Skip to main content
langchain-ai
Profil créateur GitHub

langchain-ai

Vue par dépôt de 211 skills collectés dans 22 dépôts GitHub.

skills collectés
211
dépôts
22
mis à jour
6 nov. 2026
carte des dépôts

Où se trouvent les skills

Principaux dépôts par nombre de skills collectés, avec leur part dans ce catalogue créateur et leur couverture métier.

#01
design-agent
47 skills · 3 nov. 2026
classification en attente
22 %part
#02
deepagents
26 skills · 26 oct. 2026
Analystes en études de marché et spécialistes en marketingDéveloppeurs de logicielsScientifiques des donnéesAnalystes en assurance qualité des logiciels et testeursAnalystes en sécurité de l'information
5 catégories métier · 81 % classifié
12 %part
#03
docs
24 skills · 29 oct. 2026
Développeurs de logicielsScientifiques des données
2 catégories métier · 25 % classifié
11 %part
#04
langchain-skills
22 skills · 2 oct. 2026
Développeurs de logicielsAutres occupations informatiquesAnalystes en assurance qualité des logiciels et testeurs
3 catégories métier · 91 % classifié
10 %part
#05
skills-benchmarks
22 skills · 25 juin 2026
Développeurs de logicielsAnalystes en assurance qualité des logiciels et testeursAdministrateurs de réseaux et de systèmes informatiquesArchitectes de bases de donnéesAutres occupations informatiquesDéveloppeurs web
6 catégories métier · 100 % classifié
10 %part
#06
lca-deepagents
10 skills · 29 sept. 2026
Analystes en études de marché et spécialistes en marketingReprésentants de vente de services (sauf publicité, assurance, services financiers et voyages)Spécialistes en gestion de projets
3 catégories métier · 90 % classifié
4,7 %part
#07
open-swe
8 skills · 6 nov. 2026
classification en attente
3,8 %part
#08
paid-media-agent
8 skills · 5 oct. 2026
Spécialistes en gestion de projetsAnalystes en études de marché et spécialistes en marketingGraphistes
3 catégories métier · 88 % classifié
3,8 %part
Les 8 principaux dépôts sont affichés ici ; la liste complète continue ci-dessous.
explorateur de dépôts

Dépôts et skills représentatifs

image-generation
non classé

Generate original imagery with the generate_image host tool, such as illustrations, scenes, textures, hero objects, look plates for storyboards and transparent cut-outs. Not for layouts, logos, exact copy, charts or product UI.

3 nov. 2026
brand-onboarding
non classé

Build the active brand pack in workspace/brand/ from a brand guide, website, files or a Paper file, validate it, and have a person review it.

30 oct. 2026
design-agent-deploy
non classé

Put Design Agent in a team's Slack. Deploy it to Managed Deep Agents (one command, managed Slack app) or self-host it with Docker Compose, verify it with a real request, ship updates, and keep a separate test copy. Use when someone wants the agent running for…

26 oct. 2026
design-agent-customize
non classé

Change what Design Agent knows and does. Teach it a new deliverable with a runtime skill, change its instructions, design doctrine or checks, connect MCP servers and tools, or change models and cost caps. Use when someone wants it to make something new,…

23 oct. 2026
design-wiki
non classé

Design doctrine to weigh on any visual. Hierarchy, typography, colour, layout, platform sizes, chart and diagram principles, and the review rubric critics score against.

23 oct. 2026
motion-direction
non classé

Direct and review motion built in HyperFrames, from a sting to a film. The idea and its turn, timing on a grid, craft, named moves, sound on the picture, and the review rubric.

23 oct. 2026
stills
non classé

On-brand still images built as HTML and rendered in a real browser, such as ads and banners in several sizes, social images, carousels, and paged PDFs (one-pagers, booklets, static decks). Not for charts or diagrams (data-viz), thumbnails or motion.

21 oct. 2026
design-agent-troubleshoot
non classé

Diagnose Design Agent when something fails. Setup, a render, a deploy, Slack or a model call. Run doctor and the connection tests, read logs and traces, match the symptom to its fix, and never print credentials. Use when a command errors, a reply never comes,…

21 oct. 2026
Affichage de 8 skills collectés sur 47.
deepagents-plugin-discovery
non classé

Discover plugins from configured dcode marketplaces when a capability is missing or the user asks about available, disabled, not-yet-installed, or outdated plugins and connected marketplaces.

26 oct. 2026
deepagents-thread-inspector
non classé

Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use to look up the current thread's title or name, as a fallback when LangSmith trace tooling is unavailable, for offline or untraced sessions, or when asked to identify or…

22 oct. 2026
configuration-hardening
Analystes en sécurité de l'information

Review Talon tool placement and defensive prompts when requested or when adding or changing tools or subagents; apply confirmed changes and verify active capabilities.

13 oct. 2026
skill-creator
non classé

Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5)…

29 sept. 2026
skill-creator
non classé

Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5)…

29 sept. 2026
safety
non classé

Check secret handling, staged changes and push targets, destructive Git operations, Docker image hygiene, and new dependencies before consequential coding actions. Use for commits, pushes, container builds or publishes, dependency additions, and explicit…

28 sept. 2026
textual-screenshot
Développeurs de logiciels

Capture a Textual terminal UI as an SVG using its headless test harness. Use when asked to make, attach, or preview a screenshot of deepagents-code/dcode or another Textual app, visually verify a TUI state, or render a modal, screen, or widget without a…

28 août 2026
remember
Développeurs de logiciels

Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2)…

26 août 2026
Affichage de 8 skills collectés sur 26.
add-docs-page
non classé

Add, move, rename, or delete a page on the LangChain docs site. Covers choosing the source directory, writing frontmatter, placing the entry in src/docs.json navigation, adding redirects, and verifying with the lint and broken-link gates. Use when asked to…

29 oct. 2026
docs-edit
non classé

Edit a docs page that already has an open pull request, or revise a page in place. Covers checking out the PR's own branch instead of cutting a new one, forked cross-repository PRs, reading the real diff, checking the edit against related pages, and the…

29 oct. 2026
open-docs-pr
non classé

Open a pull request for finished docs changes. Covers cutting the branch from the latest origin/main, the lint and link gates, the commit, writing the PR description in the repo's short format with the AI disclosure line, pushing safely, and watching the PR…

29 oct. 2026
docs-team-voice
non classé

Write or revise documentation prose so it reads like the rest of this site, in the docs team's shared voice. Covers sentence length, cross-link density, how to state defaults and conditions, naming exact identifiers, and what to cut in a revision pass. Use…

29 oct. 2026
ship-docs-update
non classé

Open one Linear DOC ticket and one draft docs PR for a single documentation feature, grounded in product-source evidence.

29 oct. 2026
docs-code-samples
non classé

Use this skill 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 snippets. Applies when extracting code blocks from documentation,…

28 oct. 2026
deep-agents
non classé

Build batteries-included agents with planning, context management, subagent delegation, and sandboxed execution. Use for complex, multi-step tasks that need built-in capabilities.

27 oct. 2026
submit-integration
non classé

Create a LangChain docs integration listing from a structured GitHub issue submission (issue form fields as JSON). Applies the hosted-guide eligibility policy (50K monthly downloads or maintainer feature override), edits YAML / downloads snippets /…

22 oct. 2026
Affichage de 8 skills collectés sur 24.
langgraph-cli
Développeurs de logiciels

INVOKE THIS SKILL when using the langgraph CLI to scaffold, develop, build, or deploy LangGraph applications. Covers langgraph new, dev, build, up, deploy, and langgraph.json configuration.

2 oct. 2026
managed-deep-agents
non classé

INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith. Walks a user through their first agent end to end — interviewing them about what they want to build, mapping it onto what MDA can actually do, then scaffolding and…

2 oct. 2026
langgraph-decision-models
non classé

INVOKE THIS SKILL when routing a LangGraph agent with a decision model (TypeSafe Jev, SemIf) instead of an LLM, or when auditing an existing agent for LLM calls that only produce a routing decision. Covers langchain-typesafe Noul/Choice/Score, reading answers…

25 sept. 2026
langgraph-fundamentals
Développeurs de logiciels

INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.

17 sept. 2026
eval-engineering
Analystes en assurance qualité des logiciels et testeurs

Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable project World Knowledge Skills. Use for agent evals, benchmark design, Task generation, controlled…

20 août 2026
deepagents-python-quickstart
Développeurs de logiciels

Scaffold a minimal local Deep Agent in Python by following the official quickstart, using provider-native web search instead of Tavily. Use when the user wants to quickly build or try a Deep Agent locally.

22 juil. 2026
deepagents-typescript-quickstart
Développeurs de logiciels

Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using provider-native web search instead of Tavily. Use when the user wants to quickly build or try a Deep Agent locally.

22 juil. 2026
langchain-python-quickstart
Développeurs de logiciels

Scaffold a minimal local LangChain agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangChain agent locally.

22 juil. 2026
Affichage de 8 skills collectés sur 22.
deep-agents-orchestration
Autres occupations informatiques

INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.

25 juin 2026
langchain-dependencies
Développeurs de logiciels

INVOKE THIS SKILL when asked about and/or have to implement package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents. Covers required packages, minimum versions, environment requirements, versioning best…

25 juin 2026
langsmith-evaluator
Analystes en assurance qualité des logiciels et testeurs

INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running…

7 juin 2026
langsmith-trace
Développeurs de logiciels

INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Uses the langsmith CLI tool.

7 juin 2026
ecosystem-primer
Développeurs de logiciels

INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required starting point for up to date info on framework selection (LangChain vs LangGraph vs Deep Agents vs hybrid…

21 mai 2026
langsmith-dataset
Développeurs de logiciels

INVOKE THIS SKILL when creating evaluation datasets, uploading datasets to LangSmith, or managing existing datasets. Covers dataset types (final_response, single_step, trajectory, RAG), CLI management commands, SDK-based creation, and example management. Uses…

9 avr. 2026
langchain-middleware
Développeurs de logiciels

INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured…

8 avr. 2026
framework-selection
Développeurs de logiciels

INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent…

4 mars 2026
Affichage de 8 skills collectés sur 22.
qbr-report
non classé

Generate a Quarterly Business Review (QBR) report for the DVD rental business, covering revenue and rental volume with breakdowns by film language, category (genre), and actor. Use whenever someone asks for a QBR, a quarterly report, or a quarterly business…

29 sept. 2026
weekly-newsletter
Analystes en études de marché et spécialistes en marketing

Produce the weekly 'This Week in Music' customer newsletter by researching the distributor's top genres and assembling a styled HTML page. Use when asked to create, write, or send the weekly newsletter or a music-news roundup.

10 sept. 2026
weekly-newsletter
Analystes en études de marché et spécialistes en marketing

Produce the weekly 'This Week in Music' customer newsletter by researching the distributor's top genres in parallel and assembling a styled HTML page. Use when asked to create, write, or send the weekly newsletter or a music-news roundup.

6 août 2026
territory-report
Analystes en études de marché et spécialistes en marketing

Build a report on the rep's sales territory — revenue, top customers, top genres, and trends for Jane's book of business — with a chart. Use when asked for a territory report, sales summary, performance numbers, or 'how is my book doing'.

6 août 2026
territory-report
Analystes en études de marché et spécialistes en marketing

Build a report on the rep's sales territory — revenue, top customers, top genres, and trends for Jane's book of business — with a chart. Use when asked for a territory report, sales summary, performance numbers, or 'how is my book doing'.

21 juil. 2026
weekly-newsletter
Analystes en études de marché et spécialistes en marketing

Produce the weekly 'This Week in Music' customer newsletter by researching the distributor's top genres and assembling a styled HTML page. Use when asked to create, write, or send the weekly newsletter or a music-news roundup.

21 juil. 2026
rfq-quote
Spécialistes en gestion de projets

Process an incoming request for quote (RFQ) from a customer: read the email, look up the customer and catalogue prices, compute a quote, have it reviewed, draft the reply, and log it. Use whenever a customer asks for a price, a quote, or to license/buy a…

20 juil. 2026
territory-report
Analystes en études de marché et spécialistes en marketing

Build a report on the rep's sales territory — revenue, top customers, top genres, and trends for Jane's book of business — with a chart. Use when asked for a territory report, sales summary, performance numbers, or 'how is my book doing'.

6 juil. 2026
Affichage de 8 skills collectés sur 10.
baby-sit
non classé

Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.

6 nov. 2026
html-artifacts
non classé

Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for publish_artifact, output_iframe, or slack_attach_html.

6 nov. 2026
linear-tickets
non classé

Create or update high-quality Linear tickets while preserving the originating report, diagnostic links, attachments, and reporter/requester attribution. Read this whenever someone asks to create, recreate, or update a Linear issue.

6 nov. 2026
web-apps
non classé

Build an app that runs in the Open SWE web UI, preview it beside the thread with preview_app, and release it with publish_app. Read this before building an Open SWE app or plugin.

6 nov. 2026
workspaces
non classé

How a Robin workspace's sandbox image works and how to change it — create one, edit or fork an existing one, start from scratch, what setup_script and update_script are for, why a nightly refresh failed, where the build logs are, and how to read a rebuild in…

6 nov. 2026
local-gh-dev
non classé

Run the Open SWE dashboard locally against real GitHub data, signed in with the `gh` CLI instead of a per-machine GitHub App. Use when asked to run the app locally, test a dashboard change against real PRs, reproduce something a screenshot shows, or when…

28 oct. 2026
writing-pr-body-title-description
non classé

Use when writing or editing a pull request title or body.

27 oct. 2026
dashboard-preview
non classé

Drive this checkout's dashboard (`ui/`) against the shared preview deployment's real threads, with no local backend. Use to verify a UI change in a browser, count the requests a page makes, or compare a page's behaviour before and after a change.

27 oct. 2026
paid-media-wiki
Analystes en études de marché et spécialistes en marketing

The paid-media business wiki the other skills route to. General doctrine on goals, metrics and attribution, the decision model, platform differences, benchmarks, anomalies, bidding and budget, reporting, write safety, and answer style. Read the page a…

5 oct. 2026
paid-media-writes
non classé

Prepare, review, edit, approve, reject, or reconcile a paid-media change while preserving the human approval and provider verification boundary.

5 oct. 2026
paid-media-design
Graphistes

Configure company branding or update report design, tokens, templates, and runtime design guidance. Use during onboarding, when DESIGN.md changes, or when a user requests report styling or layout changes.

14 sept. 2026
paid-media-onboarding
Spécialistes en gestion de projets

Install and configure Paid Media Agent, connect ad platforms, choose MDA or self-hosting, and diagnose setup without exposing credentials.

14 sept. 2026
paid-media-org-onboarding
Spécialistes en gestion de projets

Set up or update a company's paid-media context and runtime skills in the local workspace. Use before deployment or when business goals, measurement, or campaign conventions change.

14 sept. 2026
paid-media-report
Spécialistes en gestion de projets

Build a reconciled paid-media report or executive summary from deterministic analysis results and render it as a shareable artifact.

14 sept. 2026
report-design
Graphistes

Apply company design rules to HTML reports, PDFs, and briefs. Read before creating a shareable document or changing its appearance.

14 sept. 2026
paid-media-analysis
Analystes en études de marché et spécialistes en marketing

Analyze paid-media performance, compare periods or entities, diagnose issues, and make evidence-backed recommendations across connected ad platforms.

13 sept. 2026
arxiv-search
Enseignants postsecondaires, autres

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields

2 avr. 2026
skill-creator
Autres occupations informatiques

Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: create a skill, make a skill, build a skill, set up a skill, initialize a skill, scaffold a…

2 avr. 2026
eval-writer
Analystes en assurance qualité des logiciels et testeurs

Create new eval suites for the deepagentsjs monorepo. Handles dataset design, test case scaffolding, scoring logic, vitest configuration, and LangSmith integration. Use when the user asks to: (1) create an eval, (2) write an evaluation, (3) add a benchmark,…

17 mars 2026
langsmith-trace
Développeurs de logiciels

INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Uses the langsmith CLI tool.

17 mars 2026
file-organizer
Commis de bureau généraux

Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.

23 janv. 2026
langgraph-docs
Développeurs de logiciels

Use this skill for requests related to LangGraph in order to fetch relevant documentation to provide accurate, up-to-date guidance.

9 janv. 2026
web-research
Analystes en études de marché et spécialistes en marketing

Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research

9 janv. 2026
12 dépôts affichés sur 22