api-design
Skill104 starsChanged 2 months agoMITView on GitHub
Use BEFORE adding any new tool, parameter, or endpoint to the Apple Mail MCP server. Also use when considering API changes, evaluating feature requests, or when tempted to create a specialized operation. Contains the decision tree that prevents tool sprawl and the anti-pattern catalog.
192 other projects use a version of this.
Adopted by
Most recently taken up by
- samsam007b/claude-code-standards-kittheir own version, first seen Nov 16, 2026
- lengrufeng2008/dsh-skill-librarytheir own version, first seen Nov 15, 2026
- agenticluke/rest-api-designer-plustheir own version, first seen Nov 15, 2026
- dovuthanhhien1609/claude-skillstheir own version, first seen Nov 15, 2026
- tayyebi/skillstheir own version, first seen Nov 15, 2026
- swap-cameroon/kuro-antigravity-configtheir own version, first seen Nov 15, 2026
Used with
Projects with it also use db-design, everything-claude-code and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
yuexueyuSkilldb-design
数据库工程师技能 - Schema设计、索引优化、并发安全、数据库审计。当你涉及数据库表/字段/索引/SQL/迁移/MCP数据库操作、建表改表、写查询时必须使用此技能。即使用户只是说"加个字段"或"查下数据",也应触发。
Also in 4 projects that use this
InfopibeSkilleverything-claude-code
Also in 9 projects that use this
mryeastcodeSkilleverything-claude-code-conventions
Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.
Also in 8 projects that use this
tpavanipradeepSkillnextjs-turbopack
Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.
Also in 15 projects that use this
Indium-AI-LabsSkilldata-pipeline-design
Design batch or incremental ETL and ELT pipelines and warehouse models: grain, partitioning, idempotent loads, late-arriving data, data quality tests, PII controls, and cost monitoring, before building them. Use when adding or changing a dbt model, warehouse table, scheduled transformation, or ingestion job. Not for transactional schema design (use the database-design skill) or event-sourced stores (use the event-sourcing-architecture skill).
Also in 3 projects that use this
thejordanleopoldSkillthird-party-integration
Use when integrating with external APIs, payment processors (Stripe), webhooks, or third-party services. Use when implementing API clients with authentication and rate limiting, handling webhooks with signature verification and idempotency, writing contract tests for external services, or isolating third-party dependencies behind adapters. Triggers: \"Stripe\", \"payment integration\", \"webhook\", \"third-party API\", \"external service\", \"API client\", \"integrate with\", \"signature verification\", \"idempotency key\".
Also in 3 projects that use this
Other versions192 projects use a version of this.
Word for word · 1
- s-morgan-jeffries/apple-mail-fast-mcp★ 103100% same
Edited · 0
None found.
Wrote their own version · 191
- affaan-m/ECC★ 246ksame name
- databasus/databasus★ 9.3ksame name
- RostislavDugin/postgresus★ 9.3ksame name
- authgear/authgear-server★ 2.1ksame name
- xu-xiang/everything-claude-code-zh★ 1.9ksame name
- Aaronontheweb/dotnet-skills★ 1.2ksame name
- epam/ai-dial-chat★ 501same name
- loulanyue/awesome-claude-notes★ 272same name
- KbWen/agentic-os★ 236same name
- DevelopersGlobal/ai-agent-skills★ 216same name
181 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- applescript-mailSkill
- integration-testingSkill
- performance-patternsSkill
- releaseSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 165 edited versions we read keep these.
4
Distinctive
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 83
Verify it doesn't fit in an existing tool (run through decision tree above)
- Distinctive: line 84
Write unit tests (mock AppleScript)
- Distinctive: line 85
Write integration tests (real Mail.app)
- Distinctive: line 90
Add blind eval scenarios if tool has non-obvious parameters
“Common” is measured: kept by at least 6 in 10 of the 165 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Apple Mail MCP API Design
The current API has 17 tools organized into 4 phases. Tool count should grow slowly and deliberately. Every new tool request must pass through the decision tree.
Decision Tree: Use BEFORE Adding Any Tool
Can an existing tool handle this with current parameters? (70% of cases: YES)
|-- Searching with a new filter? -> Add parameter to search_messages()
|-- Reading with different format? -> Add parameter to get_messages()
|-- Sending/composing with new options? -> Extend create_draft() or update_draft()
|
Can an existing tool handle this with a NEW parameter? (20% of cases: YES)
|-- Example: search by date range -> add date_from, date_to to search_messages()
|-- Example: search flagged only -> add is_flagged to search_messages()
|
Is this truly a distinct operation? (10% of cases: MAYBE)
|-- Different Mail.app object? (accounts, rules, smart mailboxes)
|-- Different action type? (not CRUD on messages/mailboxes)
|
If NO to all three: You might need a new tool. This is rare.Anti-Patterns (Never Do These)
Field-Specific Tools
# WRONG - creates tool sprawl
mark_as_flagged(message_id)
mark_as_unflagged(message_id)
mark_as_junk(message_id)
# RIGHT - one CRUD-style update tool with patch semantics
update_message(message_ids, read_status=True)
update_message(message_ids, flag_color="red")
update_message(message_ids, destination_mailbox="Archive", account="Gmail")Specialized Search Tools
# WRONG - each filter becomes a tool
get_unread_messages()
get_flagged_messages()
get_messages_from_sender()
# RIGHT - parameters on existing search
search_messages(read_status="unread")
search_messages(is_flagged=True)
search_messages(sender_contains="user@example.com")Formatted Text Returns
# WRONG - returns human-readable string
def list_mailboxes():
return "Inbox (42 messages)\nSent (15 messages)"
# RIGHT - returns structured data
def list_mailboxes():
return {"success": True, "mailboxes": [{"name": "Inbox", "count": 42}, ...]}Response Format Rules
- Always return
dict[str, Any]with"success": bool - Errors include
"error"(message) and"error_type"(category) - Never return formatted text strings — return structured data
- Include context fields — e.g.,
"messages_found": 5alongside the results
Tool Naming Convention
- Verb + noun:
search_messages,create_draft,delete_messages - Plural when accepting lists:
delete_messages,get_messages - CRUD-style for multi-field mutation:
update_message(read_status, flag_color, destination_mailbox, ...)over per-field verbs (mark_as_read,flag_message,move_messages). Patch semantics — unset fields are unchanged.
Adding a New Tool Checklist
- Verify it doesn't fit in an existing tool (run through decision tree above)
- Write unit tests (mock AppleScript)
- Write integration tests (real Mail.app)
- Implement in
mail_connector.py - Expose in
server.py - Run
./scripts/check_client_server_parity.sh - Update
docs/reference/TOOLS.md - Add blind eval scenarios if tool has non-obvious parameters
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.

