IntegrationDownloads / YAML only
Redirects for never-shipped pagesDelete them
Duplicate table rowsRemove YAML if keeping hosted page
Private source repoSkip incomplete packages.yml entry
JS + Python packagesAdd both YAML sections / download rows when both exist

Reference

  • Eligibility docs: /oss/contributing/publish-langchain#eligibility-for-hosted-guides
  • YAML data: scripts/data/integration_external_docs.yaml
  • Downloads snippets: src/snippets/oss/*-downloads.mdx
  • Package registry: packages.yml
  • Policy PR: https://github.com/langchain-ai/docs/pull/4865

© langchain-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/update-integrations-prs of langchain-ai/docs.

Open the folder on GitHubat commit be3028f

Compare with similar skills

Update Integrations PRs next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Update Integrations PRs compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Update Integrations PRs this skilllangchain-ai/docs426—~1.7kAutomated safety check: PassMIT
Mem0 Platform SDKmem0ai/mem067k1 repos~2.2kAutomated safety check: PassApache-2.0
LangSmith Trace DebuggingComposioHQ/awesome-claude-skills77k8 repos~2.7kAutomated safety check: PassNone
Add Example AgentGetBindu/Bindu10k—~1.1kAutomated safety check: NotesCustom licence
Failproof AI SDK IntegrationFailproofAI/failproofai5.3k—~6kAutomated safety check: PassCustom licence
Edgeone Makers MigrationTencentEdgeOne/edgeone-makers-tools1.9k1 repos~4.1kAutomated safety check: PassMIT

Similar skills

  • Adds persistent memory to AI apps with the Mem0 Python and TypeScript SDKs: store, search, update and delete user memories, with framework integrations.

    67k GitHub starsUsed in 1 repo~2.2k tokens
    AI & LLM EngineeringAuto-check passed
  • LangSmith Trace Debugging

    ComposioHQ/awesome-claude-skills

    Debugs LangChain and LangGraph agents by pulling recent execution traces with the langsmith-fetch CLI and reporting errors, tool calls, timings and token use.

    77k GitHub starsUsed in 8 repos~2.7k tokens
    AI & LLM EngineeringAuto-check passed
  • Add Example Agent

    GetBindu/Bindu

    Add a new self-contained example agent under examples/. An agent skill from GetBindu/Bindu.

    10k GitHub stars~1.1k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check: notes
  • Failproof AI SDK Integration

    FailproofAI/failproofai

    Helps instrument a custom Python or TypeScript agent to record events for Failproof AI, verify what gets written, and run an evaluator worker that scores the runs.

    5.3k GitHub stars~6k tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed
  • Edgeone Makers Migration

    TencentEdgeOne/edgeone-makers-tools

    Migrate existing AI agent projects (LangChain, LangGraph, OpenAI Agents SDK, Claude Agent SDK, CrewAI) to EdgeOne Makers platform conventions.

    1.9k GitHub starsUsed in 1 repo~4.1k tokens
    AI & LLM EngineeringAuto-check passed
  • Synalinks

    SynaLinks/synalinks-skills

    A skill your agent uses for anything involving the Synalinks neuro-symbolic LM framework (Keras-inspired): DataModel/Field/Input, JSON operators (+ & | ^ ~), synalinks.ops…

    907 GitHub stars~4.8k tokensUpdated 11 days ago
    AI & LLM EngineeringAuto-check passed

More from langchain-ai/docs

All 17 skills in this repo
  • Add Docs Page

    langchain-ai/docs

    Official

    Add, move, rename, or delete a page on the LangChain docs site.

    426 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Deep Agents

    langchain-ai/docs

    Official

    Build batteries-included agents with planning, context management, subagent delegation, and sandboxed execution.

    426 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Docs Code Samples

    langchain-ai/docs

    Official

    A skill your agent uses when migrating inline code samples from LangChain docs (MDX files) into external, testable code files that are extracted by this repo’s snippet scripts and used as Mintlify…

    426 GitHub stars~4.6k tokensUpdated today
    Auto-check passed
  • Docs Edit

    langchain-ai/docs

    Official

    Edit a docs page that already has an open pull request, or revise a page in place.

    426 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Docs Restructure

    langchain-ai/docs

    Official

    Restructure documentation that spans several pages. An agent skill from langchain-ai/docs.

    426 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Docs Team Voice

    langchain-ai/docs

    Official

    Write or revise documentation prose so it reads like the rest of this site, in the docs team's shared voice.

    426 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

Works with

Questions about Update Integrations PRs

What does Update Integrations PRs do?

Process open LangChain docs integration PRs against the hosted-guide featuring policy (50K monthly downloads or maintainer feature override). Update Integrations PRs is an agent skill from langchain-ai/docs, published by the product's own GitHub organization. Process open LangChain docs integration PRs against the hosted-guide featuring policy (50K monthly downloads or maintainer feature override).

When should I use Update Integrations PRs?

Update Integrations PRs fits situations like: tasks that involve Building AI agents.

How do I install Update Integrations PRs in Claude Code?

Run `npx skills add langchain-ai/docs --skill update-integrations-prs -a claude-code`. Or copy the skill folder (.agents/skills/update-integrations-prs in langchain-ai/docs) into .claude/skills/update-integrations-prs in your project. Claude Code loads it when a task matches its description.

How do I install Update Integrations PRs in Codex?

Run `npx skills add langchain-ai/docs --skill update-integrations-prs -a codex`. Or copy the skill folder (.agents/skills/update-integrations-prs in langchain-ai/docs) into .agents/skills/update-integrations-prs in your project. Codex loads it when a task matches its description.

Can I use Update Integrations PRs in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add langchain-ai/docs --skill update-integrations-prs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/update-integrations-prs, .gemini/skills/update-integrations-prs, .github/skills/update-integrations-prs and .opencode/skills/update-integrations-prs in your project.

What does Update Integrations PRs need to run?

Going by SKILL.md and its folder, Update Integrations PRs needs the command-line tools its instructions call (git, curl, gh, python3 and make). Our summary lists: Python 3.

Does Update Integrations PRs access the network?

SKILL.md names 3 domains. In commands or code: pypistats.org and api.npmjs.org; the agent is likely to contact these when it follows the instructions. As links in the text: docs.langchain.com. This is read from the text; nothing was executed.

Is Update Integrations PRs safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Update Integrations PRs use?

Update Integrations PRs is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Update Integrations PRs use?

About 1.7k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Update Integrations PRs?

Skills that share tags, products or a category with Update Integrations PRs: Mem0 Platform SDK (mem0ai/mem0, 67k stars), LangSmith Trace Debugging (ComposioHQ/awesome-claude-skills, 77k stars), Add Example Agent (GetBindu/Bindu, 10k stars) and Failproof AI SDK Integration (FailproofAI/failproofai, 5.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Update Integrations PRs?

langchain-ai (a GitHub organization, an official publisher) maintains it in langchain-ai/docs, which has 426 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 9, 2026.

Source: langchain-ai/docs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.