write-agentmemory-skill

The house format and rules for writing or updating an agentmemory skill. Use when adding a new skill, restructuring an existing one, or reviewing a skill contribution for consistency.

3.13x

Quality

82%

Does it follow best practices?

Impact

91%

3.13x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

86%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 tight, well-organized instruction-only skill that models its own rules: lean prose, concrete commands, a clear generation/validation loop, and an explicit one-level-deep reference structure. The only gap is the absence of a full worked SKILL.md example to anchor the body-order template.

Suggestions

Add a short 'Quick start' worked example showing a minimal compliant SKILL.md (frontmatter + one-line body) to make the body-order template copy-paste ready and lift actionability.

Make the currency loop an explicit numbered micro-workflow with a decision gate (e.g., 'If skills:check reports drift, regenerate before committing') to match the workflow clarity the skill itself prescribes.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: tight rules, a compact directory-layout block, and a one-line style directive ('State the thing and stop.'), with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	Concrete, executable guidance is present (directory layout, body-order template, `npm run skills:gen` / `npm run skills:check` commands, a checklist), but there is no full worked example SKILL.md to copy, leaving a minor gap.	4 / 5
Workflow Clarity	The 'Keep it current' section gives a clear sequence (edit source -> run skills:gen -> CI runs skills:check and fails on drift) with a validation checkpoint, but the bulk of the body is rules rather than a numbered workflow with decision gates, so a checkpoint is implicit.	4 / 5
Progressive Disclosure	The directory-layout block clearly signals the tiered split (SKILL.md plus optional REFERENCE.md/EXAMPLES.md) and mandates one-level-deep cross-links ('Shared recovery steps live in ../_shared/TROUBLESHOOTING.md, never inlined'); the file is under 50 lines, well-sectioned, and needs no external references.	5 / 5
	Total	18 / 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 well-crafted two-sentence description that explicitly pairs a capability statement with a 'Use when' trigger clause and concrete, naturally-phrased triggers. It is slightly abstract on the 'what' side and has minor overlap risk with sibling review skills.

Suggestions

Replace the abstract phrase 'house format and rules' with one or two concrete actions (e.g., 'Defines the required directory layout, frontmatter fields, and body section order for agentmemory skills') to lift specificity.

Add a synonym or file-based trigger (e.g., 'or when editing a SKILL.md file') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('agentmemory skill') and two concrete actions ('writing or updating'), but 'house format and rules' is abstract rather than enumerating specific actions, so coverage is not comprehensive.	3 / 5
Completeness	Sentence one states the capability ('house format and rules for writing or updating an agentmemory skill') and sentence two opens with 'Use when' listing concrete triggers, explicitly answering both what and when.	5 / 5
Trigger Term Quality	Natural trigger phrases users would say ('adding a new skill', 'restructuring an existing one', 'reviewing a skill contribution') give good coverage, though a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The 'agentmemory skill' niche is mostly distinct with clear triggers, though 'reviewing a skill contribution for consistency' could overlap slightly with a general skill-reviewer sibling.	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/write-agentmemory-skill/SKILL.md
Commit: 2d38daf

Reviewed: about 22 hours 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.