ReddRadar
Agent skill
episodic-archiver
Episodic Memory Archiver. Stores full conversation transcripts with embeddings and analysis into ArangoDB. Tracks UNRESOLVED sessions for reflection.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/episodic-archiver
Metadata
Additional technical details for this skill
- short description
- Analyzes and stores episodic conversation memory
SKILL.md
Episodic Archiver
Analyzes conversation transcripts, embeds them for search, categorizes turns, and tracks unresolved sessions for later reflection.
Commands
# Archive a conversation transcript
./run.sh archive transcript.json
# List unresolved sessions (for reflection)
./run.sh list-unresolved
# Mark a session as resolved after follow-up
./run.sh resolve <session_id>
Unresolved Session Tracking
When archiving, the skill analyzes if the session was resolved:
| Condition | Result |
|---|---|
| Session ends with error | Unresolved |
| Session ends with unanswered question | Unresolved |
| Errors without following solutions | Unresolved |
| Tasks without completion | Unresolved |
Unresolved sessions are stored in unresolved_sessions collection for reflection.
Integration with /learn
# Reflect on past failures to find what to learn
/learn --from-gaps --scope horus_lore
# This queries:
# 1. unresolved_sessions (high priority)
# 2. agent_conversations (errors, questions)
# 3. Skill logs (failures)
The Reflection Loop
Session ends → Archive → Detect unresolved → Store gap
↓
/learn --from-gaps
↓
Curiosity targets
↓
/dogpile → /learn
↓
Knowledge acquired
↓
./run.sh resolve <session>
Storage
Collections:
agent_conversations- Individual turns with embeddingsunresolved_sessions- Sessions needing follow-up
Turn categories: Task, Question, Solution, Error, Chat, Meta
Input Format
{
"session_id": "task_123",
"messages": [
{"from": "User", "content": "Fix the bug in auth", "timestamp": 1234567890},
{"from": "Agent", "content": "Looking at auth.py...", "timestamp": 1234567891}
]
}
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?