docs: normalize frontmatter titles to sentence case

docs/concepts/active-memory.md

@@ -1,5 +1,5 @@
 ---
-title: "Active Memory"
+title: "Active memory"
 summary: "A plugin-owned blocking memory sub-agent that injects relevant memory into interactive chat sessions"
 read_when:
   - You want to understand what active memory is for

docs/concepts/agent-loop.md

@@ -3,7 +3,7 @@ summary: "Agent loop lifecycle, streams, and wait semantics"
 read_when:
   - You need an exact walkthrough of the agent loop or lifecycle events
   - You are changing session queueing, transcript writes, or session write lock behavior
-title: "Agent Loop"
+title: "Agent loop"
 ---
 
 # Agent Loop (OpenClaw)

docs/concepts/agent-workspace.md

@@ -3,7 +3,7 @@ summary: "Agent workspace: location, layout, and backup strategy"
 read_when:
   - You need to explain the agent workspace or its file layout
   - You want to back up or migrate an agent workspace
-title: "Agent Workspace"
+title: "Agent workspace"
 ---
 
 The workspace is the agent's home. It is the only working directory used for

docs/concepts/agent.md

@@ -2,7 +2,7 @@
 summary: "Agent runtime, workspace contract, and session bootstrap"
 read_when:
   - Changing agent runtime, workspace bootstrap, or session behavior
-title: "Agent Runtime"
+title: "Agent runtime"
 ---
 
 OpenClaw runs a single embedded agent runtime.

docs/concepts/architecture.md

@@ -2,7 +2,7 @@
 summary: "WebSocket gateway architecture, components, and client flows"
 read_when:
   - Working on gateway protocol, clients, or transports
-title: "Gateway Architecture"
+title: "Gateway architecture"
 ---
 
 ## Overview

docs/concepts/context-engine.md

@@ -4,7 +4,7 @@ read_when:
   - You want to understand how OpenClaw assembles model context
   - You are switching between the legacy engine and a plugin engine
   - You are building a context engine plugin
-title: "Context Engine"
+title: "Context engine"
 ---
 
 A **context engine** controls how OpenClaw builds model context for each run.

docs/concepts/delegate-architecture.md

@@ -1,6 +1,6 @@
 ---
 summary: "Delegate architecture: running OpenClaw as a named agent on behalf of an organization"
-title: Delegate Architecture
+title: Delegate architecture
 read_when: "You want an agent with its own identity that acts on behalf of humans in an organization."
 status: active
 ---

docs/concepts/experimental-features.md

@@ -1,5 +1,5 @@
 ---
-title: "Experimental Features"
+title: "Experimental features"
 summary: "What experimental flags mean in OpenClaw and which ones are currently documented"
 read_when:
   - You see an `.experimental` config key and want to know whether it is stable

docs/concepts/markdown-formatting.md

@@ -4,7 +4,7 @@ read_when:
   - You are changing markdown formatting or chunking for outbound channels
   - You are adding a new channel formatter or style mapping
   - You are debugging formatting regressions across channels
-title: "Markdown Formatting"
+title: "Markdown formatting"
 ---
 
 OpenClaw formats outbound Markdown by converting it into a shared intermediate

docs/concepts/memory-builtin.md

@@ -1,5 +1,5 @@
 ---
-title: "Builtin Memory Engine"
+title: "Builtin memory engine"
 summary: "The default SQLite-based memory backend with keyword, vector, and hybrid search"
 read_when:
   - You want to understand the default memory backend

docs/concepts/memory-honcho.md

@@ -1,5 +1,5 @@
 ---
-title: "Honcho Memory"
+title: "Honcho memory"
 summary: "AI-native cross-session memory via the Honcho plugin"
 read_when:
   - You want persistent memory that works across sessions and channels

docs/concepts/memory-qmd.md

@@ -1,5 +1,5 @@
 ---
-title: "QMD Memory Engine"
+title: "QMD memory engine"
 summary: "Local-first search sidecar with BM25, vectors, reranking, and query expansion"
 read_when:
   - You want to set up QMD as your memory backend

docs/concepts/memory-search.md

@@ -1,5 +1,5 @@
 ---
-title: "Memory Search"
+title: "Memory search"
 summary: "How memory search finds relevant notes using embeddings and hybrid retrieval"
 read_when:
   - You want to understand how memory_search works

docs/concepts/memory.md

@@ -1,5 +1,5 @@
 ---
-title: "Memory Overview"
+title: "Memory overview"
 summary: "How OpenClaw remembers things across sessions"
 read_when:
   - You want to understand how memory works

docs/concepts/model-failover.md

@@ -4,7 +4,7 @@ read_when:
   - Diagnosing auth profile rotation, cooldowns, or model fallback behavior
   - Updating failover rules for auth profiles or models
   - Understanding how session model overrides interact with fallback retries
-title: "Model Failover"
+title: "Model failover"
 ---
 
 OpenClaw handles failures in two stages:

docs/concepts/multi-agent.md

@@ -1,6 +1,6 @@
 ---
 summary: "Multi-agent routing: isolated agents, channel accounts, and bindings"
-title: Multi-Agent Routing
+title: Multi-agent routing
 read_when: "You want multiple isolated agents (workspaces + auth) in one gateway process."
 status: active
 ---

docs/concepts/qa-e2e-automation.md

@@ -4,7 +4,7 @@ read_when:
   - Extending qa-lab or qa-channel
   - Adding repo-backed QA scenarios
   - Building higher-realism QA automation around the Gateway dashboard
-title: "QA E2E Automation"
+title: "QA E2E automation"
 ---
 
 The private QA stack is meant to exercise OpenClaw in a more realistic,

docs/concepts/queue.md

@@ -2,7 +2,7 @@
 summary: "Command queue design that serializes inbound auto-reply runs"
 read_when:
   - Changing auto-reply execution or concurrency
-title: "Command Queue"
+title: "Command queue"
 ---
 
 # Command Queue (2026-01-16)

docs/concepts/retry.md

@@ -3,7 +3,7 @@ summary: "Retry policy for outbound provider calls"
 read_when:
   - Updating provider retry behavior or defaults
   - Debugging provider send errors or rate limits
-title: "Retry Policy"
+title: "Retry policy"
 ---
 
 ## Goals

docs/concepts/session-pruning.md

@@ -1,5 +1,5 @@
 ---
-title: "Session Pruning"
+title: "Session pruning"
 summary: "Trimming old tool results to keep context lean and caching efficient"
 read_when:
   - You want to reduce context growth from tool outputs

docs/concepts/session-tool.md

@@ -4,7 +4,7 @@ read_when:
   - You want to understand what session tools the agent has
   - You want to configure cross-session access or sub-agent spawning
   - You want to inspect status or control spawned sub-agents
-title: "Session Tools"
+title: "Session tools"
 ---
 
 OpenClaw gives agents tools to work across sessions, inspect status, and

docs/concepts/session.md

@@ -3,7 +3,7 @@ summary: "How OpenClaw manages conversation sessions"
 read_when:
   - You want to understand session routing and isolation
   - You want to configure DM scope for multi-user setups
-title: "Session Management"
+title: "Session management"
 ---
 
 OpenClaw organizes conversations into **sessions**. Each message is routed to a

docs/concepts/soul.md

@@ -4,7 +4,7 @@ read_when:
   - You want your agent to sound less generic
   - You are editing SOUL.md
   - You want a stronger personality without breaking safety or brevity
-title: "SOUL.md Personality Guide"
+title: "SOUL.md personality guide"
 ---
 
 `SOUL.md` is where your agent's voice lives.

docs/concepts/streaming.md

@@ -4,7 +4,7 @@ read_when:
   - Explaining how streaming or chunking works on channels
   - Changing block streaming or channel chunking behavior
   - Debugging duplicate/early block replies or channel preview streaming
-title: "Streaming and Chunking"
+title: "Streaming and chunking"
 ---
 
 # Streaming + chunking

docs/concepts/system-prompt.md

@@ -3,7 +3,7 @@ summary: "What the OpenClaw system prompt contains and how it is assembled"
 read_when:
   - Editing system prompt text, tools list, or time/heartbeat sections
   - Changing workspace bootstrap or skills injection behavior
-title: "System Prompt"
+title: "System prompt"
 ---
 
 OpenClaw builds a custom system prompt for every agent run. The prompt is **OpenClaw-owned** and does not use the pi-coding-agent default prompt.

docs/concepts/typing-indicators.md

@@ -2,7 +2,7 @@
 summary: "When OpenClaw shows typing indicators and how to tune them"
 read_when:
   - Changing typing indicator behavior or defaults
-title: "Typing Indicators"
+title: "Typing indicators"
 ---
 
 Typing indicators are sent to the chat channel while a run is active. Use

docs/concepts/usage-tracking.md

@@ -3,7 +3,7 @@ summary: "Usage tracking surfaces and credential requirements"
 read_when:
   - You are wiring provider usage/quota surfaces
   - You need to explain usage tracking behavior or auth requirements
-title: "Usage Tracking"
+title: "Usage tracking"
 ---
 
 ## What it is