rememberCurate persistent memory that actually helps. Filter what matters, organize by function, decay what doesn't.
Install via ClawdBot CLI:
clawdbot install ivangdavila/rememberStoring everything creates noise. Wrong retrieval is worse than no memory. The goal isn't maximum recall ā it's retrieving the right thing at the right time.
High value (persist indefinitely):
Medium value (persist with review):
Low value (don't persist):
Structure by how you'll retrieve it. Adapt categories to your domain:
memory/
āāā commitments.md # Promises, deadlines (with dates!)
āāā preferences.md # Likes/dislikes, style, boundaries
āāā corrections.md # Mistakes not to repeat
āāā decisions.md # What was decided and why
āāā relationships.md # People, roles, context
āāā contexts/ # Per-project or per-client state
āāā {name}.md
Every entry needs:
Prune aggressively:
archive/The staleness test: "If retrieved in 6 months, will this help or mislead?"
When new info conflicts with old:
[Updated 2026-02-11] Was: X, Now: YSee categories.md for domain-specific templates.
See consolidation.md for the review/prune process.
Related: reflection (self-evaluation), loop (iterative refinement)
Generated Mar 1, 2026
An AI agent uses the Remember skill to track customer preferences and past issues, ensuring personalized support. It stores corrections like 'customer dislikes automated responses' and commitments such as 'follow up on ticket #123 by Friday'. This reduces repetition and improves satisfaction by recalling relevant history.
In a software development team, the AI organizes project states, decisions, and team roles in memory. It keeps track of deadlines in commitments.md and updates context files for active projects, helping teams stay aligned and avoid redundant discussions during meetings.
The AI curates user health preferences and goals, storing data like dietary restrictions in preferences.md and workout commitments. It prunes outdated information to prevent misleading advice, ensuring recommendations are based on current, high-value insights for personalized coaching.
An AI agent uses the skill to remember case-specific decisions, client relationships, and legal corrections. It organizes information by function, such as storing precedents in decisions.md and client boundaries in relationships.md, aiding in accurate retrieval for case preparation and avoiding errors.
Offer the Remember skill as part of a monthly subscription for businesses, providing enhanced memory management for customer interactions. Revenue comes from tiered plans based on storage capacity and integration features, targeting SMEs needing persistent AI memory.
Sell licenses to large corporations for integrating the skill into internal AI systems, such as project management or CRM tools. Revenue is generated through one-time setup fees and annual maintenance contracts, focusing on scalability and custom domain templates.
Provide a free basic version of the skill for individual users, with premium upgrades for advanced features like automated pruning and multi-context support. Revenue streams from in-app purchases and ads in the free tier, appealing to developers and small teams.
š¬ Integration Tip
Integrate the skill by mapping its memory categories to existing data structures, such as linking commitments.md to task management systems, and ensure regular review cycles to maintain memory hygiene.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Perform a comprehensive read-only security audit of Clawdbot's own configuration. This is a knowledge-based skill that teaches Clawdbot to identify hardening opportunities across the system. Use when user asks to "run security check", "audit clawdbot", "check security hardening", or "what vulnerabilities does my Clawdbot have". This skill uses Clawdbot's internal capabilities and file system access to inspect configuration, detect misconfigurations, and recommend remediations. It is designed to be extensible - new checks can be added by updating this skill's knowledge.
Use when reviewing code for security vulnerabilities, implementing authentication flows, auditing OWASP Top 10, configuring CORS/CSP headers, handling secrets, input validation, SQL injection prevention, XSS protection, or any security-related code review.
Security check for ClawHub skills powered by Koi. Query the Clawdex API before installing any skill to verify it's safe.
Scan Clawdbot and MCP skills for malware, spyware, crypto-miners, and malicious code patterns before you install them. Security audit tool that detects data exfiltration, system modification attempts, backdoors, and obfuscation techniques.