Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

memory

Persistent memory system for preferences, facts, and notes

Quality

66%

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 ./src/skills/bundled/memory/SKILL.md

Quality

Content

72%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 highly actionable, with complete, copy-paste-ready TypeScript and chat-command examples, and is reasonably token-efficient. Its main weaknesses are the lack of validation/verification steps for destructive memory operations and a monolithic inline API reference that would benefit from splitting into separate reference files.

Suggestions

Add an explicit validation/verification checkpoint for destructive operations, e.g. 'Before /forget all, run /memory to review items and confirm with the user; after forget, recall to verify deletion.'

Split the full TypeScript API reference into a separate REFERENCE.md (or similar) and keep SKILL.md as a concise overview with one-level-deep links, to improve progressive disclosure.

Tighten redundancy between the Chat Commands and TypeScript API sections so each token earns its place.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean code examples, command tables, and API snippets with little over-explanation of concepts Claude already knows, matching the score-4 anchor 'Efficient; minor instances of over-explanation that could be trimmed.' There is mild redundancy (the chat-commands section and the TypeScript API cover the same store/recall/forget surface), keeping it just below a 5.	4 / 5
Actionability	The body provides copy-paste-ready, executable TypeScript covering create, remember, recall, semanticSearch, forget, and daily-journal flows, plus concrete slash commands, matching the score-5 anchor 'Fully executable; copy-paste ready code; specific examples cover the common cases.' Not below 5 because examples are complete and cover the documented cases.	5 / 5
Workflow Clarity	Content is organized by operation, but destructive and batch operations (/forget all, forgetAll, forgetByType) carry only a '(careful!)' warning with no validation or verification step (e.g., confirm-before-delete or recall-to-verify), which per the judging guidelines caps workflow clarity at 3. Not a 4 because the explicit validation/feedback loop the guideline requires for destructive operations is absent.	3 / 5
Progressive Disclosure	Sections are well organized, but the entire API reference (chat commands, TypeScript API, types, backends, best practices) is inlined in one ~180-line SKILL.md with no separate reference files and no cross-file navigation, matching the score-3 anchor 'Some structure... content that should be separate is inline.' Not a 4 because the under-50-line simple-skill exception does not apply and nothing is split into one-level-deep reference files.	3 / 5
	Total	15 / 20 Passed

Description

45%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 names the memory domain and its content types but omits action verbs and any 'Use when' trigger guidance, leaving both specificity and completeness at the midpoint or below. It is functional but generic and would benefit from explicit capabilities and trigger phrasing.

Suggestions

Add concrete action verbs, e.g. 'Store, recall, and semantically search user preferences, facts, and notes across conversations.'

Append an explicit trigger clause, e.g. 'Use when the user wants to persist or retrieve personal preferences, facts, notes, or rules between conversations.'

Include natural synonyms or request phrasing users actually say (e.g., 'remember this', 'what do you know about me', 'recall') to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Persistent memory system') and enumerates content types ('preferences, facts, and notes') but states no concrete action verbs (e.g., store, recall, search), matching the score-2 anchor 'Names the domain but actions are minimal or generic.' It is not a 3 because there are no explicit concrete actions; it is not a 1 because the domain and its scope are clearly named rather than entirely vague.	2 / 5
Completeness	It provides a clear 'what' (a persistent memory system for preferences, facts, notes) but no 'when' or 'Use when...' trigger guidance, which per the judging guidelines caps completeness at 3. Not a 4 because there is no explicit 'when' clause at all.	3 / 5
Trigger Term Quality	'preferences', 'facts', and 'notes' are natural terms a user might say, but the description lacks common synonyms or natural request phrases and omits any trigger phrasing, fitting the score-3 anchor 'Some relevant keywords but missing common variations or synonyms.' Not a 4 because keyword coverage is thin and no user-facing request phrasing is present.	3 / 5
Distinctiveness Conflict Risk	'Memory' is a recognizable niche and the enumerated types add specificity, but the phrasing is still broad enough to overlap with note-taking or general preferences skills, matching the score-3 anchor 'Somewhat specific but could still overlap with similar skills.' Not a 4 because no distinct trigger phrases reduce that overlap.	3 / 5
	Total	11 / 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: alsk1992/CloddsBot
Path: src/skills/bundled/memory/SKILL.md
Revision: c930628

Reviewed: 1 month ago

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.

memory

Table of Contents

Is this your skill?