Context Recovery

---

name: context-recovery description: Automatically recover working context after session compaction or when continuation is implied but context is missing. Works across Discord, Slack, Telegram, Signal, and other supported channels. homepage: https://github.com/PSPDFKit-labs/agent-skills repository: https://github.com/PSPDFKit-labs/agent-skills metadata: { "openclaw": { "emoji": "🔄", }, }

---

Context Recovery

Automatically recover working context after session compaction or when continuation is implied but context is missing. Works across Discord, Slack, Telegram, Signal, and other supported channels.

Use when: Session starts with truncated context, user references prior work without specifying details, or compaction indicators appear.

---

Safety Boundaries

This skill prioritizes channel/session API history to recover context.

It does NOT perform broad filesystem scans or shell glob searches by default.

It does NOT send recovered context to external services.

It does NOT write to disk unless the user explicitly asks to persist recovered state.

Triggers

Automatic Triggers

Session begins with a

tag (compaction detected)

User message contains compaction indicators: "Summary unavailable", "context limits", "truncated"

Manual Triggers

User says "continue", "did this happen?", "where were we?", "what was I working on?"

User references "the project", "the PR", "the branch", "the issue" without specifying which

User implies prior work exists but context is unclear

User asks "do you remember...?" or "we were working on..."

---

Execution Protocol

Step 1: Detect Active Channel

Extract from runtime context:

channel — discord | slack | telegram | signal | etc.

channelId — the specific channel/conversation ID

threadId — for threaded conversations (Slack, Discord threads)

Step 2: Fetch Channel History (Adaptive Depth)

Initial fetch:

message:read
  channel: 
  channelId: 
  limit: 50

Adaptive expansion logic: 1. Parse timestamps from returned messages 2. Calculate time span: newest_timestamp - oldest_timestamp 3. If time span < 2 hours AND message count == limit: - Fetch additional 50 messages (using before parameter if supported) - Repeat until time span ≥ 2 hours OR total messages ≥ 100 4. Hard cap: 100 messages maximum (token budget constraint)

Thread-aware recovery (Slack/Discord):

# If threadId is present, fetch thread messages first
message:read
  channel: 
  threadId: 
  limit: 50
Then fetch parent channel for broader context
message:read
  channel: 
  channelId: 
  limit: 30

Parse for:

Recent user requests (what was asked)

Recent assistant responses (what was done)

URLs, file paths, branch names, PR numbers

Incomplete actions (promises made but not fulfilled)

Project identifiers and working directories

Step 3: Fetch Session Context (safe mode)

Use platform/session APIs only (no shell filesystem scans):

# List recent sessions (if tool exists)
sessions_list:
  limit: 5
Pull last messages from likely matching session
sessions_history:
  sessionKey: 
  limit: 80
  includeTools: true

If session APIs are unavailable, skip this step and proceed with channel-only evidence.

Step 4: Optional Memory Check (explicitly scoped)

Only inspect memory if the agent runtime already provides a scoped memory tool/path. Do not run shell glob scans across home directories.

Step 5: Synthesize Context

Compile a structured summary:

## Recovered Context
Channel: # ()
Time Range:  to 
Messages Analyzed: 
Active Project/Task
Repository: 
Branch: 
PR: # —