CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-code-memory-and-rules

This skill should be used when the user asks to "set up memory", "configure CLAUDE.md", "add rules", "create project rules", "organize instructions", or mentions Claude Code memory, CLAUDE.md files, .claude/rules, rules, or project instructions. Also use when the user wants to persist preferences, add coding conventions, scope instructions to specific files, or understand when to use rules vs hooks or other memory mechanisms.

70

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A well-structured, actionable reference skill that uses progressive disclosure effectively and provides concrete, copy-paste-ready guidance. Its only weak spot is minor content redundancy between the hierarchy table and the location decision tree.

DimensionReasoningScore

Conciseness

The body is lean and uses compact tables and a decision tree without explaining concepts Claude already knows, but the Memory Hierarchy table and the Choosing-the-Right-Location tree overlap noticeably, offering a minor trim opportunity.

4 / 5

Actionability

Provides copy-paste-ready templates (CLAUDE.md structure, path-scoped rules frontmatter, import syntax), exact file locations, a concrete decision tree, and bootstrap commands (/init, /memory) covering the common configuration cases.

5 / 5

Workflow Clarity

The decision tree and bootstrapping sequence (/init then refine) give a clear selection-and-setup flow with no destructive or batch operations requiring validation, but there is no explicit verification checkpoint confirming rules are correctly placed or loaded.

4 / 5

Progressive Disclosure

A concise overview in SKILL.md points via a Quick Reference section to four well-signaled, one-level-deep reference files (memory-types.md, rules-guide.md, auto-memory.md, examples.md), all of which exist, with detail appropriately split out for easy navigation.

5 / 5

Total

18

/

20

Passed

Description

86%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 strong, trigger-rich description that excels in natural keyword coverage and niche distinctiveness. Its main weakness is the lack of a crisp declarative "what" statement, with capabilities conveyed indirectly through user-ask phrases.

DimensionReasoningScore

Specificity

Lists several concrete actions ("set up memory", "configure CLAUDE.md", "add rules", "scope instructions to specific files"), but a couple are soft or abstract ("organize instructions", "understand when to use rules vs hooks"), leaving minor coverage gaps rather than full comprehensiveness.

4 / 5

Completeness

The "when" is explicit ("This skill should be used when...", "Also use when..."), but the "what" is only implied through the trigger list rather than stated as a declarative capability, so it falls just short of the anchor that requires both explicitly.

4 / 5

Trigger Term Quality

Comprehensive coverage of natural trigger phrases including synonyms and file paths ("CLAUDE.md files", ".claude/rules", "rules vs hooks", "project instructions"), matching the anchor for full keyword coverage.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Claude Code memory/CLAUDE.md/rules) with distinct triggers and explicitly routes hook requests to a separate skill, keeping conflict risk minimal.

5 / 5

Total

18

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
dwmkerr/claude-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.