saas-agent-talent-strategy
Use when producing or reviewing the saas agent talent strategy component of a business plan; applies its specialist evidence, decisions, and acceptance tests…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
ai-agent-memory-erasure-proof
Use when proving agent-memory erasure was complete and verifiable for GDPR / CCPA / POPIA / KE DPA requests — the 9-step cascade verification job emits a…
ai-agents-tools
Use when building AI features that need to take actions, use multiple tools, or execute multi-step workflows — agent patterns, tool integration, ReAct loop,…
ai-architecture-patterns
Integration architecture for AI-powered features — AI Module Gate, Token Ledger schema, Budget Guard, provider abstraction, RAG, function calling, and…
deepseek-integration
Integrate DeepSeek AI models into apps — DeepSeek V3 (general), R1 (reasoning/CoT), API setup (OpenAI-compatible), local deployment with Ollama, distilled…
llm-security
Use when building any AI-powered feature or LLM-integrated endpoint — covers OWASP Top 10 for LLMs, trust boundaries, prompt injection defense, data leakage…
scenario-planning-skill
Scenario Planning thinking tool. By constructing multiple plausible and structurally different future scenarios, it helps decision-makers change their mental models and formulate robust strategies under deep uncertainty. Trigger words: "Scenario Planning", "scenario planning", "coping with uncertainty", "future forecasting", "strategic foresight".
flywheel-qa
Agentic QA for flywheel PRs. Navigate preview deploy with Agent Browser, verify UI renders, check for error boundaries, test interactive flows. Use when: PR…
orchestrator
Switch into an explicit orchestration mode that plans work with the user, delegates almost all execution to subagents, coordinates parallel workstreams, and…
linear-ticket
Create or update a Linear ticket, including its description, metadata, estimate, native relations, and saved-field verification. Use for ticket writes within…
custom-agent-creator
Creates new agents using markdown, with frontmatter and a best-practices structured body—purpose, up to 3 goals, personality, I/O, and enabled skills. Inspired…
context-engineering-global
Do context engineering for the global rules file. Applies to reviewing or rewriting global context files such as ~/.claude/CLAUDE.md, judging whether a long-term rule should enter the global layer, or optimizing collaboration constraints that take effect across projects, tasks, and sessions. Trigger words include: global prompt, global context, CLAUDE.md optimization, system…
system-prompt-tuning
Evaluate and optimize the global context (~/.claude/CLAUDE.md). Use when the user wants to adjust the global prompt, give feedback on friction in Claude Code collaboration, propose changes to the global context, or request a review of the existing global context against official standards. Trigger words include: global prompt, CLAUDE.md optimization, global context, system prompt, global…
rag-systems
Retrieval Augmented Generation systems with vector search, document processing, and hybrid retrieval.
ar
Augmented reality (AR) reality tech. Passthrough overlays, hit-test/anchors, occlusion, lighting, camera permissions, and safety.
onboarding-agent
Interactive onboarding workflow that interviews users to understand their coding goals and generates PR-ready implementation plans. Use when starting a new…
xr
Extended reality (XR/MR) reality tech. Mixed reality and spatial computing across AR and VR capabilities.
signals-scout-llm-analytics
Focused Signals scout for PostHog projects using LLM analytics. Watches `$ai_generation`, `$ai_evaluation`, `$ai_trace` and related events for cost spikes,…
creating-experiments
Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics. Delegates rollout decisions…
exploring-llm-clusters
Investigate AI observability clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into…
exploring-llm-evaluations
Investigate AI observability evaluations — `hog` (deterministic code-based), `llm_judge` (LLM-prompt-based), and `sentiment` (user-message sentiment). Find…
exploring-llm-traces
ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g.…
feature-usage-feed
Set up an LLM-judge evaluation that extracts canonical use cases for a PostHog feature at scale and streams the results to a Slack channel as a live feed. Use…
skills-store
Discover and use shared team skills stored in PostHog. Use when the user asks to list, browse, load, or manage "shared skills", "team skills", or references…