Rekal Usage Guide

Trust Score 90/100

Operational decision tree and rules for using Rekal memory tools and associated MCP memory helpers during sessions and onboarding.

triggers:rekalmemory_build_contextmemory_storehow to use rekalrekal usage

GitHub SKILL.md

What it does

Provides a precise, operational guide for using Rekal and associated MCP memory tools: session startup rules, decision trees for querying memory, standardized storage rules, and explicit function-level instructions for memory_store/memory_search/memory_supersede. It codifies how to scope projects, query hybrid search, and maintain memory hygiene.

When to use it

Use this skill at the start of a new session, when onboarding to a Rekal workspace, or when the user asks how to use Rekal or its MCP memory helpers. It is also useful when deciding whether to store, supersede, or link memories.

What's included

Scripts: No bundled scripts (has_scripts=false).
References: No separate references directory, but the skill lists allowed MCP tool names and exact call signatures to use.
Instructions: Detailed decision trees for queries, filtering rules, content rules for memory_store, memory_supersede semantics, memory types, and conversation utilities. Clear do/don't guidance for storage and linking.

Compatible agents

Best suited for agents integrated with MCP memory tooling and hybrid search backends (agents that can call mcp__rekal__* APIs). Also useful for developers and analysts implementing memory pipelines.

Audit Summary

Rekal Usage is a pure documentation skill providing an operational decision tree and rules for using Rekal memory MCP tools. No scripts to run — it's entirely a SKILL.md guide. The documentation is thorough with specific triggers, parameter references, decision trees for retrieval, and clear content compression rules. Well-structured frontmatter with allowed-tools list. Niche audience limited to Rekal MCP users, but genuinely useful for that audience.

Watch Out

Requires Rekal MCP server installed and configured
Only useful if your agent has access to rekal MCP tools

Notes

No executable code — purely a reference/operational guide skill. Clean frontmatter, comprehensive decision trees, good examples of both correct and incorrect usage. Content compression rules are a nice touch. No security concerns whatsoever.

Information

Repository: rekal
Stars: 41
Installs: 0

Trust Score

Overall90

Security100

Code Quality82

Architecture78

Usefulness55

Related Skills

Caveman Compress

Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.

Chinese Software Copyright Application

Generate complete Chinese software copyright application materials (application form, code documentation, user manual, design docs) and export them to PDF from

Ip2Location IO Automation (Composio)

Automate Ip2location IO tasks via Composio's Rube MCP toolkit — discover tools, verify connections, and execute schema-compliant workflows safely.

CTF Write-up Generator

Generate a concise, reproducible submission-style CTF writeup with a one-path solution script, metadata, and a short checklist for fast verification.

Verifying Markdown Formatting

Checks Markdown files for structural and stylistic formatting issues (headings, lists, code blocks, links) and applies deterministic fixes.

Code Spec Backfill

Identify missing function-level contracts and backfill docstrings and type annotations; report ambiguous gaps with misuse scenarios. Incremental, state-driven w

Azure External Attack Surface Management

Provides expert guidance for Azure External Attack Surface Management (EASM): quotas, configuration, integrations, and exporting inventory to analytics platform

Smalltalk MCP

Connects an LLM (Claude/OpenAI/etc.) to a live Smalltalk (Squeak/Cuis) image over MCP for browsing, evaluating and modifying Smalltalk code.

Back to Skills