Topic: langchain
98 skills in this topic.
-
redis
Manage Redis databases via the redis-cli tool.
olasunkanmi-SE/codebuddy 118
-
sentry
Manage Sentry projects and releases via the sentry-cli.
olasunkanmi-SE/codebuddy 118
-
telegram
Send Telegram messages, files, and interact with Telegram bots via the telegram-send CLI tool.
olasunkanmi-SE/codebuddy 118
-
test-skill
A minimal test skill for API testing
BerriAI/litellm 42,955
-
test-skill-litellm
A test skill created by LiteLLM automated tests
BerriAI/litellm 42,955
-
test-delete-skill
A test skill created specifically for deletion testing
BerriAI/litellm 42,955
-
slack-gif-creator
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."
BerriAI/litellm 42,955
-
mengram-memory
Long-term memory with 3 types (facts, events, workflows). Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, or tracking completed workflows.
alibaizhanov/mengram 154
-
octopoda-memory
Persistent memory across sessions — recall, store, share, audit decisions, snapshots, and version history
RyjoxTechnologies/Octopoda-OS 109
-
brain_dump
Capture unstructured thoughts and organize them into structured notes saved to memory.
siddsachar/Thoth 113
-
web_navigator
Strategic patterns for effective browser automation — research, forms, and data extraction.
siddsachar/Thoth 113
-
task_automation
Design effective automated workflows using scheduled tasks, prompt chaining, and delivery channels.
siddsachar/Thoth 113
-
self_reflection
Periodically review memory for contradictions, gaps, and stale information.
siddsachar/Thoth 113
-
proactive_agent
Anticipate user needs, ask clarifying questions, and self-check work at milestones.
siddsachar/Thoth 113
-
meeting_notes
Structure raw meeting notes into actionable minutes with follow-ups.
siddsachar/Thoth 113
-
knowledge_base
Manage the user's personal knowledge base — knowledge graph, documents, and wiki vault.
siddsachar/Thoth 113
-
humanizer
Write in a natural, human tone — no AI-speak, no filler, no corporate fluff.
siddsachar/Thoth 113
-
deep_research
Perform multi-source research on a topic and produce a structured report.
siddsachar/Thoth 113
-
data_analyst
Analyses datasets with professional rigour — statistical summaries, clear narratives, and well-chosen visualisations.
siddsachar/Thoth 113
-
daily_briefing
Compile a morning briefing with weather, calendar, and news headlines.
siddsachar/Thoth 113
-
turborepo
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines,
dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment
variables, internal packages, monorepo structure/best practices, and boundaries.
Use when user: configures tasks/workflows/pipelines, creates packages, sets up
monorepo, shares code between apps, runs changed/affected packages, debugs cache,
or has apps/packages directories.
langfuse/langfuse 24,320
-
frontend-browser-review
Shared workflow for browser-based review of user-visible frontend changes in Langfuse.
Use when a change affects UI behavior, layout, styling, navigation, or browser-visible
regressions and should be checked with the Playwright MCP server before signoff.
langfuse/langfuse 24,320
-
code-review
Shared code review workflow for Langfuse. Use when reviewing a PR, branch, diff,
or local changes for correctness, regressions, risk, and missing tests.
Start with references/review-checklist.md for repo-specific review rules and
use package AGENTS.md files plus any matching shared skills when the change
touches those areas.
langfuse/langfuse 24,320
-
clickhouse-best-practices
MUST USE when reviewing ClickHouse schemas, queries, or configurations. Contains 28 rules that MUST be checked before providing recommendations. Always read relevant rule files and cite specific rules in responses.
langfuse/langfuse 24,320