Tessl • The management layer for AI agent skills

SkillPublic

remember

Save an insight, decision, or learning to agentmemory's long-term storage with searchable concept tags. Use when the user says "remember this", "save this", "note that", "don't forget", or wants to preserve knowledge for future sessions.

Quality

91%

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

Quality

Content

96%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.

An exemplary skill body: lean, immediately actionable with a concrete tool-call example and expected output, and a well-sequenced workflow with confirmation and a checklist. The only flaw is a dangling reference to TROUBLESHOOTING.md that is not present in the bundle being evaluated.

Dimension	Reasoning	Score
Conciseness	The ~60-line body is lean: every section (Quick start, Why, Workflow, Anti-patterns, Checklist) earns its place, no concepts Claude already knows are explained, and the Why section carries skill-specific rationale rather than filler. Matches anchor 5 (lean and efficient).	5 / 5
Actionability	The Quick start gives a concrete, copy-paste-ready memory_save example with real parameter values (content, concepts, files) plus expected output, and the workflow specifies exact formats (2-5 lowercased concepts, comma-separated strings, agentId for multi-agent). Matches anchor 5 (fully executable, common cases covered).	5 / 5
Workflow Clarity	The 6-step workflow is clearly sequenced with a confirmation checkpoint (step 5: echo concepts back), explicit update semantics (step 6), and a checklist section. Saving a memory is not destructive or batch, so the validation cap does not apply. Matches anchor 5.	5 / 5
Progressive Disclosure	Sections are well organized and the single external reference is clearly signaled and one level deep. However, the referenced TROUBLESHOOTING.md does not exist anywhere in the provided bundle (no references/, scripts/, or assets/ directories), a minor navigation gap that fits anchor 4 rather than anchor 5's easy navigation.	4 / 5
	Total	19 / 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 description with an explicit what-and-when structure and highly natural trigger phrases. The only gap is action coverage breadth — it describes saving and tagging but omits secondary capabilities the body actually supports (file references, updates, agent scoping).

Suggestions

Broaden the what-clause to mention 1-2 more supported actions, e.g. 'Save an insight, decision, or learning ... with searchable concept tags and file references' to lift specificity from 1-2 actions toward several.

Consider adding an update-related trigger phrase (e.g. "update what you remembered") to reduce overlap ambiguity with generic 'save this' file operations and sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ("Save an insight, decision, or learning to agentmemory's long-term storage with searchable concept tags") but coverage is not comprehensive — no mention of file-path tagging, updates, or agent scoping. This matches anchor 3 (1-2 concrete actions, not comprehensive) rather than anchor 4, which expects several listed actions.	3 / 5
Completeness	Explicitly answers both questions: the "what" (save insight/decision/learning to long-term storage with searchable concept tags) and an explicit "Use when..." clause with concrete trigger phrases. This mirrors anchor 5's example structure exactly; not anchor 4, where the "when" would be less specific.	5 / 5
Trigger Term Quality	The trigger phrases are exactly what a user would naturally say: "remember this", "save this", "note that", "don't forget", plus the intent phrasing "wants to preserve knowledge for future sessions". Coverage of natural synonyms is comprehensive for this domain, matching anchor 5.	5 / 5
Distinctiveness Conflict Risk	The agentmemory niche and tag-based saving are distinct, but the trigger "save this" has minor overlap risk with generic file-saving phrasing. Mostly distinct with minor overlap (anchor 4) rather than a fully clear niche (anchor 5).	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: rohitg00/agentmemory
Path: plugin/skills/remember/SKILL.md
Revision: 70517d2

Reviewed: 12 days 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.

remember

Table of Contents

Is this your skill?