engram-memory

ALWAYS ACTIVE — Persistent memory protocol. You MUST save decisions, conventions, bugs, and discoveries to engram proactively. Do NOT wait for the user to ask.

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugin/claude-code/skills/memory/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete tooling and clearly sequenced workflows, and it mostly respects token budget with only minor redundancy. Its main weakness is monolithic inline content with no progressive disclosure structure.

Suggestions

Split detailed reference material (full mem_save field specs, session-summary template) into separate referenced files and link to them from the overview.

Remove redundant restatements (e.g., the repeated setup instructions at the end) to tighten token usage.

Add a brief top-of-file navigation/overview so the structure of the protocol is immediately scannable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but reinforcement language ('MANDATORY', 'ALWAYS ACTIVE') and the repeated setup instructions introduce redundancy that keeps it from being fully lean.	2 / 3
Actionability	It provides concrete tool names, an explicit mem_save field format (title/type/scope/topic_key/content), and specific commands ('engram setup codex') — fully actionable, copy-ready guidance for an instruction-only skill.	3 / 3
Workflow Clarity	Multi-step processes (search memory, session close, after-compaction recovery) are clearly numbered with explicit checkpoints and a self-check prompt; the operations are not destructive, so no validation feedback-loop is required.	3 / 3
Progressive Disclosure	The skill has no bundle files and keeps all 118 lines inline in one monolithic document with no navigation to deeper material, matching the anchor where content that could be split out remains inline.	2 / 3
	Total	10 / 12 Passed

Description

35%

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 conveys the skill's purpose and mandatory-proactive stance clearly, but it relies on directive jargon rather than natural user trigger terms and omits an explicit 'Use when' clause. This limits both completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions memory, recalling past work, or after a decision/bug/convention is established'.

Replace directive jargon ('ALWAYS ACTIVE', 'protocol') with natural terms a user would say ('remember', 'recall', 'save to memory').

Sharpen the action list to concrete, distinctive capabilities to reduce overlap with generic logging skills.

Dimension	Reasoning	Score
Specificity	Names the domain (persistent memory) and several concrete actions ('save decisions, conventions, bugs, and discoveries') but the action list is not comprehensive, matching the anchor that names a domain and some actions.	2 / 3
Completeness	It states what the skill does but lacks an explicit 'Use when...' trigger clause, so per the judging guideline a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Uses directive/technical phrasing ('ALWAYS ACTIVE', 'protocol', 'proactively', 'engram') rather than natural keywords a user would say when needing the skill; there are no user-facing trigger terms like 'remember' or 'recall'.	1 / 3
Distinctiveness Conflict Risk	'Persistent memory protocol' is a recognizable niche, but 'save decisions, conventions, bugs, and discoveries' is broad and could overlap with general memory or logging skills.	2 / 3
	Total	7 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Gentleman-Programming/engram
Path: plugin/claude-code/skills/memory/SKILL.md
Commit: 763a6ba

Reviewed: 3 days 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.