Agent Skills

This docs site now publishes Agent Skills so coding agents can discover reusable implementation playbooks directly from your docs URL.

• Open the live skills index: /.well-known/skills/index.json

What gets published

At build time, the docs generate:

• /.well-known/skills/index.json — skill index
• /.well-known/skills/<skill-name>/SKILL.md — canonical skill file

Current published skills (dynamic)

The list below is generated from the live skills collection at build time, and each link points to the published markdown endpoint:

• a2a-specialized-agents — Build specialized multi-agent systems using A2A servers, local agent-tools, and remote-agent delegation.
• context-engineering-optimization — Optimize prompt context for model tier, latency, and token budget using prioritization, compression, and tiered loading.
• cost-budget-enforcement — Enforce per-task, daily, and monthly budgets with complexity-aware routing and graceful degradation.
• gateway-persistent-scheduled-agents — Build persistent scheduled agents with Gateway heartbeats, cron jobs, webhook ingestion, and policy enforcement.
• identity-and-guardrails — Implement secure agent identity, behavioral contracts, and guardrail enforcement for production-safe autonomy.
• mcp-tool-integration — Integrate MCP servers as agent tools for filesystem, GitHub, and external-system workflows.
• memory-consolidation — Configure working, episodic, semantic, and procedural memory with consolidation rules optimized for local and frontier models.
• multi-agent-orchestration — Design and implement reliable multi-agent workflows using sequential, parallel, pipeline, and map-reduce execution patterns.
• observability-instrumentation — Instrument agents with structured traces, events, metrics, and execution-phase diagnostics for production debugging.
• reactive-agents-framework — Build specialized production agents with the Reactive Agents builder using accurate layer composition and use-case-driven configuration.
• reasoning-strategy-selection — Select and configure the right Reactive Agents reasoning strategy for task complexity, latency, and cost constraints.
• streaming-real-time-agents — Build agents that stream tokens and lifecycle events to users in real-time via runStream(), AgentStream adapters, and density modes.
• verification-pipeline-design — Build a layered verification pipeline with semantic entropy, fact decomposition, NLI, multi-source checks, and hallucination detection.

Where skills live

Skills are stored in:

• apps/docs/skills/<skill-name>/SKILL.md

Current example:

• apps/docs/skills/reactive-agents-framework/SKILL.md

Skill format

Each SKILL.md must include frontmatter fields:

• name (string)
• description (string)

Example:

---
name: reactive-agents-framework
description: Design and implement production-grade TypeScript AI agents using Reactive Agents.
---

# Reactive Agents Framework Skill

...

How this is wired

The docs app uses:

• astro-skills integration for discovery routes
• A Starlight-safe custom content loader for the skills collection

Key files:

• apps/docs/astro.config.mjs
• apps/docs/src/content/config.ts
• apps/docs/src/content/skills-loader.ts

Validate locally

Build docs:

bun run docs:build

Verify generated outputs:

cd apps/docs
find dist -maxdepth 8 -type f | grep '.well-known/skills' | sort
cat dist/.well-known/skills/index.json

You should see entries like:

• dist/.well-known/skills/index.json
• dist/.well-known/skills/reactive-agents-framework/SKILL.md

Add a new skill

1. Create a new folder under apps/docs/skills/ using kebab-case (for example, reasoning-optimization).
2. Add SKILL.md with valid name + description frontmatter.
3. Rebuild docs.
4. Confirm the new skill appears in dist/.well-known/skills/index.json.

Why this matters

This lets external agents consume implementation guidance that matches Reactive Agents architecture and conventions, directly from the public docs.