Canonical consumer algorithm for the `DECISIONS_CONTEXT` index passed by orchestrators. The index lists each ADR/PF entry with ID, truncated title, status, and area — not the full body. Use this skill to surface the right decisions and pitfalls for your task without loading the entire corpus.

Canonical consumer algorithm for the `KNOWLEDGE_CONTEXT` index passed by orchestrators. The index lists each ADR/PF entry with ID, truncated title, status, and area — not the full body. Use this skill to surface the right decisions and pitfalls for your task without loading the entire corpus.

This skill should be used when the user asks to "validate input", "parse request data", "handle form data", "add Zod schema", "sanitize user input", or creates API endpoints and system boundaries. Provides parse-don't-validate patterns with schema validation for type-safe boundary enforcement and hostile input defense.

This skill should be used when reviewing code for high cyclomatic complexity, deep nesting, or long functions.

This skill should be used when reviewing code for high cyclomatic complexity, deep nesting, or long functions.

This skill should be used when reviewing code for naming convention violations, pattern deviations, or inconsistent API styles.

This skill should be used when reviewing code for naming convention violations, pattern deviations, or inconsistent API styles.

This skill should be used when the user asks to "handle errors", "inject dependencies", "return Result", "make it immutable", "compose with pipes", or implements business logic, error handling, or service composition. Provides Result type patterns, dependency injection, immutability by default, pipe composition, and structured logging for robust application architecture.

Agent pipeline for DEBUG intent in ambient ORCHESTRATED mode. Competing hypothesis investigation, parallel evidence gathering, convergence validation, and optional fix.

This skill should be used when reviewing dependency changes, lock files, or package additions.

This skill should be used when reviewing dependency changes, lock files, or package additions.

This skill should be used when the user asks to "create a review report", "write a status log", "add documentation", "name this artifact", or creates files in the .docs/ directory. Provides naming conventions, templates, and directory structure for reviews, debug sessions, design docs, and all persistent DevFlow documentation artifacts.

Agent pipeline for EXPLORE intent in ambient GUIDED and ORCHESTRATED modes. Codebase analysis, flow tracing, dependency mapping, and architecture understanding.

Structures codebase exploration into a feature knowledge base

Structures codebase exploration into a feature knowledge base

This skill should be used when the user asks to "rebase safely", "manage branches", "fix merge conflicts", "clean git history", "undo a commit", or performs git operations that could lose work. Provides safety patterns for branch management, force-push prevention, index.lock handling, and sequential command execution to prevent data loss.

This skill should be used when the user asks to "comment on a PR", "create a release", "manage issues", "use gh CLI", "check PR status", or performs GitHub API operations. Provides patterns for PR comments, issue management, release workflows, rate limiting, and gh CLI usage for safe GitHub automation.

Agent pipeline for IMPLEMENT intent in ambient ORCHESTRATED mode. Pre-flight checks, plan synthesis, Coder execution, and quality gates.

This skill should be used when the user asks to "create an API endpoint", "add CRUD operations", "implement event handlers", "set up logging", "add configuration", or builds features involving database operations, REST/GraphQL APIs, pub/sub patterns, or service configuration. Provides implementation patterns that follow existing codebase conventions.