CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

conversation-memory

Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.

Quality

54%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./cli-tool/components/skills/ai-research/conversation-memory/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

22%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 body is a skeletal outline rather than a usable skill: sections exist but nearly all substance is missing, the principles list is truncated mid-sentence, and the only 'solutions' offered are comment-style placeholders. A reader gains section names but no executable guidance or workflow.

Suggestions

Fix the truncated principles list ('Memory types differ—short-term, lo') and complete each item with the actual principle, not just the category name.

Replace the one-line pattern stubs with concrete guidance — e.g. for the Tiered Memory System, give the actual tier definitions, retention rules, and a retrieval/consolidation procedure.

Rewrite the Sharp Edges table solutions as real instructions instead of placeholders ('// Implement memory lifecycle management'), e.g. specific eviction/consolidation steps and how user isolation is enforced.

Expand the empty Anti-Pattern sections with why each fails and what to do instead, so the section is not bare headers.

DimensionReasoningScore

Conciseness

The body is short and does not explain concepts Claude already knows, but the persona preamble ('You're a memory systems specialist who has built AI assistants that remember users across months') is padding, and the principles list is truncated mid-sentence. Fits 'mostly efficient but includes some unnecessary explanation or could be tightened'; not 4 because the preamble and dead text do not earn their tokens.

3 / 5

Actionability

There is no concrete code, command, or step anywhere: patterns are one-line abstractions ('Different memory tiers for different purposes', 'Store and update facts about entities') and the sharp-edge solutions are comment placeholders ('// Implement memory lifecycle management'). This matches anchor 1 — 'entirely vague or abstract; only describes rather than instructs'.

1 / 5

Workflow Clarity

No multi-step process is ever sequenced, and the one numbered list is literally cut off ('1. Memory types differ—short-term, lo'), leaving the document incoherent. Matches anchor 1 ('steps missing or incoherent; no sequence; no validation for risky operations').

1 / 5

Progressive Disclosure

The skill has no bundle files and is roughly 55 lines with clear section headers (Capabilities, Patterns, Anti-Patterns, Sharp Edges, Related Skills), but several sections are empty or skeletal headers ('❌ Remember Everything' with no body), so it only reaches 'some structure but could be better organized'.

3 / 5

Total

8

/

20

Passed

Description

65%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 has a solid explicit 'Use when' trigger clause with natural keywords, and the niche is distinct. Its main weakness is the 'what': it enumerates memory categories instead of concrete actions, so a reader learns the topic but not what the skill does.

Suggestions

Replace the category list with concrete actions, e.g. 'Store, retrieve, and consolidate conversation memory across sessions, including short-term, long-term, and entity-based stores'.

Add a few natural trigger synonyms such as 'recall', 'persist user preferences', or 'remember past chats' to broaden keyword coverage.

DimensionReasoningScore

Specificity

The description names the domain and its categories ('short-term, long-term, and entity-based memory') but contains no concrete actions — it never says what the skill does (store, retrieve, consolidate memories), matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 1 because the domain scoping is specific, and not a 3 because zero concrete actions are stated.

2 / 5

Completeness

Both parts are present: a 'what' ('Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory') and an explicit 'when' with concrete trigger phrases. Not 5 because the 'what' describes categories rather than what the skill actually does, leaving the capability statement at domain level.

4 / 5

Trigger Term Quality

'Use when: conversation memory, remember, memory persistence, long-term memory, chat history' provides good coverage of natural user phrases. Not 5 because common synonyms like 'recall', 'persist user info', or 'forget' are missing; better than 3 because the listed terms are the ones users would actually say.

4 / 5

Distinctiveness Conflict Risk

'conversation memory, remember, memory persistence, long-term memory, chat history' carves a clear niche with distinct triggers and minimal conflict risk; only minor overlap with closely related skills such as context-window or RAG skills keeps it from a 5.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

davila7/claude-code-templates

Path

cli-tool/components/skills/ai-research/conversation-memory/SKILL.md

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.