CtrlK
BlogDocsLog inGet started
Tessl Logo

agentmemory-mcp-tools

Map of every agentmemory MCP tool, what each does, and its parameters. Use when choosing which memory tool to call, when a tool name or argument is unclear, or when answering what agentmemory can do via MCP.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 is a tight, well-structured index that appropriately offloads the full tool table to REFERENCE.md and gives concrete selection guidance. Its main weaknesses are the missing explicit validation/recovery loop for destructive governance operations and the absence of a concrete tool-call example inline.

Suggestions

Add an explicit validation feedback loop for destructive/batch governance tools (e.g., memory_governance_delete, memory_heal): verify with memory_verify or memory_audit before and after, and recover via memory_heal on failure.

Include one concrete memory_save or memory_smart_search call with example arguments inline so the most common path is copy-paste-ready without opening REFERENCE.md.

Ensure REFERENCE.md is present in the bundle (e.g., under ./references/) so the one-level-deep reference resolves, since the body points to it as the canonical parameter source.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: it lists tool families as compact bulleted inventories and points elsewhere for details ('exact parameter names ... in REFERENCE.md'), with every token earning its place and no padding.

5 / 5

Actionability

Gives concrete, executable guidance (named tools, 'Pass only documented fields. REST handlers whitelist fields and drop unknown ones.') but defers exact parameter names to REFERENCE.md rather than providing a copy-paste-ready example call, leaving a minor gap.

4 / 5

Workflow Clarity

The Workflow section sequences the steps clearly (pick narrowest tool → look up parameters → pass documented fields), and the governance/health family plus the whitelist note act as soft validation, but there is no explicit validate-then-fix feedback loop for risky operations like memory_governance_delete or memory_heal.

4 / 5

Progressive Disclosure

Content is well-organized into clear sections with a one-level-deep reference to REFERENCE.md for the full table, but REFERENCE.md is referenced yet not present in the bundle, so navigation is clear but the referenced file cannot be verified.

4 / 5

Total

17

/

20

Passed

Description

87%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 is well-crafted: it states the skill's purpose concisely in third person and provides explicit, multi-clause 'Use when' triggers tied to a distinct niche. It earns top marks on completeness and distinctiveness, with only minor gaps in action specificity and trigger synonyms.

DimensionReasoningScore

Specificity

Names the domain ('every agentmemory MCP tool') and lists several concrete actions (mapping tools, describing parameters, clarifying unclear tool names/arguments), but stops short of enumerating specific tool capabilities, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both 'what' ('Map of every agentmemory MCP tool, what each does, and its parameters') and 'when' ('Use when choosing which memory tool to call, when a tool name or argument is unclear, or when answering what agentmemory can do via MCP') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural trigger phrases users would say ('choosing which memory tool to call', 'tool name or argument is unclear', 'what agentmemory can do'), with good coverage but missing a few common synonyms like 'recall', 'save', or 'memory tools'.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (the agentmemory MCP tool catalog) with triggers specific to that domain, so it is unlikely to fire for unrelated skills and carries minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rohitg00/agentmemory
Reviewed

Table of Contents

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.