engram-memory-protocol

Persistent memory discipline for Engram contributors. Trigger: Decisions, bugfixes, discoveries, preferences, or session closure.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/memory-protocol/SKILL.md

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.

The content is a tight, well-organized instruction skill with named tools and clear sequenced workflows, fully respecting the token budget. Its only gap is the absence of executable tool signatures and explicit validation checkpoints.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive (named tools, short rules) with no padding or explanation of concepts Claude already knows; every line earns its place. It is not below 5 because there is no verbosity to trim.	5 / 5
Actionability	It names concrete tools (mem_save, mem_context, mem_search, mem_session_summary) and gives clear ordering and structured fields (What/Why/Where/Learned). It is not 5 because tool signatures and arguments (e.g. mem_search parameters, topic_key usage) are not specified, leaving minor gaps.	4 / 5
Workflow Clarity	Session close and post-compaction steps are clearly numbered and the save/search rules give explicit conditional triggers. It is not 5 because there are no validation/feedback checkpoints (e.g. confirming a save succeeded), though these are minor given the non-destructive nature of memory operations.	4 / 5
Progressive Disclosure	At ~47 lines with no need for external references, the skill is organized into clear sections (When to Use, Save/Search/Session Close Rules) that are easy to navigate. It is not below 5 because the structure is clean and no content belongs in a separate file.	5 / 5
	Total	18 / 20 Passed

Description

53%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.

The description clearly scopes the skill to Engram memory discipline and provides an explicit trigger clause, but it is light on concrete capabilities and relies on somewhat generic trigger situations. It is functional but could be sharper.

Suggestions

Name concrete actions in the description, e.g. 'Save, search, and summarize session memory via the Engram tools (mem_save, mem_search, mem_session_summary).' to lift specificity.

Add natural user-facing trigger terms and synonyms such as 'remember', 'recall', 'save a decision', or 'before context compaction' to improve trigger term quality.

Tighten the 'what' clause so it distinguishes this from generic note-taking skills, e.g. explicitly mention the Engram toolset and persistent topic_key-based recall.

Dimension	Reasoning	Score
Specificity	The phrase 'Persistent memory discipline' names the domain but lists no concrete actions (no save/search/summarize verbs), matching the anchor 'Names the domain but actions are minimal or generic.' It does not reach 3 because no concrete capability is stated, only an abstract discipline.	2 / 5
Completeness	It states a 'what' ('Persistent memory discipline for Engram contributors') and an explicit 'when' ('Trigger: ...'), satisfying both halves. It falls short of 5 because the 'what' is abstract rather than listing concrete actions.	4 / 5
Trigger Term Quality	'Trigger: Decisions, bugfixes, discoveries, preferences, or session closure' supplies several relevant trigger terms, but they are generic situations and lack common synonyms (e.g. remember, recall, save). It is above 2 (more than one or two generic keywords) but below 4 due to missing natural variations.	3 / 5
Distinctiveness Conflict Risk	'Engram contributors' and the memory framing give it a niche, but the trigger situations (decisions, bugfixes, discoveries) are broad enough to overlap with general memory or logging skills. It is not 4 because the overlap risk with closely related skills remains non-minor.	3 / 5
	Total	12 / 20 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: skills/memory-protocol/SKILL.md
Commit: 47f281c

Reviewed: 6 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.