Write Agentmemory Skill
Author or refactor agentmemory plugin skills so they follow the house SKILL.md tier, triggers, and cross-link rules before contributors merge.
Overview
write-agentmemory-skill is a journey-wide agent skill that enforces the agentmemory house format for SKILL.md packages—usable whenever a solo builder needs to add, restructure, or review a skill before committing.
Install
npx skills add https://github.com/rohitg00/agentmemory --skill write-agentmemory-skillWhat is this skill?
- Mandatory layout: SKILL.md (required), optional REFERENCE.md and EXAMPLES.md under plugin/skills/<name>/
- SKILL.md capped under 100 lines with fixed body order: Quick start, Why, Workflow, Anti-patterns, Checklist, See also
- Two-sentence frontmatter description: capability plus “Use when” triggers, third person, under 1024 chars
- user-invocable: true only for slash-command skills; reference/knowledge skills stay false
- WRONG vs RIGHT anti-pattern callout required for the top mistake
- SKILL.md must stay under 100 lines
- Frontmatter description under 1024 characters with two sentences
- Fixed body sections including Workflow with decision gates and a top-mistake WRONG vs RIGHT callout
Adoption & trust: 3 installs on skills.sh; 21.9k GitHub stars; trending (+300% hot-view momentum).
What problem does it solve?
Your agentmemory skill drafts drift in length, triggers, and section order so agents pick the wrong skill or load bloated context.
Who is it for?
Maintainers and contributors standardizing new or updated agentmemory skills before merge or plugin release.
Skip if: Runtime memory operations (use agentmemory MCP tools) or one-off hacks that ignore the tiered SKILL/REFERENCE/EXAMPLES split.
When should I use this skill?
Use when adding a new skill, restructuring an existing one, or reviewing a skill contribution for consistency.
What do I get? / Deliverables
You ship a compliant under-100-line SKILL.md with clear triggers, gated workflow steps, anti-patterns, and sibling cross-links, optionally splitting facts and examples into REFERENCE.md and EXAMPLES.md.
- Compliant SKILL.md with quick start, workflow gates, checklist, and See also
- Optional REFERENCE.md for dense facts and generated tables
- Optional EXAMPLES.md with worked transcripts
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Draft a new memory workflow skill with correct frontmatter triggers before wiring MCP tools.
Check a contributor SKILL.md against the numbered workflow and WRONG vs RIGHT anti-pattern before approving.
Split an overlong SKILL.md into REFERENCE.md tables after production agents started skipping the skill.
Align EXAMPLES.md transcripts so sibling skills cross-link one level deep only.
How it compares
Use this meta formatter instead of ad-hoc SKILL.md templates that lack agentmemory-specific triggers and line budgets.
Common Questions / FAQ
Who is write-agentmemory-skill for?
Solo builders and plugin maintainers who extend agentmemory with new skills and need agents to load consistent, skimmable SKILL.md files.
When should I use write-agentmemory-skill?
Any time you add a skill, restructure an existing one, or review a PR—during Build agent-tooling work, before Ship review of contributions, or during Operate iteration when fixing stale skill docs—whenever format consistency matters.
Is write-agentmemory-skill safe to install?
It is editorial and structural guidance with no mandated shell or network tools in the excerpt; still review the Security Audits panel on this Prism page before installing from an unfamiliar source.
SKILL.md
READMESKILL.md - Write Agentmemory Skill
agentmemory skills follow one tiered format so they stay skimmable, accurate, and current. Match it exactly. ## Directory layout ```text plugin/skills/<name>/ SKILL.md (required, under 100 lines) REFERENCE.md (optional, dense facts; auto-generate data tables) EXAMPLES.md (optional, worked transcripts) ``` ## SKILL.md rules - Frontmatter: `name`, `description`, optional `argument-hint`, and `user-invocable`. Set `user-invocable: true` only for skills the user runs as a slash command; reference and knowledge skills are `false`. - Description is two sentences and the only thing the agent sees when deciding to load the skill. Sentence one states the capability. Sentence two starts "Use when" and lists concrete triggers. Keep it distinct from sibling skills, under 1024 chars, third person. - Body order: Quick start (one concrete example), Why (the governing principle), Workflow (numbered steps with decision gates), Anti-patterns (a WRONG vs RIGHT callout for the top mistake), Checklist, See also (cross-link siblings), Reference or Troubleshooting pointer. - Stay under 100 lines. Move dense facts to REFERENCE.md and examples to EXAMPLES.md. - Cross-references link one level deep only. Shared recovery steps live in `../_shared/TROUBLESHOOTING.md`, never inlined. ## Keep it current Facts that exist in source (tool names and parameters, REST endpoints, env vars, connect adapters, hook events) are generated, never hand-typed. Edit the source, then run `npm run skills:gen`. CI runs `npm run skills:check` and fails on drift, so generated tables cannot fall behind the code. ## Style No external or competitor product names. No emojis. No em-dashes. No filler. State the thing and stop. ## Checklist - Description has a "Use when" sentence with real triggers. - SKILL.md is under 100 lines. - No time-sensitive claims and no duplicated troubleshooting block. - Concrete example present; generated facts come from the generator. - Cross-links resolve and go one level deep.