agentmemory-hooks

The agentmemory plugin hooks that capture observations automatically across the agent session lifecycle. Use when explaining how memory gets captured without manual saves, when debugging missing observations, or when tuning what gets recorded.

Quality

85%

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

78%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 concise and well-structured with concrete install commands and named configuration flags, but it is more descriptive than instructional in places and its two cross-file references point to files that are not present in the bundle. Fixing the dangling references and sharpening the actionable guidance would raise the content score.

Suggestions

Provide the missing referenced files (REFERENCE.md and ../_shared/TROUBLESHOOTING.md) or remove the references, so the one-level-deep disclosure is actually navigable rather than dangling.

Add a short, explicit diagnostic workflow for the "observations are missing" case (e.g., check plugin enabled → check server running → check hook events in REFERENCE.md) so the guidance is instructional rather than only descriptive.

Optionally surface the key capture/injection flags with their default values inline so Claude can tune recording without leaving SKILL.md.

Dimension	Reasoning	Score
Conciseness	The ~35-line body is lean and assumes Claude's competence — it never explains what hooks or memory are, and each section earns its tokens with concrete commands, flags, and pointers.	5 / 5
Actionability	It gives executable install commands, a live URL, specific environment flags (AGENTMEMORY_AUTO_COMPRESS, AGENTMEMORY_INJECT_CONTEXT), and a concrete diagnostic step, but much of the "What the hooks do" section describes behavior rather than instructing Claude how to act, leaving minor gaps.	4 / 5
Workflow Clarity	The Quick start gives a clear two-step sequence (install, then watch observations land live as a lightweight checkpoint), and this is a simple informational skill rather than a destructive or batch operation, so no validation cap applies; it falls short of 5 only because the body is reference-style rather than a fully checkpointed workflow.	4 / 5
Progressive Disclosure	The body is well-organized into clear sections and explicitly signals one-level-deep pointers (REFERENCE.md, ../_shared/TROUBLESHOOTING.md), but neither referenced file exists in any bundle directory, so the promised deeper content is unreachable and the cross-file navigation is effectively broken.	3 / 5
	Total	16 / 20 Passed

Description

92%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 strong: it pairs a concrete statement of what the hooks do with an explicit "Use when..." clause covering three realistic triggering situations, all in third person. Trigger-term coverage is the only mild weakness, missing a few natural synonyms a user might say.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions across the session lifecycle — "capture observations automatically", "explaining how memory gets captured", "debugging missing observations", and "tuning what gets recorded" — giving comprehensive, specific coverage rather than vague domain naming.	5 / 5
Completeness	It clearly states what the skill does ("hooks that capture observations automatically across the agent session lifecycle") and pairs it with an explicit "Use when..." clause giving three concrete trigger scenarios, matching the top anchor.	5 / 5
Trigger Term Quality	It uses natural phrases users would actually say ("debugging missing observations", "tuning what gets recorded", "without manual saves"), giving good keyword coverage, but it omits a few natural variations such as "recall", "recap", or "agent memory" that a user might voice.	4 / 5
Distinctiveness Conflict Risk	The narrow framing around the agentmemory plugin's lifecycle hooks and observation capture carves out a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 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: rohitg00/agentmemory
Path: plugin/skills/agentmemory-hooks/SKILL.md
Commit: 2d38daf

Reviewed: 1 day 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.