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.

47

Quality

59%

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

30%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: it names the right concepts (memory tiers, entity memory, retrieval, user isolation) but provides no executable guidance, no workflow, and empty or placeholder sections, and it appears truncated mid-sentence. Claude reading this would know the topic but not what to do.

Suggestions

Replace the persona introduction and truncated principles list with a concrete workflow, e.g. 1. classify the memory need (short-term/entity), 2. choose a store, 3. retrieve with relevance filtering, 4. validate isolation and bounds — with validation checkpoints.

Flesh out each Pattern with a concrete example (schema, retrieval prompt snippet, or consolidation rule) instead of single-line descriptions, and fill in the empty Anti-Pattern sections with why each fails.

Turn the Sharp Edges '// comment' solutions into actionable fixes, e.g. 'enforce per-user key prefixes and TTL-based eviction' instead of '// Strict user isolation in memory'.

DimensionReasoningScore

Conciseness

The two persona paragraphs ('You're a memory systems specialist...', 'You understand that...') add no instructional value, and the body is otherwise skeletal rather than padded. It is short but includes unnecessary framing that could be trimmed.

3 / 5

Actionability

Patterns are one-line abstractions ('Different memory tiers for different purposes'), Anti-Pattern sections contain only headers, and Sharp Edges 'solutions' are placeholder comments ('// Implement memory lifecycle management'). Only the Sharp Edges table names concrete issues, so guidance remains high-level hints without executable specifics.

2 / 5

Workflow Clarity

No sequence or steps appear anywhere in the body: nothing tells Claude how to design, wire up, or validate a memory system, and there are no validation checkpoints. Even a rough ordered list is absent.

1 / 5

Progressive Disclosure

Sections exist (Capabilities, Patterns, Anti-Patterns, Sharp Edges, Related Skills) and no broken file references are present since no bundle files exist, but the Anti-Pattern subsections are empty and the body is truncated mid-sentence ('Memory types differ—short-term, lo'), leaving the structure incomplete.

3 / 5

Total

9

/

20

Passed

Description

70%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.

A solid description with an explicit and well-populated 'Use when:' trigger clause and a clearly scoped domain. Its main weakness is that the 'what' enumerates memory types rather than concrete actions, and it stays in third person with no padding.

Suggestions

Replace the categorical 'including short-term, long-term, and entity-based memory' with action verbs, e.g. 'Store, retrieve, and consolidate short-term, long-term, and entity-based memories for LLM conversations'.

Add one or two synonym triggers users naturally say, such as 'recall' or 'persist', to broaden keyword coverage.

DimensionReasoningScore

Specificity

Names the domain ('Persistent memory systems for LLM conversations') and concrete memory types ('short-term, long-term, and entity-based memory'), but describes scope categories rather than actions the skill performs, so it is not comprehensive.

3 / 5

Completeness

Explicitly answers both: the 'what' (persistent memory systems including the three memory types) and an explicit 'Use when:' clause with five concrete triggers. The 'what' states categories rather than actions, keeping it just below a 5.

4 / 5

Trigger Term Quality

'conversation memory', 'remember', 'memory persistence', 'long-term memory', 'chat history' are natural phrases a user would say, though synonyms like 'recall' or 'persist' are missing.

4 / 5

Distinctiveness Conflict Risk

The LLM conversation-memory niche is distinct, but generic triggers like 'remember' carry minor overlap risk with closely related skills the body itself lists (context-window-management, prompt-caching).

4 / 5

Total

15

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

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.