agent-memory-systems
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm
22
3%
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 ./.agent/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 reads like an educational essay about memory systems rather than a functional skill description. It provides conceptual background and 'key insights' but fails to specify what actions Claude can take, when to use the skill, or include natural trigger terms. The description also appears truncated, ending mid-word.
Suggestions
Replace conceptual explanations with concrete actions (e.g., 'Store and retrieve information across conversations, manage vector databases, implement RAG pipelines').
Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks to remember something, recall previous information, or set up persistent memory').
Remove educational content about memory architecture and focus on what the skill enables Claude to do for the user.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses abstract, conceptual language ('cornerstone of intelligent agents', 'cognitive architectures') without listing concrete actions Claude can perform. No specific capabilities like 'create', 'retrieve', 'store', or 'query' are mentioned. | 1 / 3 |
Completeness | The description explains conceptual background about memory systems but never answers 'what does this skill do' in actionable terms or 'when should Claude use it'. There is no 'Use when...' clause or equivalent trigger guidance. The text also appears truncated ('The field is fragm'). | 1 / 3 |
Trigger Term Quality | Contains technical jargon ('vector stores', 'chunking', 'embedding') that users wouldn't naturally say. Missing natural trigger terms like 'remember', 'recall', 'save information', or 'look up'. The terms used are academic rather than user-facing. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so abstract and conceptual that it's unclear what specific tasks it handles. Terms like 'memory', 'storage', and 'retrieval' are extremely generic and could conflict with many other skills involving data management or information lookup. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
7%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 a stub with persona fluff and a list of links. It provides no actionable guidance, no concrete examples, and no actual content about memory systems. The philosophical framing wastes tokens on concepts Claude already knows, while the 'Capabilities' section is just keyword tagging with no instructional value.
Suggestions
Replace the persona introduction with a concise quick-start section showing a concrete memory implementation example (e.g., basic vector store setup with embedding and retrieval code)
Add actual content to the 'Patterns' section with brief descriptions of when to use each pattern before linking to sub-skills
Remove the 'Capabilities' keyword list entirely - it provides no instructional value
Include at least one executable code example demonstrating a core memory operation (chunking, embedding, or retrieval)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is padded with unnecessary persona framing ('You are a cognitive architect...') and vague philosophical statements about memory that Claude already understands. The 'Capabilities' section is just a list of keywords with no actionable content. | 1 / 3 |
Actionability | No concrete code, commands, or executable guidance provided. The content describes concepts abstractly ('Memory failures look like intelligence failures') without any specific implementation details, examples, or copy-paste ready solutions. | 1 / 3 |
Workflow Clarity | No workflow or process is defined. The content is entirely conceptual with no steps, sequences, or validation checkpoints. The 'Patterns' section header exists but contains no actual pattern content. | 1 / 3 |
Progressive Disclosure | The structure attempts progressive disclosure by linking to sub-skills, which is appropriate. However, the main skill provides no useful overview content - it's just links with no context about what each sub-skill contains or when to use them. | 2 / 3 |
Total | 5 / 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
- Dokhacgiakhoa/antigravity-ide
- Commit
332e58b
- 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.