aso-mcp-skills
AGENTS.md8 starsChanged 14 days agoMITView on GitHub
This repo contains App Store Intelligence skills following the Agent Skills open standard, plus an MCP server for real-time data access. Compatible directories: .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/ Description drives discovery — agent reads all descriptions to decide which skill to load. Include "When the user wants to...", trigger keywords, and "For X, see Y skill" boundaries. iOS limits: Title 30 chars, Subtitle 30 chars, Keyword field 100 chars (comma-separated, no spaces), Description 4000 chars (not indexed for search), Promotional text…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- appkittieSkill
- ad-intelligenceSkill
- app-discoverySkill
- app-marketing-contextSkill
- competitor-analysisSkill
- creator-discoverySkill
- growth-analysisSkill
- keyword-researchSkill
- metadata-optimizationSkill
- onboarding-analysisSkill
- revenue-analysisSkill
- review-analysisSkill
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 35
No filler, no hedging
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
Agent Guidelines
This repo contains App Store Intelligence skills following the Agent Skills open standard, plus an MCP server for real-time data access.
Structure
src/worker.py — MCP server (Cloudflare Workers, Python)
skills/<name>/SKILL.md — Skill instructions (required, <500 lines)
skills/<name>/references/ — Detailed docs loaded on demand (optional)
tools/integrations/ — API integration guides (AppKittie)
tools/REGISTRY.md — Capability matrix: which skill uses which toolCompatible directories: .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
SKILL.md Format
---
name: skill-name # Must match directory, lowercase+hyphens, 1-64 chars
description: ... # Trigger phrases + scope boundaries, 1-1024 chars
metadata:
version: 1.0.0
---Description drives discovery — agent reads all descriptions to decide which skill to load. Include "When the user wants to...", trigger keywords, and "For X, see Y skill" boundaries.
Writing Style
- Direct, actionable, second person
- Tables for comparisons, numbered lists for steps
- Bold for key terms, code blocks for examples
- No filler, no hedging
App Store Reference
iOS limits: Title 30 chars, Subtitle 30 chars, Keyword field 100 chars (comma-separated, no spaces), Description 4000 chars (not indexed for search), Promotional text 170 chars.
Key rules: Title has highest keyword weight. Don't repeat keywords across fields. Use singular forms. Don't include "app" or category names in keyword field.
Commits
feat(skill-name): ... / fix(skill-name): ... / docs: ...
Branches: feature/skill-name, fix/skill-name-desc, docs/desc
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.