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

78%

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 ./plugin/skills/agentmemory-hooks/SKILL.md

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.

A concise, well-structured overview body with concrete install commands and exact flag names, appropriate for a simple informational skill. The main defects are a dangling REFERENCE.md pointer that fails to resolve within the bundle and a debugging step that lacks a concrete verification command.

Suggestions

Ship REFERENCE.md (the generated hook-event listing) in the skill bundle or remove the pointer, since the body's final section directs readers to a file that is not present.

Add a concrete check command for the "server is running" debugging step (e.g., the exact curl or status invocation against http://localhost:3113) so the failure path is executable rather than implied.

Clarify that ../_shared/TROUBLESHOOTING.md resolves at the plugin level, or inline the plugin-specific troubleshooting steps, so readers are not sent outside the bundle with no path context.

Dimension	Reasoning	Score
Conciseness	The ~33-line body is lean with no padding and no explanation of concepts Claude already knows; every section (Quick start, What the hooks do, Important, See also, Reference) carries new information. It assumes competence ("You do not have to call memory_save for routine work") and every token earns its place.	5 / 5
Actionability	Concrete, copy-paste install commands ("/plugin marketplace add rohitg00/agentmemory", "/plugin install agentmemory"), exact flag names (AGENTMEMORY_AUTO_COMPRESS, AGENTMEMORY_INJECT_CONTEXT), and a live URL. Not 5: the debugging step "confirm the plugin is enabled and the server is running" gives no concrete command to perform that check, leaving a minor gap.	4 / 5
Workflow Clarity	For a simple single-purpose informational skill the sequence is clear: install via Quick start, observe at the localhost URL, and follow the Important section when observations are missing. Not 5: the debug path stops at an implicit checkpoint ("confirm the plugin is enabled and the server is running") without an explicit verification step or command.	4 / 5
Progressive Disclosure	Sections are well organized and references are clearly signaled ("The exact registered hook events live in REFERENCE.md"), but neither referenced file — REFERENCE.md nor ../_shared/TROUBLESHOOTING.md — exists in the bundle (references/, scripts/, assets/ are absent), so navigation dead-ends. Anchor 3 (references present but ineffective/organization gap) fits better than 4, which requires minor gaps only, and better than 2, since the structure itself is good and no oversized content is inlined.	3 / 5
	Total	16 / 20 Passed

Description

78%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 explicit what and when clauses using natural trigger phrases. Its main weaknesses are the noun-phrase form that lists few concrete actions and mild overlap with the sibling agentmemory-config skill on the "tuning what gets recorded" trigger.

Dimension	Reasoning	Score
Specificity	"The agentmemory plugin hooks that capture observations automatically across the agent session lifecycle" names the domain and one concrete action (automatic capture) but is a noun phrase without an enumerated list of several concrete capabilities. It does not reach anchor 4 because no multiple specific actions are listed, and exceeds anchor 2 because the capture mechanism and lifecycle scope are concrete.	3 / 5
Completeness	Both what ("plugin hooks that capture observations automatically across the agent session lifecycle") and when (three explicit "Use when..." clauses: explaining capture, debugging missing observations, tuning recording) are clearly and explicitly stated with concrete trigger phrases, matching the anchor-5 example pattern.	5 / 5
Trigger Term Quality	"explaining how memory gets captured without manual saves", "debugging missing observations", and "tuning what gets recorded" are natural phrases users would say. Not 5: synonyms and sibling-skill terms users might naturally say (e.g., "recall", "handoff", "recap", "session history") are absent; not 3 because multiple natural trigger variations are present rather than a single generic keyword.	4 / 5
Distinctiveness Conflict Risk	The hook-capture niche is mostly distinct from other skills, but "when tuning what gets recorded" overlaps the sibling agentmemory-config skill (capture/injection flags), a minor conflict risk with a closely related skill. Not 5 because of that overlap; not 3 because the hook-lifecycle framing and debugging-missing-observations triggers are fairly specific to this skill.	4 / 5
	Total	16 / 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: c314c7b

Reviewed: 4 days 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.