Name: recallmax
Rating: 48.8 (1 reviews)
Author: administrakt0r

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

52%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/recallmax/SKILL.md

The canonical home for this skill is recallmax in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

46%Weight 40%Scale 1-5

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

The skill body is well-structured and concise enough, but it reads as a product pitch rather than an actionable skill: it describes what RecallMax does at a high level without providing executable commands, code, or verifiable workflow steps. The actionability gap is the dominant weakness.

Suggestions

Replace the abstract 'How It Works' steps with concrete, executable usage examples — actual commands/API calls to inject context, trigger summarization, and run compression — so Claude can act rather than only read.

Add validation/verification checkpoints into the workflow (e.g., how to confirm injected context was deduplicated correctly, or how to verify compression preserved key facts before discarding the raw history).

Strip marketing fluff ('God-Tier', 'Free forever', 'dramatically', the emoji best-practices padding) to recover tokens for the missing actionable guidance.

Dimension	Reasoning	Score
Conciseness	The body is short and sectioned, but promotional padding ("God-Tier", "Free forever. Built by the Genesis Agent Marketplace", "dramatically") and redundant capability restatement mean it 'includes some unnecessary explanation or could be tightened'; not 4 because the marketing puff and emoji best-practices list add tokens without adding skill value.	3 / 5
Actionability	The only concrete command is `npx skills add`; the four 'How It Works' steps are pure description ('RecallMax cleanly injects... it deduplicates... preserves... prevents') with no executable code, API, or specific steps, matching 'minimal concrete guidance; high-level hints but missing the specific steps to execute'; not 1 because the install command and quantified targets provide minimal concrete grounding.	2 / 5
Workflow Clarity	Steps 1-4 are sequenced (Context Injection, Adaptive Summarization, History Compression, Fact Verification) but they describe features rather than an executable procedure, and there are no validation checkpoints or error-recovery loops, matching 'steps listed but validation gaps; checkpoints missing or implicit'; not 4 because nothing is verifiable.	3 / 5
Progressive Disclosure	The body is well organized into clear sections (Overview, Install, When to Use, How It Works, Best Practices, Related Skills, Links) with no nested or broken references and no bundle files to misroute, matching 'good structure; most content appropriately placed; minor organization gaps'; not 5 because the Links/Related Skills sections are external promotion rather than skill-internal navigation.	4 / 5
	Total	12 / 20 Passed

Description

58%Weight 40%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.

The description conveys concrete, quantified capabilities but is weighed down by marketing fluff and completely lacks explicit trigger guidance. Adding a 'Use when...' clause and natural user phrasing would lift its weakest dimensions.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when your agent loses context in long conversations or needs to inject large external documents into its context window').

Replace promotional filler ('God-tier', 'FREE', 'clean tokens') with natural trigger keywords users would actually say, such as 'losing context', 'context window limits', and 'remember long conversations'.

Include common synonyms and concrete trigger phrases (e.g., 'long conversations', 'RAG documents', 'context truncation') to broaden trigger-term coverage toward the 5 anchor.

Dimension	Reasoning	Score
Specificity	Lists three concrete, quantified actions — "Injects 500K-1M clean tokens", "auto-summarizes with tone/intent preservation", "compresses 14-turn history into 800 tokens" — matching the 'several specific actions; minor gaps' anchor; falls short of 5 only because coverage is framed by marketing fluff ("God-tier", "clean tokens") rather than exhaustive capability listing.	4 / 5
Completeness	The 'what' is clear (inject, summarize, compress) but there is no 'Use when...' clause or equivalent trigger guidance, so per the boundary guideline completeness is capped at 3 ('clear what but when is missing or only weakly implied'); not 4 because the 'when' is entirely absent rather than weakly stated.	3 / 5
Trigger Term Quality	Relevant domain keywords are present ("long-context memory", "summarizes", "compression") but it lacks the natural phrases a user would actually say ("loses context", "context window", "remember everything"), matching the 'some relevant keywords but missing common variations' anchor; not 4 because no natural user phrasing is included.	3 / 5
Distinctiveness Conflict Risk	The tone/intent preservation and 800-token compression features carve a fairly distinct niche, though the broad "memory for AI agents" framing carries minor overlap risk with other memory skills, matching 'mostly distinct; minor overlap risk'; not 5 because the category label itself is broad.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/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.