remember
alirezarezvani/claude-skills
Explicitly save important knowledge to auto-memory with timestamp and context.
What is remember?
A skill that writes explicit entries to auto-memory when a discovery is too important to rely on Claude noticing automatically. Use it to capture hard-won debugging insights, project conventions, tool-specific gotchas, architecture decisions, and preferences you want Claude to learn across sessions.
- Save concrete facts and patterns to project-specific MEMORY.md for persistent recall
- Check for duplicate entries before writing to avoid redundant notes
- Suggest promotion to CLAUDE.md when knowledge sounds like an enforced rule
- Warn when MEMORY.md approaches capacity (180+ lines)
- Keep entries concise and actionable with one-line format when possible
How to install remember
npx skills add https://github.com/alirezarezvani/claude-skills --skill rememberHow to use remember
- 1.Use the command /si:remember followed by the knowledge to save
- 2.Keep entries concise — one line when possible, include concrete commands or values
- 3.Claude will check for duplicates and show existing entries if found
- 4.Review the confirmation message showing the entry and current MEMORY.md line count
- 5.If prompted, consider using /si:promote instead for enforced rules that belong in CLAUDE.md
Use cases
- Capture a debugging insight that took hours to discover (e.g., 'CORS errors on /api/upload are caused by the CDN, not the backend')
- Document project conventions not yet in CLAUDE.md (e.g., 'We use barrel exports in src/components/')
- Record tool-specific gotchas (e.g., 'Jest needs --forceExit flag or it hangs on DB tests')
- Preserve architecture decisions made during development (e.g., 'We chose Drizzle over Prisma for type-safe SQL')
- Store developer preferences for code style (e.g., 'Don't add comments explaining obvious code')
- Developers working on projects with Claude Code or Cursor
- Teams building institutional knowledge across coding sessions
- Anyone who discovers non-obvious patterns they want Claude to remember
remember FAQ
/si:remember saves to MEMORY.md for contextual notes that Claude learns across sessions. /si:promote writes to CLAUDE.md for enforced rules with higher priority. Use promote for imperatives (always/never) and conventions that should be strictly followed.
No. Keep entries as concise one-liners without timestamps, IDs, or metadata. They're notes, not database records.
When MEMORY.md reaches 180+ lines, you'll see a warning to run /si:review to free space and consolidate old entries.
No. Don't use it for temporary session context (just tell Claude in conversation), sensitive data like credentials or tokens, or cross-project knowledge (use ~/.claude/CLAUDE.md instead).
If it's a rule, convention, or preference that should always apply (imperative, always/never), promote it to CLAUDE.md. If it's a specific insight or gotcha for this project, remember it to MEMORY.md.
Full instructions (SKILL.md)
Source of truth, from alirezarezvani/claude-skills.
name: "remember" description: "Explicitly save important knowledge to auto-memory with timestamp and context. Use when a discovery is too important to rely on auto-capture."
/si:remember — Save Knowledge Explicitly
Writes an explicit entry to auto-memory when something is important enough that you don't want to rely on Claude noticing it automatically.
Usage
/si:remember <what to remember>
/si:remember "This project's CI requires Node 20 LTS — v22 breaks the build"
/si:remember "The /api/auth endpoint uses a custom JWT library, not passport"
/si:remember "Reza prefers explicit error handling over try-catch-all patterns"
When to Use
| Situation | Example |
|---|---|
| Hard-won debugging insight | "CORS errors on /api/upload are caused by the CDN, not the backend" |
| Project convention not in CLAUDE.md | "We use barrel exports in src/components/" |
| Tool-specific gotcha | "Jest needs --forceExit flag or it hangs on DB tests" |
| Architecture decision | "We chose Drizzle over Prisma for type-safe SQL" |
| Preference you want Claude to learn | "Don't add comments explaining obvious code" |
Workflow
Step 1: Parse the knowledge
Extract from the user's input:
- What: The concrete fact or pattern
- Why it matters: Context (if provided)
- Scope: Project-specific or global?
Step 2: Check for duplicates
MEMORY_DIR="$HOME/.claude/projects/$(pwd | sed 's|/|%2F|g; s|%2F|/|; s|^/||')/memory"
grep -ni "<keywords>" "$MEMORY_DIR/MEMORY.md" 2>/dev/null
If a similar entry exists:
- Show it to the user
- Ask: "Update the existing entry or add a new one?"
Step 3: Write to MEMORY.md
Append to the end of MEMORY.md:
- {{concise fact or pattern}}
Keep entries concise — one line when possible. Auto-memory entries don't need timestamps, IDs, or metadata. They're notes, not database records.
If MEMORY.md is over 180 lines, warn the user:
⚠️ MEMORY.md is at {{n}}/200 lines. Consider running /si:review to free space.
Step 4: Suggest promotion
If the knowledge sounds like a rule (imperative, always/never, convention):
💡 This sounds like it could be a CLAUDE.md rule rather than a memory entry.
Rules are enforced with higher priority. Want to /si:promote it instead?
Step 5: Confirm
✅ Saved to auto-memory
"{{entry}}"
MEMORY.md: {{n}}/200 lines
Claude will see this at the start of every session in this project.
What NOT to use /si:remember for
- Temporary context: Use session memory or just tell Claude in conversation
- Enforced rules: Use
/si:promoteto write directly to CLAUDE.md - Cross-project knowledge: Use
~/.claude/CLAUDE.mdfor global rules - Sensitive data: Never store credentials, tokens, or secrets in memory files
Tips
- Be concise — one line beats a paragraph
- Include the concrete command or value, not just the concept
- ✅ "Build with
pnpm build, tests withpnpm test:e2e" - ❌ "The project uses pnpm for building and testing"
- ✅ "Build with
- If you're remembering the same thing twice, promote it to CLAUDE.md
Related skills
More from alirezarezvani/claude-skills and the wider catalog.

report
Generate test reports with automatic routing to TestRail, Slack, GitHub, or HTML.

research-summarizer
Structured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and documentation. Extracts key findings, generates comparative analyses, and produces properly formatted citations. Use when: user wants to summarize a research paper, compare multiple sources, extract citations from documents, or create structured research briefs. Plugin for Claude Code, Codex, Gemini CLI, and OpenClaw.

resume
Resume a paused experiment, read history, and continue iterating from where you left off.

revenue-operations
Analyzes sales pipeline health, revenue forecasting accuracy, and go-to-market efficiency metrics for SaaS revenue optimization. Use when analyzing sales pipeline coverage, forecasting revenue, evaluating go-to-market performance, reviewing sales metrics, assessing pipeline analysis, tracking forecast accuracy with MAPE, calculating GTM efficiency, or measuring sales efficiency and unit economics for SaaS teams.

review
Systematically audit Playwright tests for anti-patterns, best practices, and coverage gaps.

risk-management-specialist
Medical device risk management specialist implementing ISO 14971 throughout product lifecycle. Provides risk analysis, risk evaluation, risk control, and post-production information analysis. Use when user mentions risk management, ISO 14971, risk analysis, FMEA, fault tree analysis, hazard identification, risk control, risk matrix, benefit-risk analysis, residual risk, risk acceptability, or post-market risk.