advanced-memory-skill-creator
Skill19 starsChanged 20 days agoMITView on GitHub
Use when planning, scaffolding, validating, or packaging Claude skills inside Advanced Memory MCP.
In this repository121 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/advanced-memory-mcp-standards.mdcCursor rule
- .cursor/rules/architect.mdcCursor rule
- llms-full.txtllms.txt
- llms.txtllms.txt
- windsurf-ide-integrationSkill
- full-stack-developerSkill
- mcp-server-architectSkill
- skill-creatorSkill
- agentic-zettelkastenSkill
- ai-debate-dominatorSkill
- china-expertSkill
- content-strategy-plannerSkill
- copywriting-and-persuasion-expertSkill
- graphic-design-fundamentalsSkill
- music-production-basicsSkill
- photography-composition-guideSkill
- podcast-production-guideSkill
- presentation-design-expertSkill
- social-media-strategy-advisorSkill
- storytelling-and-narrative-coachSkill
- technical-writing-editorSkill
- uiux-design-consultantSkill
- video-editing-advisorSkill
- asian-fusion-chefSkill
- bbq-and-smoking-expertSkill
- bread-baking-artisanSkill
- cocktail-mixology-masterSkill
- coffee-and-espresso-expertSkill
- french-pastry-masterSkill
- italian-cooking-expertSkill
- meal-prep-efficiency-guruSkill
- mexican-cuisine-specialistSkill
- vegetarian-and-vegan-chefSkill
- wine-sommelier-assistantSkill
- business-japanese-specialistSkill
- classical-japanese-literature-guideSkill
- etymology-and-word-origins-expertSkill
- french-language-coachSkill
- japanese-grammar-masterSkill
- jlpt-preparation-expert-n5-n1Skill
- kanji-etymology-and-learning-expertSkill
- advanced-keigo-usage-expertSkill
- linguistic-anthropology-guideSkill
- polyglot-learning-strategies-expertSkill
- spanish-language-tutorSkill
- translation-techniques-specialistSkill
- abstract-algebra-specialistSkill
- applied-mathematics-for-engineeringSkill
- calculus-tutor-single-multivariableSkill
- complex-analysis-expertSkill
- differential-equations-solverSkill
- discrete-mathematics-expertSkill
- fourier-analysis-expertSkill
- game-theory-strategistSkill
- linear-algebra-expertSkill
- mathematical-logic-expertSkill
- mathematical-proofs-mentorSkill
- matrix-theory-specialistSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 53
Document new sources inside the Source Log and modules/research-checklist.md when revisions are made.
- Very specific: line 54
Update the status banner to 🟢 High after field validation and peer review.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Advanced Memory Skill Creator
Status: ✅ Research complete
Last validated: 2025-11-08
Confidence: 🟡 Medium — Ready for packaging – keep sources current
When to load this skill
- You need to build a new Claude skill that matches Anthropic’s gold-standard structure.
- You are upgrading a legacy skill (single SKILL.md file) into the modular layout.
- You must validate a skill before sharing it with teammates or packaging it for SkillsMP.
- You want to create repeatable automation around scaffolding, validation, or packaging.
Quick start workflow
- Collect requirements using the prompts in modules/process-guide.md.
- Run the MCP tool:
adn_skills_creator( operation="scaffold", skill_name="my-new-skill", output_dir="skills/custom", category="developer" ) - Fill in content following the templates in
modules/core-guidance.md. - Validate and package:
adn_skills_creator(operation="validate", skill_path="skills/custom/my-new-skill") adn_skills_creator(operation="package", skill_path="skills/custom/my-new-skill", output_dir="dist") - Record sources, update
the status banner, and publish.
CLI equivalents
- Scaffold:
uv run am-skill-creator scaffold my-new-skill --output-dir skills/custom - Validate:
uv run am-skill-creator validate skills/custom/my-new-skill - Package:
uv run am-skill-creator package skills/custom/my-new-skill --output-dir dist - Upgrade legacy skill:
uv run am-skill-creator upgrade skills/legacy/old-skill
Module overview
- Core guidance — Complete playbooks for scaffolding, validation, packaging, and automation.
- Process guide — Anthropic six-step methodology tailored to Advanced Memory.
- Known gaps — Validation tasks, pending research, and integration TODOs.
- Research checklist — Mandatory workflow to capture sources and verify freshness.
Research status
- Research complete as of 2025-11-08 (see sources above); rerun checklist quarterly or after Anthropic updates.
- Document new sources inside
the Source Logand modules/research-checklist.md when revisions are made. - Update
the status bannerto 🟢 High after field validation and peer review.
Related tools and references
adn_skills_creatorportmanteau – runtime interface for all operations.scripts/refactor_skills_modular.py– bulk upgrade helper.docs/patterns/claude-skills/skill-creator-reference.md– Anthropic gold standard.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

