Back to list
b17z

knowledge

by b17z

Stop losing context. Checkpoint your AI research and recall it later. A Plugin and CLI for context preservation: semantic checkpoints, knowledge recall, session handoffs

1🍴 1📅 Jan 24, 2026

SKILL.md


name: knowledge description: > Recall and save insights using sage_recall_knowledge and sage_save_knowledge MCP tools. INVOKE WHEN: user asks "what do we know about", "recall", "remember this"; starting research on a topic that may have prior knowledge; user wants to save an insight for future use. DO NOT INVOKE: for general questions without stored context.

Knowledge Recall Skill

You have access to a knowledge base of stored insights, decisions, and research findings. When a query relates to stored knowledge, relevant items are automatically injected into your context.

How It Works

Knowledge items are stored in ~/.sage/knowledge/ with keyword triggers. When your query matches those triggers, the relevant knowledge is automatically recalled and injected.

You'll see a notification like:

📚 Knowledge recalled (2)
   ├─ gdpr-summary (~450 tokens)
   └─ consent-patterns (~280 tokens)

What Gets Stored as Knowledge

Knowledge items capture durable insights that are useful across sessions:

TypeExample
Research conclusions"GDPR Article 6 requires explicit consent for AI training"
Validated decisions"We chose PostgreSQL over MongoDB because..."
Domain expertiseAPI patterns, regulatory summaries, technical constraints
User preferences"Prefers academic sources", "Wants concise answers"
Project contextTech stack, architecture decisions, constraints

Storage Structure

~/.sage/knowledge/
├── index.yaml              # Registry with triggers
├── global/                 # Available to all skills
│   └── api-patterns.md
└── skills/                 # Skill-scoped knowledge
    └── privacy/
        └── gdpr-summary.md

Knowledge Item Format

Each item has:

  • id: Unique identifier
  • keywords: Trigger words for matching
  • scope: Which skills can access it (empty = all)
  • content: The actual knowledge (markdown)
  • source: Where it came from (optional)

Adding Knowledge

Via CLI

sage knowledge add notes.md --id gdpr-summary --keywords "gdpr,privacy,consent"
sage knowledge add api-guide.md --id api-patterns --keywords "api,rest" --skill web-dev

Via Conversation

Say "save this as knowledge" or "remember this" after discovering something worth preserving:

You: That's really useful about GDPR consent. Remember this.
Claude: [Extracts key insight and saves to knowledge base]
        Saved knowledge: gdpr-consent-requirements
        Keywords: gdpr, consent, legal basis

Querying Knowledge

Automatic

Just ask questions. If your query matches stored knowledge, it's injected automatically.

Manual

You: What do we know about GDPR?
Claude: [Recalls and presents relevant stored knowledge]

Test Matching

sage knowledge match "How does GDPR affect our API?"

Behavior

  • Automatic: Knowledge is recalled based on query keywords—no explicit request needed
  • Additive: Multiple items can be recalled if relevant (up to token limit)
  • Scoped: Skill-specific knowledge only appears when using that skill
  • Transparent: Always shows what was recalled and token cost

Score

Total Score

60/100

Based on repository quality metrics

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

0/10
説明文

100文字以上の説明がある

+10
人気

GitHub Stars 100以上

0/15
最近の活動

3ヶ月以内に更新がある

0/10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

0/5

Reviews

💬

Reviews coming soon