CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

86

3.13x
Quality

82%

Does it follow best practices?

Impact

91%

3.13x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Evaluation results

96%

83%

DataHub Connection String Advisor

New agentmemory skill authoring

Criteria
Without this skill
With this skill

SKILL.md location

33%

100%

Frontmatter name field

0%

100%

Frontmatter description field

0%

100%

Frontmatter user-invocable field

0%

100%

user-invocable is false

0%

100%

Description two sentences

0%

100%

Description Use-when opener

0%

100%

Description third person

0%

100%

Quick start section

0%

100%

Why section

0%

100%

Workflow section

100%

100%

Anti-patterns section

0%

100%

Checklist section

20%

100%

Under 100 lines

0%

100%

No emojis

100%

100%

No em-dashes

0%

0%

78%

63%

Deploy Helper Skill Audit

SKILL.md style and format violation review

Criteria
Without this skill
With this skill

Two-sentence description

0%

100%

Use when trigger

0%

100%

user-invocable false

0%

0%

No emojis

100%

100%

No em-dashes

0%

100%

Troubleshooting not inlined

0%

53%

One-level cross-links

0%

100%

Under 100 lines

0%

100%

100%

40%

Update the Webhook Handler Skill Documentation

Generated facts placement and contributor workflow documentation

Criteria
Without this skill
With this skill

Hook events in REFERENCE.md

100%

100%

Env vars in REFERENCE.md

100%

100%

No inline hook event table in SKILL.md

100%

100%

skills:gen in workflow

0%

100%

skills:check in workflow

0%

100%

SKILL.md line count

100%

100%

Quick start section

50%

100%

Anti-patterns section

0%

100%

Checklist section

0%

100%

No emojis in SKILL.md

100%

100%

Repository
rohitg00/agentmemory
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.