agentsclimarketplace
Sign in

Knowledge curation

Skill a5c-ai/babysitter/library/methodologies/metaswarm/skills/knowledge-curation

Context priming before work (bd prime) and self-reflection after completion to extract patterns, gotchas, and decisions into the knowledge base.From its SKILL.md

Install
npx -y skills add a5c-ai/babysitter --skill knowledge-curation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.6 KB, 248 tokens by cl100k_base, as published. Nobody here has run it

  • After completing work, BEFORE PR creation (reflect mode)
  • When recovering from context loss (recovery priming)

Knowledge Categories

CategoryFileContent
Critical Rulesfacts.jsonlMUST FOLLOW constraints
Gotchasgotchas.jsonlCommon pitfalls
Patternspatterns.jsonlCodebase best practices
Decisionsdecisions.jsonlArchitectural choices with rationale
Anti-Patternsanti-patterns.jsonlWhat NOT to do
Codebase Factscodebase-facts.jsonlStructural information
API Behaviorsapi-behaviors.jsonlUndocumented quirks

Process

Prime Mode

  1. Load knowledge base files for work type
  2. Surface MUST FOLLOW rules first
  3. Present GOTCHAS and PATTERNS
  4. Load relevant DECISIONS

Reflect Mode

  1. Extract patterns from completed work
  2. Identify gotchas from review failures
  3. Record architectural decisions with rationale
  4. Persist to .beads/knowledge/

Tool Use

Invoke via babysitter process: methodologies/metaswarm/metaswarm-knowledge-cycle

What ships with it: 1 file

660 B alongside SKILL.md

Keep looking

Skills are one crate of 326,059. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.