Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

agent-memory

A hybrid memory system that provides persistent, searchable knowledge management for AI agents.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-agent-memory/SKILL.md

Quality

Content

67%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 body delivers concrete, executable setup and usage guidance with unusually strong safety gating (pinned revision, review-before-install, approval checkpoint, scope verification). Its main weaknesses are redundant purpose statements and the absence of error-recovery steps.

Suggestions

State the skill's purpose once — remove the verbatim description echo in "When to Use" and the filler "Example" user request, which adds no new guidance.

Add a short error-recovery step to Setup (e.g., what to check if `npm ci` or `npm run compile` fails, or how to confirm the MCP server actually started).

Dimension	Reasoning	Score
Conciseness	The skill's purpose is stated three times — the description is echoed verbatim in "When to Use", paraphrased again in the next paragraph, and restated in the "Example" user request — and the Limitations section is partly boilerplate. The remaining sections are otherwise tight.	3 / 5
Actionability	Concrete, executable commands throughout: a pinned-revision clone, `npm ci`, `npm run compile`, `npm run start-server my-project "$(pwd)"`, and MCP tool calls with args and usage examples. Minor placeholders (`cd <approved-agent-memory-directory>`, `content: "..."`) keep it from being fully copy-paste ready.	4 / 5
Workflow Clarity	The review → install → start sequence is clear with explicit checkpoints ("wait for explicit user approval", "verify the resulting file changes", "check the resulting documentation diff"), but there are no error-recovery loops for failures such as a compile error or server startup failure.	4 / 5
Progressive Disclosure	A single, well-sectioned SKILL.md with no bundle files and clear navigation, but at ~110 lines it exceeds the under-50-line simple-skill exception, and content like the security review checklist and MCP tool reference could be split into separate files.	4 / 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 states what the system is but never says when to use it, and it relies on category-level language rather than concrete capabilities. It sits just below the midpoint: acceptable but generic for a crowded memory-skill space.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants the agent to remember, recall, or persist knowledge across sessions, or mentions a memory bank or knowledge base for AI agents."

Replace the abstract "provides persistent, searchable knowledge management" with 2-3 concrete capabilities, e.g. "Record decisions and findings, search memories by query, type, or tags, and sync them to project markdown files."

Add distinguishing keywords (memory bank, MCP memory tools, cross-session context) that separate this skill from generic note-taking or documentation skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ("hybrid memory system", "knowledge management for AI agents") but the only action offered is the generic "provides... management" — no concrete operations like searching memories by query or recording decisions are stated.	2 / 5
Completeness	The "what" is clear (a hybrid, persistent, searchable memory system), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like "memory", "searchable", and "knowledge management" are relevant, but natural user phrasings ("remember this", "recall", "context") and their variations are missing. Not score 2 because more than one or two relevant, domain-specific keywords are present.	3 / 5
Distinctiveness Conflict Risk	The "hybrid memory system for AI agents" framing is somewhat specific, but memory/knowledge-management is a crowded skill category with high overlap risk and no distinct trigger phrases to disambiguate.	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: boisenoise/skills-collections
Path: skills/antigravity-agent-memory/SKILL.md
Revision: dab80ce

Reviewed: 6 hours 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.

agent-memory

Table of Contents

Is this your skill?