CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-memory-kit

Persistent memory system for Claude Code. Two-layer architecture (hot cache + knowledge wiki), safety hooks, /close-day end-of-day synthesis. Zero external dependencies.

49

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/claude-memory-kit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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 compact, well-organized overview with an executable install snippet, but it stops at describing features rather than instructing how to use them, and includes a promotional section that adds tokens without actionable value. It works as a landing page more than as operational guidance.

Suggestions

Add a short, concrete usage example for /close-day and the memory workflow so the body instructs rather than only describes.

Remove or condense the 'Built from production' section to eliminate promotional tokens that do not aid execution.

Show one minimal sequence for recording and recalling a fact (with the hook/validation behavior) to give the core operation explicit checkpoints.

DimensionReasoningScore

Conciseness

The body is short and the feature list is tight, but the "Built from production" section ("700+ sessions across 7 projects. Adapted from Karpathy/Cole Medin's knowledge base pattern...") is promotional context that does not help Claude act, so it is mostly efficient rather than fully lean.

2 / 3

Actionability

The Quick Start bash block is concrete and copy-paste ready, but it only covers cloning/launching; the body describes /close-day, /tour, and safety hooks without any executable guidance on how to use them.

2 / 3

Workflow Clarity

A clear three-step install sequence is present, but the core operations the skill advertises (end-of-day synthesis via /close-day, hook-driven context protection) are not sequenced with validation checkpoints, so guidance is incomplete.

2 / 3

Progressive Disclosure

At under 50 lines with no external bundle files needed or provided, the body is organized into clear, well-signaled sections (What it does, Quick Start, Built from production), satisfying the simple-skill standard for progressive disclosure.

3 / 3

Total

9

/

12

Passed

Description

50%

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 concisely conveys what the kit is and its main components in third person, but it omits any explicit when-to-use guidance and relies on feature labels rather than natural trigger terms. It is clear and non-generic but stops short of the trigger-rich, action-oriented standard.

Suggestions

Add a 'Use when...' clause naming natural user triggers, e.g. 'Use when you want Claude to remember context across sessions, recall past work, or capture a day's activity.'

Reframe feature labels as concrete actions (e.g. 'records and recalls facts across sessions', 'synthesizes the day with /close-day') to lift specificity.

Include common trigger variations users would actually say ('remember', 'recall', 'keep context') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain and several concrete components ("hot cache + knowledge wiki", "safety hooks", "/close-day end-of-day synthesis", "Zero external dependencies"), but these are feature labels rather than the concrete actions the anchor for 3 calls for.

2 / 3

Completeness

Clearly states what the skill does, but provides no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Includes relevant terms like "memory" and "Claude Code" a user might say, but lacks common natural variations ("remember across sessions", "recall", "context") and reads as a feature summary rather than user-facing triggers.

2 / 3

Distinctiveness Conflict Risk

The "Persistent memory system for Claude Code" niche is fairly specific, but without distinct trigger phrasing it could still overlap with general context-management skills.

2 / 3

Total

8

/

12

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.

Validation15 / 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
rohitg00/awesome-claude-code-toolkit
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.