Babysitter knowledge-curation
Context priming before work (bd prime) and self-reflection after completion to extract patterns, gotchas, and decisions into the knowledge base.
install
source · Clone the upstream repo
git clone https://github.com/a5c-ai/babysitter
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/methodologies/metaswarm/skills/knowledge-curation" ~/.claude/skills/a5c-ai-babysitter-knowledge-curation && rm -rf "$T"
manifest:
library/methodologies/metaswarm/skills/knowledge-curation/SKILL.mdsource content
Knowledge Curation
Overview
Two-phase knowledge management: prime context before work starts, and extract learnings after work completes. Knowledge persists in JSONL files for cross-session continuity.
When to Use
- Before starting any work (prime mode)
- After completing work, BEFORE PR creation (reflect mode)
- When recovering from context loss (recovery priming)
Knowledge Categories
| Category | File | Content |
|---|---|---|
| Critical Rules | facts.jsonl | MUST FOLLOW constraints |
| Gotchas | gotchas.jsonl | Common pitfalls |
| Patterns | patterns.jsonl | Codebase best practices |
| Decisions | decisions.jsonl | Architectural choices with rationale |
| Anti-Patterns | anti-patterns.jsonl | What NOT to do |
| Codebase Facts | codebase-facts.jsonl | Structural information |
| API Behaviors | api-behaviors.jsonl | Undocumented quirks |
Process
Prime Mode
- Load knowledge base files for work type
- Surface MUST FOLLOW rules first
- Present GOTCHAS and PATTERNS
- Load relevant DECISIONS
Reflect Mode
- Extract patterns from completed work
- Identify gotchas from review failures
- Record architectural decisions with rationale
- Persist to .beads/knowledge/
Tool Use
Invoke via babysitter process:
methodologies/metaswarm/metaswarm-knowledge-cycle