common-context-optimization

Maximize context window efficiency, reduce latency, and prevent lost-in-middle issues through strategic masking and compaction. Use when token budgets are tight, tool outputs flood the context, conversations drift from intent, or latency spikes from cache misses. (triggers: *.log, chat-history.json, reduce tokens, optimize context, summarize history, clear output)

385 stars

Best use case

common-context-optimization is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Maximize context window efficiency, reduce latency, and prevent lost-in-middle issues through strategic masking and compaction. Use when token budgets are tight, tool outputs flood the context, conversations drift from intent, or latency spikes from cache misses. (triggers: *.log, chat-history.json, reduce tokens, optimize context, summarize history, clear output)

Teams using common-context-optimization should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/common-context-optimization/SKILL.md --create-dirs "https://raw.githubusercontent.com/HoangNguyen0403/agent-skills-standard/main/.agent/skills/common/common-context-optimization/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/common-context-optimization/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How common-context-optimization Compares

Feature / Agentcommon-context-optimizationStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Maximize context window efficiency, reduce latency, and prevent lost-in-middle issues through strategic masking and compaction. Use when token budgets are tight, tool outputs flood the context, conversations drift from intent, or latency spikes from cache misses. (triggers: *.log, chat-history.json, reduce tokens, optimize context, summarize history, clear output)

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

## **Priority: P1 (OPTIMIZATION)**

Manage the Attention Budget. Treat context as a scarce resource.

## 1. Observation Masking (Noise Reduction)

**Problem**: Large tool outputs (logs, JSON lists) flood context and degrade reasoning.
**Solution**: Replace raw output with semantic summaries _after_ consumption.

1. **Identify** outputs exceeding 50 lines or 1 KB.
2. **Extract** critical data points immediately.
3. **Mask** by rewriting history to replace raw data with a summary placeholder.
4. **See** `references/masking.md` for patterns.

See [implementation examples](references/implementation.md) for masking patterns.

## 2. Context Compaction (State Preservation)

**Problem**: Long conversations drift from original intent.
**Solution**: Recursive summarization that preserves _State_ over _Dialogue_.

1. **Trigger** compaction every 10 turns or 8k tokens.
2. **Compact**:
   - **Keep**: User Goal, Active Task, Current Errors, Key Decisions.
   - **Drop**: Chat chit-chat, intermediate tool calls, corrected assumptions.
3. **Format**: Update System Prompt or Memory File with compacted state.
4. **See** `references/compaction.md` for algorithms.

See [implementation examples](references/implementation.md) for compacted state format.

## 3. KV-Cache Awareness (Latency)

**Goal**: Maximize pre-fill cache hits.

- **Static Prefix**: Enforce strict ordering — System -> Tools -> RAG -> User.
- **Append-Only**: Never insert into the middle of history; append new turns only.

## References

- [Observation Masking Patterns](references/masking.md)
- [Compaction Algorithms](references/compaction.md)

## Anti-Patterns

- **No raw tool dumps**: Mask large outputs immediately after extracting data.
- **No unbounded growth**: Compact every 10 turns to preserve intent over dialogue.
- **No middle insertions**: Append-only history maximizes KV cache hits.

Related Skills

nextjs-optimization

385
from HoangNguyen0403/agent-skills-standard

Optimize images, fonts, scripts, and metadata for Next.js performance and Core Web Vitals. Use when configuring next/image for LCP, next/font for zero layout shift, next/script loading strategies, or generateMetadata for SEO. (triggers: **/layout.tsx, **/page.tsx, next/image, next/font, metadata, generateMetadata)

common-observability

385
from HoangNguyen0403/agent-skills-standard

Enforce structured JSON logging, OpenTelemetry distributed tracing, and RED metrics across backend services. Use when adding request correlation, setting up tracing spans, defining SLO burn-rate alerts, or instrumenting middleware. (triggers: **/*.service.ts, **/*.handler.ts, **/*.middleware.ts, **/*.interceptor.ts, **/*.go, **/*.java, **/*.kt, **/*.py, logging, tracing, metrics, opentelemetry, observability, slo)

common-mobile-ux-core

385
from HoangNguyen0403/agent-skills-standard

Enforce universal mobile UX principles for touch-first interfaces including touch targets, safe areas, and mobile-specific interaction patterns. Use when building mobile screens, handling touch interactions, or validating safe area compliance. (triggers: **/*_page.dart, **/*_screen.dart, **/*_view.dart, **/*.swift, **/*Activity.kt, **/*Screen.tsx, mobile, responsive, SafeArea, touch, gesture, viewport)

common-mobile-animation

385
from HoangNguyen0403/agent-skills-standard

Apply motion design principles for mobile apps covering timing curves, transitions, gestures, and performance-conscious animations. Use when implementing screen transitions, gesture-driven interactions, shared-element animations, or optimizing animation frame rates on iOS, Android, or Flutter. (triggers: **/*_page.dart, **/*_screen.dart, **/*.swift, **/*Activity.kt, **/*Screen.tsx, Animation, AnimationController, Animated, MotionLayout, transition, gesture)

common-error-handling

385
from HoangNguyen0403/agent-skills-standard

Cross-cutting standards for error design, response shapes, error codes, and boundary placement across API, domain, and infrastructure layers. Use when defining error hierarchies, wrapping exceptions, building standardized error responses, or placing error boundaries in layered architectures. (triggers: **/*.service.ts, **/*.handler.ts, **/*.controller.ts, **/*.go, **/*.java, **/*.kt, **/*.py, error handling, exception, try catch, error boundary, error response, error code, throw)

common-architecture-diagramming

385
from HoangNguyen0403/agent-skills-standard

Standards for creating clear, audience-appropriate C4 and UML architecture diagrams with Mermaid. Use when producing system context diagrams, container views, sequence diagrams, or updating ARCHITECTURE.md files. (triggers: ARCHITECTURE.md, **/*.mermaid, **/*.drawio, diagram, architecture, c4, system design, mermaid)

common-architecture-audit

385
from HoangNguyen0403/agent-skills-standard

Audit structural debt, logic leakage, and monolithic components across Web, Mobile, and Backend codebases. Use when reviewing architecture, assessing tech debt, detecting logic in wrong layers, or identifying God classes. (triggers: package.json, pubspec.yaml, go.mod, pom.xml, nest-cli.json, architecture audit, code review, tech debt, logic leakage, refactor)

common-api-design

385
from HoangNguyen0403/agent-skills-standard

Apply REST API conventions — HTTP semantics, status codes, versioning, pagination, and OpenAPI standards for any framework. Use when designing endpoints, choosing HTTP methods, implementing pagination, or writing OpenAPI specs. (triggers: **/*.controller.ts, **/*.router.ts, **/*.routes.ts, **/routes/**, **/controllers/**, **/handlers/**, rest api, endpoint, http method, status code, versioning, pagination, openapi, api design, api contract)

common-accessibility

385
from HoangNguyen0403/agent-skills-standard

Enforce WCAG 2.2 AA compliance with semantic HTML, ARIA roles, keyboard navigation, and color contrast standards for web UIs. Use when building interactive components, adding form labels, fixing focus traps, or auditing a11y compliance. (triggers: **/*.tsx, **/*.jsx, **/*.html, **/*.vue, **/*.component.html, accessibility, a11y, wcag, aria, screen reader, focus, alt text)

common-workflow-writing

385
from HoangNguyen0403/agent-skills-standard

Rules for writing concise, token-efficient workflow and skill files. Prevents over-building that requires costly optimization passes. Use when creating or editing workflow files, SKILL.md files, or new skill definitions. (triggers: .agent/workflows/*.md, SKILL.md, create workflow, write workflow, new skill, new workflow)

common-ui-design

385
from HoangNguyen0403/agent-skills-standard

Design distinctive, production-grade frontend UI with bold aesthetic choices. Use when building web components, pages, interfaces, dashboards, or applications in any framework (React, Next.js, Angular, Vue, HTML/CSS). (triggers: build a page, create a component, design a dashboard, landing page, UI for, build a layout, make it look good, improve the design, build UI, create interface, design screen)

common-tdd

385
from HoangNguyen0403/agent-skills-standard

Implements a strict Red-Green-Refactor loop to ensure zero production code is written without a prior failing test. Use when: creating new features, fixing bugs, or expanding test coverage. (triggers: **/*.test.ts, **/*.spec.ts, **/*_test.go, **/*Test.java, **/*_test.dart, **/*_spec.rb, tdd, unit test, write test, red green refactor, failing test, test coverage)