memory-engineering

Use when designing, reviewing, or paying for an agent memory system — adding memory to an agent, choosing between long-context / RAG / graph / agentic memory, auditing what a CLAUDE.md or memory directory actually holds, deciding what to keep and what to expire, or when a memory store keeps growing and nobody has said what leaves it. Prices the write path, picks which cost to pay, classifies records as facts / skills / logs, and refuses a design that has no forgetting policy.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

92%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 tightly engineered skill body: executable workflow with a blocking validation gate, clear reference structure with all bundle files present, and a hard-rules checklist. The only slack is light rhetorical framing in the intro that slightly dents token efficiency.

Suggestions

Tighten the 'What this does' section by converting the metaphor-laden prose ('Memory is not a bucket — it is a system with a metabolism') into a one-line statement of intent to lift conciseness toward 5.

Add an explicit fix-and-retry loop for the gate step (e.g. 'on exit 4, fix the flagged F1/F4 rule and re-run the linter') so the error-recovery feedback loop is stated, not just implied by exit codes.

Dimension	Reasoning	Score
Conciseness	Mostly lean — punchy tables, hard rules, and copy-paste commands — but the 'What this does' framing ('Memory is not a bucket — it is a system with a metabolism') adds rhetorical editorializing that could be trimmed. Not a 5 because not every token strictly earns its place instructionally; not a 3 because it never explains concepts Claude already knows.	4 / 5
Actionability	Fully executable copy-paste commands for each step ('python scripts/memory_cost_profiler.py --spec workload.json'), with '--output json' and '--sample' flags and a documented exit-code table covering the common cases.	5 / 5
Workflow Clarity	Five clearly sequenced steps with an explicit validation gate ('Exit 4 is a stop, not a suggestion'), a hand-proof checkpoint ('prove each pass by hand before scheduling it'), and a seven-item hard-rules checklist. The destructive forgetting operation has real validation, so the destructive-skill cap does not apply.	5 / 5
Progressive Disclosure	A concise overview body with well-signaled one-level-deep references to four reference files and three asset files, each given a one-line description; all referenced paths resolve to real bundle files.	5 / 5
	Total	19 / 20 Passed

Description

100%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.

An exemplary description: third-person voice, concrete capabilities, comprehensive natural trigger terms, and explicit what/when guidance for a well-bounded niche. No over-claims or vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Prices the write path, picks which cost to pay, classifies records as facts / skills / logs, and refuses a design that has no forgetting policy' — alongside designing/reviewing/auditing, giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('Prices the write path, picks which cost to pay, classifies records...') and when ('Use when designing, reviewing, or paying for an agent memory system... or when a memory store keeps growing') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user phrases abound: 'adding memory to an agent', 'long-context / RAG / graph / agentic memory', 'memory store keeps growing', 'deciding what to keep and what to expire', covering synonyms and concrete trigger language.	5 / 5
Distinctiveness Conflict Risk	A narrow, clearly bounded niche — agent memory engineering with a forgetting-policy gate — with distinct triggers unlikely to fire for unrelated skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: engineering/memory-engineering/skills/memory-engineering/SKILL.md
Commit: 19392f7

Reviewed: ~5 hours ago

Table of Contents

Discovery Implementation Validation

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.