totalreclaw
End-to-end encrypted memory for AI agents — portable, yours forever. AES-256-GCM E2EE: server never sees plaintext.
What this skill does
# TotalReclaw Skill
## Recovery Phrase -- READ THIS FIRST
**CRITICAL SAFETY WARNING:** TotalReclaw generates a NEW recovery phrase for the user. NEVER let the user enter a recovery phrase from an existing crypto wallet they own. TotalReclaw uses BIP-39 mnemonics (the same format as crypto wallets), but TotalReclaw recovery phrases must be SEPARATE from any funded wallet. If a user tries to import a phrase they already use for a crypto wallet, STOP and warn them: "Do NOT use a recovery phrase from an existing crypto wallet. TotalReclaw should have its own dedicated phrase to keep your funds safe."
The recovery phrase is the user's ONLY identity in TotalReclaw. It derives all encryption keys. There is NO password reset, NO recovery mechanism, and NO support channel that can help if it is lost.
**When showing the recovery phrase to the user, ALWAYS include this warning:**
> Your recovery phrase is the ONLY way to access your encrypted memories. If you lose it, your memories are gone forever -- there is no password reset, no recovery, and no support that can help. Write it down and store it somewhere safe. Never share it with anyone.
>
> IMPORTANT: This phrase is for TotalReclaw ONLY. Never use a recovery phrase from an existing crypto wallet -- keep your TotalReclaw phrase separate from any wallet that holds funds.
If the user asks to see their recovery phrase, remind them to store it securely. If they mention losing it, be clear that recovery is impossible and they will need to start fresh with a new phrase.
---
## Tools
### totalreclaw_remember
Store a new fact or preference in long-term memory.
**Parameters:**
| Name | Type | Required | Description |
|------|------|----------|-------------|
| text | string | Yes | The fact or information to remember |
| type | string | No | Type of memory: `fact`, `preference`, `decision`, `episodic`, `goal`, `context`, or `summary`. Default: `fact` |
| importance | integer | No | Importance score 1-10. Default: auto-detected by LLM |
**Example:**
```json
{
"text": "User prefers TypeScript over JavaScript for new projects",
"type": "preference",
"importance": 7
}
```
**Returns:**
```json
{
"factId": "01234567-89ab-cdef-0123-456789abcdef",
"status": "stored",
"importance": 7,
"encrypted": true
}
```
---
### totalreclaw_recall
Search and retrieve relevant memories from long-term storage.
**Parameters:**
| Name | Type | Required | Description |
|------|------|----------|-------------|
| query | string | Yes | Natural language query to search memories |
| k | integer | No | Number of results to return. Default: 8, Max: 20 |
**Example:**
```json
{
"query": "What programming languages does the user prefer?",
"k": 5
}
```
**Returns:**
```json
{
"memories": [
{
"factId": "01234567-89ab-cdef-0123-456789abcdef",
"factText": "User prefers TypeScript over JavaScript for new projects",
"type": "preference",
"importance": 7,
"timestamp": "2026-02-22T10:30:00Z",
"relevanceScore": 0.95
}
],
"totalCandidates": 47,
"searchLatencyMs": 42
}
```
---
### totalreclaw_forget
Delete a specific fact from memory.
**Parameters:**
| Name | Type | Required | Description |
|------|------|----------|-------------|
| factId | string | Yes | UUID of the fact to delete |
**Example:**
```json
{
"factId": "01234567-89ab-cdef-0123-456789abcdef"
}
```
**Returns:**
```json
{
"status": "deleted",
"factId": "01234567-89ab-cdef-0123-456789abcdef",
"tombstoneExpiry": "2026-03-24T00:00:00Z"
}
```
---
### totalreclaw_export
Export all stored memories in plaintext format.
**Parameters:**
| Name | Type | Required | Description |
|------|------|----------|-------------|
| format | string | No | Export format: `json` or `markdown`. Default: `json` |
**Example:**
```json
{
"format": "json"
}
```
**Returns (JSON format):**
```json
{
"exportVersion": "0.3",
"exportedAt": "2026-02-22T10:30:00Z",
"totalFacts": 127,
"facts": [
{
"id": "...",
"factText": "...",
"type": "preference",
"importance": 7,
"timestamp": "...",
"entities": [...],
"relations": [...]
}
],
"graph": {
"entities": {...},
"relations": [...]
}
}
```
**Returns (Markdown format):**
```markdown
# TotalReclaw Export
Exported: 2026-02-22T10:30:00Z
Total Facts: 127
## Preferences
- User prefers TypeScript over JavaScript for new projects (importance: 7)
## Decisions
- User decided to use PostgreSQL for the main database (importance: 8)
...
```
---
### totalreclaw_status
Check subscription status and usage quota.
**Parameters:** None
**Example:**
```json
{}
```
**Returns:**
```json
{
"tier": "Free",
"writesUsed": 42,
"writesLimit": 250,
"resetsAt": "2026-04-01",
"pricingUrl": "https://totalreclaw.xyz/pricing"
}
```
---
### totalreclaw_consolidate
Scan all stored memories and merge near-duplicates. Keeps the most important/recent version and removes redundant copies.
**Parameters:**
| Name | Type | Required | Description |
|------|------|----------|-------------|
| dry_run | boolean | No | Preview consolidation without deleting. Default: `false` |
**Example:**
```json
{
"dry_run": true
}
```
**Returns:**
```
Scanned 247 memories.
Found 12 cluster(s) with 18 duplicate(s).
Cluster 1: KEEP "User prefers TypeScript over JavaScript for new projects..."
- REMOVE "User likes TypeScript more than JavaScript..." (ID: abc123)
Cluster 2: KEEP "Project uses PostgreSQL as the main database..."
- REMOVE "The main database is PostgreSQL..." (ID: def456)
...
DRY RUN -- no memories were deleted. Run without dry_run to apply.
```
**Note:** Currently only available in centralized mode (not subgraph mode).
---
### totalreclaw_upgrade
Upgrade to TotalReclaw Pro for unlimited encrypted memories on Gnosis mainnet.
**Parameters:**
| Name | Type | Required | Description |
|------|------|----------|-------------|
| *(none)* | | | The tool automatically uses the current wallet address |
**Example:**
```json
{}
```
**Returns:**
```json
{
"checkout_url": "https://checkout.stripe.com/c/pay/...",
"message": "Open this URL to upgrade to Pro: https://checkout.stripe.com/c/pay/..."
}
```
---
### totalreclaw_migrate
Migrate memories from testnet (Base Sepolia) to mainnet (Gnosis) after upgrading to Pro.
**When to use:** After a user successfully upgrades to Pro. Their memories are on the free-tier testnet and need to be copied to permanent mainnet storage.
**Parameters:**
| Name | Type | Required | Description |
|------|------|----------|-------------|
| confirm | boolean | No | Set to `true` to execute the migration. Without it, returns a dry-run preview. Default: `false` |
**Example (dry-run):**
```json
{}
```
**Example (execute):**
```json
{
"confirm": true
}
```
**Returns (dry-run):**
```json
{
"mode": "dry_run",
"testnet_facts": 47,
"already_on_mainnet": 0,
"to_migrate": 47,
"message": "Found 47 facts to migrate from testnet to Gnosis mainnet. Call with confirm=true to proceed."
}
```
**Returns (executed):**
```json
{
"mode": "executed",
"testnet_facts": 47,
"migrated": 47,
"failed_batches": 0,
"message": "Successfully migrated 47 memories from testnet to Gnosis mainnet."
}
```
**Safety:**
- Dry-run by default: call without `confirm=true` to preview what will be migrated
- Idempotent: re-running skips facts that already exist on mainnet (by content fingerprint)
- Testnet facts are never deleted (they remain as a backup)
- Handles partial failures: if a batch fails, re-run to retry (only unmigrated facts are sent)
---
### totalreclaw_import_from
Import memories from other AI memory tools into TotalReclaw.
**When to use:** User mentions migrating from Mem0, MCP Memory Server, or wants to import memories from another tool.
**Parameters:**
| Name | Type | Required | Description |
|------|------|----------|-------------|
| source | string | Yes | Source system: `mem0`, `mcp-meRelated in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.