recallmax

FREE — God-tier long-context memory for AI agents. Injects 500K-1M clean tokens, auto-summarizes with tone/intent preservation, compresses 14-turn history into 800 tokens.

Quality

27%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/recallmax/SKILL.md

Quality

Content

21%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill reads as a marketing landing page rather than actionable technical documentation. It makes bold claims ('500K-1M clean tokens', 'God-Tier') but provides zero executable guidance—no API usage, no code examples, no configuration, no concrete integration steps. Claude would be unable to actually use RecallMax based on this content alone.

Suggestions

Add concrete, executable code examples showing how to initialize RecallMax, inject context, trigger summarization, and compress history—with actual function calls and expected outputs.

Remove marketing language ('God-Tier', 'Free forever', 'Built by the Genesis Agent Marketplace') and focus on technical instructions that Claude doesn't already know.

Replace the abstract 'How It Works' steps with actionable workflow steps including specific commands, API calls, configuration options, and validation/verification checkpoints.

Add at least one complete end-to-end example showing input (e.g., a long conversation) and expected output (e.g., compressed tokens) so Claude can verify correct usage.

Dimension	Reasoning	Score
Conciseness	The content is noticeably verbose with marketing language ('God-Tier', 'Free forever', 'Built by the Genesis Agent Marketplace') and explains concepts Claude already understands (what summarization preserves, what context injection does). The 'How It Works' section describes abstract capabilities rather than providing actionable instructions, padding the content significantly.	2 / 5
Actionability	There is virtually no concrete, executable guidance. The entire skill describes what RecallMax supposedly does in abstract terms but provides zero code examples, no API calls, no function signatures, no configuration snippets, and no concrete commands beyond a single install line. Claude would have no idea how to actually use this tool.	1 / 5
Workflow Clarity	While there are numbered steps (1-4), they describe conceptual phases rather than actionable workflow steps. There are no validation checkpoints, no error handling, no feedback loops, and no concrete commands to execute at each step. The 'Best Practices' section offers vague do/don't guidance without specifics.	2 / 5
Progressive Disclosure	The content has reasonable section structure (Overview, Install, When to Use, How It Works, Best Practices) and isn't a wall of text. However, there are no bundle files or referenced documentation to support deeper exploration, and the content that exists is all surface-level with no deeper material to disclose progressively.	3 / 5
	Total	8 / 20 Passed

Description

33%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description reads more like marketing copy than a functional skill description. It uses hyperbolic language ('God-tier', 'FREE') and implementation-specific metrics (500K-1M tokens, 14-turn, 800 tokens) instead of clearly describing user-facing capabilities and trigger conditions. It completely lacks a 'Use when...' clause, making it difficult for Claude to know when to select this skill.

Suggestions

Remove marketing language ('FREE', 'God-tier') and replace with concrete, user-facing capability descriptions like 'Manages conversation memory across long sessions, preserving tone and intent'.

Add an explicit 'Use when...' clause with natural trigger phrases such as 'Use when the user needs to recall earlier conversation context, manage long conversations, or preserve memory across sessions'.

Include natural user-facing trigger terms like 'remember', 'conversation history', 'recall', 'long conversation', 'context management' instead of implementation details like token counts.

Dimension	Reasoning	Score
Specificity	Names the domain (long-context memory) and a few concrete actions (injects tokens, auto-summarizes, compresses history), but uses marketing language ('God-tier') and the specific numbers (500K-1M tokens, 14-turn, 800 tokens) are implementation details rather than user-facing capabilities.	3 / 5
Completeness	Has a partial 'what' (memory management, summarization, compression) but no 'when' clause at all. There is no guidance on when Claude should select this skill. The missing 'Use when...' clause caps this at 3, and the weak 'what' brings it to 2.	2 / 5
Trigger Term Quality	Contains some technical terms like 'memory', 'context', 'summarizes', 'compresses', and 'history', but these are not natural phrases a user would say. Missing user-facing trigger terms like 'remember', 'conversation history', 'recall previous messages', or 'context window'.	2 / 5
Distinctiveness Conflict Risk	The focus on long-context memory and token compression is somewhat specific, but 'auto-summarizes' and 'memory' could overlap with general summarization or note-taking skills. The marketing tone ('God-tier', 'FREE') adds noise rather than distinctiveness.	3 / 5
	Total	10 / 20 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/recallmax/SKILL.md
Commit: 57c135b

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.