code-context-engineering
by Roy Yuen
A high-precision pre-coding gate that detects conflicting requirements and prevents agents from making wrong assumptions.
- Prevent breaking changes by detecting conflicts between docs and existing code
- Force a "stop-and-ask" gate when acceptance criteria are ambiguous or missing
- Synchronize multi-agent handoffs by validating summaries against source files
$7
One-time purchase
Included in download
- Prevent breaking changes by detecting conflicts between docs and existing code
- Force a "stop-and-ask" gate when acceptance criteria are ambiguous or missing
- Includes example output and usage patterns
See it in action
Context Sources: - Project rules: AGENTS.md (No direct DB edits) - User request: "Force update user status in SQL" - Existing code: UsersController.js (Uses Repository pattern) Gate Status: blocked_by_rule Reason: Direct SQL edits are forbidden by project_rules. I can use the UserRepo instead.
A high-precision pre-coding gate that detects conflicting requirements and prevents agents from making wrong assumptions.
$7
One-time purchase
⚡ Also available via Agensi MCP — your AI agent can load this skill on demand via MCP. Learn more →
Included in download
- Prevent breaking changes by detecting conflicts between docs and existing code
- Force a "stop-and-ask" gate when acceptance criteria are ambiguous or missing
- Includes example output and usage patterns
- Instant install
- One-time purchase
See it in action
Context Sources: - Project rules: AGENTS.md (No direct DB edits) - User request: "Force update user status in SQL" - Existing code: UsersController.js (Uses Repository pattern) Gate Status: blocked_by_rule Reason: Direct SQL edits are forbidden by project_rules. I can use the UserRepo instead.
Screenshots
About This Skill
What it does
Code Context Engineering is a high-precision pre-flight skill for AI agents that prevents "wrong-task" failures. Before a single line of code is written, it forces the agent to inventory disparate sources—including repository rules, user requests, existing codebases, external documentation, and historical chat memory—to identify contradictions, stale instructions, or missing criteria.
Why use this skill
Standard LLM prompting often results in "hallucinated intent" where agents guess how to resolve conflicting requirements. This skill replaces guesswork with a formal Conflict Gate. It enforces a "stop-and-ask" protocol if choosing a path would materially alter scope, safety, or data integrity. It builds a source-of-truth contract that ensures the downstream implementation is actually what the developer needs, not just what the agent inferred.
Supported workflows
- Complex Refactoring: Ensures existing behavior is preserved unless explicitly targeted for change.
- Feature Migrations: Detects version drift between installed packages and external documentation.
- Architecture Planning: Aligns current requests with long-term project rules and memory.
- Issue Triage: Identifies when ticket requirements are insufficient to begin coding.
The Output
The skill produces a Context Ledger with confidence labels and a Gate Status (Clear, Blocked, or Needs Verification). If blocked, it generates a high-signal, "low-AI-smell" clarification request that pinpoints the exact sources in conflict.
📖 Learn more: Best DevOps & Deployment Skills for Claude Code →
Use Cases
- Prevent breaking changes by detecting conflicts between docs and existing code
- Force a "stop-and-ask" gate when acceptance criteria are ambiguous or missing
- Synchronize multi-agent handoffs by validating summaries against source files
- Audit legacy documentation against current code behavior to find stale context
How to Install
unzip code-context-engineering.zip -d ~/.claude/skills/Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Early access skill
Be the first to review this skill.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
No special permissions declared or detected
Frequently Asked Questions
Learn More About AI Agent Skills
Similar Skills
git-commit-writer
Writes conventional commit messages by analyzing your staged git changes. Detects commit type, scope, and breaking changes automatically.
env-doctor
Diagnoses why your project will not start. Checks runtime versions, dependencies, environment variables, databases, ports, and build artifacts systematically.
prompt-engineer
Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.
ai-productivity
High-speed intake for shaping vague prompts, triaging complex tasks, and compressing context for efficient execution.