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

86%

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.

An exemplary instruction-only skill: lean, house-convention-only content, concrete commands, and correct delegation of dense material to separate files. The remaining gaps are minor — a worked example of a compliant description/callout, and an explicit local validation step in the update workflow.

Suggestions

Add one short worked example of a compliant two-sentence description (or a WRONG vs RIGHT callout) so the mandated format is shown, not just described.

Add an explicit validation step to the update workflow, e.g., 'after editing, run npm run skills:check before committing', so drift is caught locally rather than only in CI.

Dimension	Reasoning	Score
Conciseness	Roughly 40 lines with zero filler: 'Match it exactly.', 'No filler. State the thing and stop.' Every rule is a house convention Claude could not infer, and no space is spent explaining concepts Claude already knows. Matches anchor 5.	5 / 5
Actionability	Concrete, executable guidance throughout: exact file layout, required frontmatter fields, mandated body order, and copy-paste commands ('npm run skills:gen', 'npm run skills:check'). Falls short of anchor 5 because the rules mandate artifacts (a two-sentence description, a WRONG vs RIGHT callout) without showing one worked example of either.	4 / 5
Workflow Clarity	The mandated body order and the final Checklist give a clear sequence with checkpoints, and 'CI runs npm run skills:check and fails on drift' supplies a feedback loop. Anchor 4 rather than 5 because there is no explicit 'run skills:check before finishing' validation step in the update workflow itself.	4 / 5
Progressive Disclosure	Under 50 lines with no bundle files and well-organized sections (Directory layout, SKILL.md rules, Keep it current, Style, Checklist); external detail is correctly delegated to REFERENCE.md, EXAMPLES.md, and a one-level-deep shared TROUBLESHOOTING.md. Per the simple-skill guideline this warrants anchor 5.	5 / 5
	Total	18 / 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.

A strong description: third person, two sentences, explicit 'Use when' clause with three concrete triggers, and a clearly delimited niche. The only weakness is that the stated actions are broad verbs, and a few natural trigger variations ('creating a skill', 'SKILL.md') are absent.

Dimension	Reasoning	Score
Specificity	Names the domain ('agentmemory skill') and several concrete actions — 'writing or updating', 'restructuring', 'reviewing a skill contribution for consistency' — with minor gaps since the core actions are broad verbs rather than enumerated specifics. It lists more than the 1-2 actions of anchor 3 but is not the comprehensive action list of anchor 5.	4 / 5
Completeness	Explicitly answers both: 'The house format and rules for writing or updating an agentmemory skill' states what it does, and 'Use when adding a new skill, restructuring an existing one, or reviewing a skill contribution for consistency' gives concrete trigger phrases. This matches the anchor 5 example pattern exactly.	5 / 5
Trigger Term Quality	Triggers 'adding a new skill', 'restructuring an existing one', and 'reviewing a skill contribution for consistency' are phrases a user would naturally say. A few natural terms are missing (e.g., 'creating a skill', 'SKILL.md', 'skill format'), placing it at anchor 4 rather than the comprehensive synonym coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche ('agentmemory skill' house format) with triggers distinct from general code-review or document skills. Minimal overlap risk with other skills, matching anchor 5.	5 / 5
	Total	18 / 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: 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.