ai-coding-resources

Complexity assessment framework for routing issues to appropriate preparation depth. Defines triage signals, mode selection criteria, and output templates for solo and lightweight modes. Referenced by prepare-issue before design session dispatch.

Documents agent frontmatter metadata spec and patterns for creating effective project-specific agents. Use when: creating agents, understanding agent discovery, or configuring agent metadata.

Discovers existing skills and agents across project, user, and plugin layers and provides similarity heuristics for detecting overlapping assets. Use when generating skills or agents, detecting duplicate assets, or checking for name collisions.

Governs multi-round specialist deliberation for design sessions, plan reviews, and adversarial dispatch. Defines conflict detection, dispatch rounds, cross-pollination, and resolution protocols. Referenced during design sessions, plan reviews, and adversarial plan challenges.

Structured workflow for planning and executing GitHub issues. Ensures thorough research, proper requirements analysis, and build-vs-buy evaluation before implementation. Use when: planning an issue, executing an issue, or reviewing a plan.

Writes requirements-focused issues that describe what needs to be done, not how to implement it. Works with any tracker. Use when creating issues, updating requirements, or planning work.

Framework for reviewing pull requests with severity-tiered findings, ecosystem-adapted focus areas, and strict exit criteria. Defines review principles, severity tiers, finding disposition framework, and the CREATE ISSUE protocol. Use when reviewing PRs from CLI or CI.

Shared context-resolution pattern for workflow commands. Encodes the canonical 3-step protocol (read config, auto-detect, validate) with extension points for command-specific behavior. Use when: resolving project context, reading workflow config, or auto-detecting project settings.

Safe refactoring patterns for AI-assisted development. Covers refactoring triggers, AI-specific anti-patterns (additive-only changes, wrapper inflation, dead code accumulation) with corrective annotations, size-check heuristics, and verification criteria. Use when: planning refactoring work, reviewing code for structural improvements, addressing tech debt during execution, or evaluating whether a change qualifies as refactoring vs. new feature work.

Security detection patterns, anti-patterns, and OWASP mapping for code review. Covers input validation, authentication/authorization, secret management, and dependency audit with diff-level detection heuristics. Use when: reviewing PRs with security-relevant changes, evaluating authentication flows, or assessing input handling and dependency risk.

Guides creation of effective skills that extend Claude with specialized knowledge, workflows, or tool integrations. Covers skill anatomy, frontmatter fields, bundled resources, progressive disclosure, and the init/edit/package lifecycle. Use when: creating a new skill, updating an existing skill, understanding skill structure, or packaging skills for distribution.

Technology stack detection reference tables and per-stack analysis guidance. Maps project files to languages, dependencies to frameworks, and directory structures to domains. Includes deeper analysis criteria for LLM-driven codebase understanding. Use when detecting a project's technology stack, scanning for languages, or identifying frameworks.

Governs parallel code execution teams with file ownership, TDD workflow, git coordination, and team lifecycle management. Defines spawn templates, timeout policies, and shutdown procedures. Referenced during parallel execution phases of issue implementation.

Criteria for analyzing codebases to inform agent and skill generation. Encodes signal hierarchy, specialist indicators, and domain significance evaluation. Use when: generating agents, generating skills, or evaluating project setup.

Staleness triage framework for evaluating when training data is reliable vs. when verification is required. Classifies knowledge domains by staleness risk and provides decision criteria for verification. Use when: writing code that depends on library versions, API patterns, CLI flags, or framework conventions.

Structured debugging methodology for hypothesis-driven failure resolution. Encodes failure classification, evidence hierarchy, hypothesis quality criteria, and escalation thresholds. Use when repeated failures occur during test-driven development, full suite validation, or CI failure loops.

Stack-aware TDD patterns, anti-patterns, and quality heuristics for test-driven development. Provides framework-agnostic testing knowledge that adapts guidance based on detected technology stack. Targets AI-specific testing failure modes. Use when writing tests during TDD loops, reviewing test quality, or planning testing strategy.