Agent skill
managing-context
Discovers and loads relevant project context from markdown documentation before each task. Matches context documents based on keywords, file paths, and task types. Use at task start to access project plans, architecture, and implementation status.
Install this agent skill to your Project
npx add-skill https://github.com/jiunbae/agent-skills/tree/main/context/context-manager
SKILL.md
Context Manager
Auto-load relevant project documentation.
Context Directory Structure
context/
├── planning/ # Roadmaps, implementation plans
├── architecture/ # System design, decisions
├── guides/ # Getting started, tutorials
├── operations/ # Deployment, troubleshooting
└── README.md # Context overview
Workflow
Step 1: Check for Context
ls -la context/ 2>/dev/null || echo "No context directory"
Step 2: Match Documents
Based on task keywords:
- "monitoring" →
context/monitoring/ - "deploy" →
context/operations/ - "API" →
context/architecture/
Step 3: Load Relevant Docs
Read top 3-5 matching documents:
# Example matches for "add monitoring"
context/monitoring/architecture.md (score: 0.92)
context/operations/alerting.md (score: 0.85)
Step 4: Summarize
Brief user on loaded context:
📄 Loaded context:
- monitoring/architecture.md: Prometheus + Grafana stack
- operations/alerting.md: Alert rules and escalation
Matching Algorithm
| Factor | Weight |
|---|---|
| Keyword in filename | 40% |
| Keyword in category | 30% |
| Task type match | 20% |
| Recency | 10% |
After Task: Update Context
If significant work done:
# Update implementation status
echo "- [x] Feature X completed" >> context/planning/status.md
Best Practices
DO:
- Check context at task start
- Update status after completing work
- Keep docs concise
DON'T:
- Load entire context directory
- Create duplicate documentation
- Use date-based filenames (git tracks history)
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
jiunbae/agent-skills
implementing-in-background
Orchestrates multiple AI agents (Claude, Codex, Gemini) for parallel implementation in the background. Separates independent tasks from planning docs, each agent writes code directly. Context-safe with auto-save. Use for "백그라운드 구현", "bg impl", "병렬 구현", "Codex로 구현", "구현해줘", "코드 작성해줘" requests.
jiunbae/agent-skills
review-fix-loop
Autonomous review-fix cycle that continuously reviews code using background-reviewer, fixes issues, and repeats until all findings are resolved. Use for "리뷰 루프", "자동 개선", "review fix loop", "리뷰 반복", "코드 개선 루프", "keep reviewing" requests.
jiunbae/agent-skills
planning-in-background
Orchestrates multiple AI agents (Claude, Codex, Gemini) for parallel planning in the background with auto-save. Agents continue running even when session hits context limits. Use for "백그라운드 기획", "bg plan", "병렬 기획", "멀티 AI 기획", "기획해줘", "N명이 기획", "계획", "플래닝", "plan", "설계" requests.
jiunbae/agent-skills
background-reviewer
Orchestrates multi-LLM parallel code review using Claude, Codex, and Gemini. Each agent reviews from a different perspective using agent personas (security, architecture, code quality, performance). Supports persona-based review via `agt persona review`. Use for "코드 리뷰", "리뷰해줘", "bg review", "멀티 리뷰", "background review", "페르소나 리뷰" requests.
jiunbae/agent-skills
indexing-static-context
Provides an index of global static context files in ~/.agents/. Returns appropriate static file paths for natural language queries like "내 정보", "보안 규칙". Use when other skills or agents need to locate reference information.
jiunbae/agent-skills
recommending-skills
Automatically recognizes and recommends suitable skills for user requests. Discovers helpful installed skills even without explicit skill requests. Implicitly activates on all user requests.
Didn't find tool you were looking for?