Agent skill
smith-ctx-cursor
Cursor context management with /summarize command, @ mentions for file inclusion, and @codebase discovery. Use when operating in Cursor IDE or when context exceeds 60%. Activate for context optimization in Cursor sessions.
Install this agent skill to your Project
npx add-skill https://github.com/tianjianjiang/smith/tree/main/smith-ctx-cursor
SKILL.md
Cursor Context Management
- Load if: Using Cursor, context >60%
- Prerequisites: @smith-ctx/SKILL.md
CRITICAL: Context Commands (Primacy Zone)
Agent prompts for context status, then recommends /summarize at 60-70%.
Automatic summarization uses smaller flash model → vague summaries, lost details. Recommend manual /summarize before auto-trigger.
After any summarization:
- Re-state critical context (task, files, decisions)
- Use @ mentions to restore files:
@auth/middleware.ts @auth/tokens.ts
/summarize - Manual Summarization
When to use: Before automatic trigger, between task phases
Recommendation format:
/summarize
After summarizing, re-add critical files:
@auth/middleware.ts @auth/tokens.ts
Verify summary preserved:
- Task goals
- File locations
- Design decisions
- Next steps
- Claiming to execute
/summarizedirectly - Relying solely on automatic summarization
- Continuing without verifying summary quality
@ Mentions - Force-Include Files
Syntax: @filename or @path/to/file.ext
Use @ mentions for:
- After summarization (restore critical files)
- Before implementation (load files to modify)
- Large files >600 lines (@codebase truncates at 250)
Patterns:
@auth/middleware.ts @auth/tokens.ts # Multiple files
@src/auth.ts @tests/auth.test.ts # File + tests
- @codebase for files >600 lines (only loads first 250)
- @ mention entire directories
- @ mention files you won't use
@codebase - Discovery Only
Use for: Finding files, understanding patterns Limitation: Returns summaries, not complete code
Workflow:
@codebase authentication middleware→ Find files@auth/middleware.ts→ Load full file- Implement with complete context
.cursorrules - Persistent Instructions
Location: .cursorrules in project root
Put in .cursorrules (project-specific):
- Technology stack
- Project structure
- Reference to @AGENTS.md
Put in skill files (personal/global):
- Universal principles
- Language style
- Git workflow
Example:
# Project Rules
Follow standards from @AGENTS.md
## Stack
- Framework: NestJS
- Database: PostgreSQL
- Testing: Jest
- @smith-ctx/SKILL.md - Universal context strategies
ACTION (Recency Zone)
Proactive context management:
- Prompt for context status
- At 60-70%: Recommend
/summarizebefore auto-trigger - After summarization: Remind to re-add files with @ mentions
Agent RECOMMENDS - user executes the command.
File size strategy:
- <250 lines: @codebase works
- 250-600 lines: Use @ mention
-
600 lines: Always @ mention
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
tianjianjiang/smith
smith-style
File naming, path standards, and conventional commits. Use when naming files, creating branches, writing commit messages, or setting up new projects. Covers underscore vs hyphen conventions, commit format, and branch naming patterns.
tianjianjiang/smith
smith-stacks
Stacked pull request workflows for large features. Use when creating stacked PRs, managing dependent PRs, or rebasing after parent merges. Covers stack creation, merge order, and squash merge handling.
tianjianjiang/smith
smith-python
Python development with uv, pytest, ruff, and type hints. Use when writing Python code, running tests, managing Python packages, or working with virtual environments. Covers import organization, type hints, pytest patterns, and environment variables.
tianjianjiang/smith
smith-principles
Fundamental coding principles (DRY, KISS, YAGNI, SOLID, HHH). Use when starting any development task, evaluating implementation approaches, or reviewing code quality. Always active as foundation for all development decisions.
tianjianjiang/smith
smith-nuxt
Nuxt 3 development patterns including auto-import stubbing for tests, environment variable conventions, and middleware testing. Use when working with Nuxt projects, testing Nuxt components/middleware, or configuring Nuxt environment variables.
tianjianjiang/smith
smith-plan
Plan tracking protocol (portable). Progress tracking with checkboxes, iteration workflow, completion/blocker signals. Use when executing multi-step plans, tracking task progress, or working from plan files. IMPORTANT - Always update the plan file after completing tasks.
Didn't find tool you were looking for?