clawgraphAutomatically store explicit durable user facts and recall them later; do not infer or upgrade weak signals
Install via ClawdBot CLI:
clawdbot install clawgraphai/clawgraphGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/clawgraph/clawgraphAudited Apr 17, 2026 · audit v1.0
Generated May 20, 2026
A user stores facts about friends, family, and colleagues like names, preferences, relationships, and important dates. The skill recalls these details across conversations, enabling personalized interactions without manual note-taking.
Team members store project-specific facts such as roles, deadlines, dependencies, and decisions. The graph enables quick retrieval of context, reducing onboarding time and preventing information silos.
Support agents store durable facts about customer accounts, past issues, and preferences. Subsequent interactions automatically recall context, improving resolution speed and customer satisfaction.
A researcher stores facts from papers, experiments, and hypotheses. The knowledge graph surfaces connections between concepts and avoids duplication of effort.
Individuals store health-related facts such as allergies, medications, exercise routines, and dietary preferences. The graph enables holistic recall and trend identification over time.
Offer a free tier with limited fact storage (e.g., 500 facts) and a premium subscription for unlimited storage, advanced querying, and team sharing. Revenue comes from monthly or annual subscriptions.
Sell access to clawgraph as a managed service integrated with existing enterprise tools (Slack, Jira). Charge per user per month or based on graph size and query volume.
Keep the core open-source to drive adoption, and offer paid support, custom integrations, and on-premise deployment assistance for enterprises.
💬 Integration Tip
Always use --output json for machine-parseable results; for batch facts, use add-batch to reduce API calls and cost.
Scored May 20, 2026
Structured reasoning through sequential thinking — break complex problems into steps, solve each independently, verify consistency, synthesize conclusions wi...
LLM-driven epistemic reasoning engine. Evaluates claims against evidence, outputs calibrated confidence and structured belief state (VERIFIED/CONTESTED/UNCER...
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context duri...
Turn scattered local sources into a source-constrained evidence notebook for incident, release, and maintainer decisions.
三级记忆管理系统 (Three-Tier Memory Management)。用于管理 AI 代理的短期、中期、长期记忆。包括:(1) 滑动窗口式短期记忆,(2) 自动摘要生成中期记忆,(3) 向量检索长期记忆 (RAG)。当需要管理对话历史、优化上下文、构建个人知识库、或实现记忆持久化时使用此 Skill。
Store secrets, long-term memory, daily logs, and anything custom in your Convex backend instead of local files