agent-memory-systems
You are a cognitive architect who understands that memory makes agents intelligent. You've built memory systems for agents handling millions of interactions. You know that the hard part isn't storing - it's retrieving the right memory at the right time.
19
0%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/agent-memory-systems/SKILL.mdQuality
Discovery
0%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 is written as a persona/role-play prompt rather than a functional skill description. It contains no concrete actions, no trigger terms, no 'when to use' guidance, and uses first/second person framing ('You are', 'You've built', 'You know'). It would be nearly impossible for Claude to correctly select this skill from a list of available skills.
Suggestions
Replace the persona language with concrete actions the skill performs, e.g., 'Builds and manages memory systems for AI agents, including storing conversation context, indexing past interactions, and retrieving relevant memories based on semantic similarity.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs agent memory, conversation persistence, context retrieval, or long-term memory for AI agents.'
Remove all first/second person voice ('You are', 'You've built') and rewrite in third person describing what the skill does, not who it pretends to be.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. Phrases like 'cognitive architect' and 'built memory systems' are vague and abstract, with no specific capabilities listed (e.g., no mention of storing, querying, indexing, or retrieving data). | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it.' There is no 'Use when...' clause or equivalent, and the 'what' is entirely absent—replaced by persona-building language about the skill's supposed expertise. | 1 / 3 |
Trigger Term Quality | The description uses abstract jargon like 'cognitive architect' and 'millions of interactions' that users would never naturally say. The only potentially relevant term is 'memory systems' but it's buried in self-promotional language rather than presented as a trigger keyword. | 1 / 3 |
Distinctiveness Conflict Risk | The description is extremely generic and could apply to virtually any agent-related or data management skill. 'Memory systems for agents' is too broad to distinguish this from caching, database, knowledge base, or retrieval skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially an empty outline—section headings and bullet points with no actual instructional content. It provides no executable code, no concrete guidance, no real examples, and the sharp edges table contains placeholder text ('Issue') repeated throughout. The opening paragraphs waste tokens on philosophical framing that Claude already understands while failing to deliver any actionable knowledge about implementing memory systems.
Suggestions
Fill in each Pattern section with concrete, executable code examples showing how to implement that memory type (e.g., a working vector store setup with chunking code)
Replace the placeholder 'Issue' entries in the Sharp Edges table with actual specific issues (e.g., 'Embedding drift after model updates', 'Stale memories dominating retrieval') and provide concrete solutions
Add a Quick Start workflow with numbered steps showing how to set up a basic agent memory system, including validation steps for testing retrieval quality
Remove the persona description and capabilities list, replacing them with actionable content like code snippets for different memory backends and chunking strategies
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening paragraphs explain concepts Claude already knows (what memory failures look like, that retrieval is harder than storage). The capabilities list is pure padding with no actionable content. The content is verbose yet paradoxically incomplete—it wastes tokens on fluff while providing no substance. | 1 / 3 |
Actionability | There is zero executable code, no concrete commands, no specific examples, and no actual instructions. Every section is a heading or label with no content beneath it. The patterns are named but never described. The sharp edges table has placeholder 'Issue' text with solutions that are just vague headings. | 1 / 3 |
Workflow Clarity | There are no workflows, no sequenced steps, no validation checkpoints. The patterns section lists names without any process description. There is no guidance on how to actually implement any memory system. | 1 / 3 |
Progressive Disclosure | The content is a skeleton of headings with no substance at any level. There are no references to external files, no navigation structure, and no meaningful content to disclose progressively. The 'Related Skills' section lists names but provides no links or context. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
90%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
- sickn33/antigravity-awesome-skills
- Commit
d739c8b
- Reviewed
Table of Contents
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.