Claude Code: AI Agent Workflow Collection

Detect gaps and contradictions across all prior phases; surface cross-phase tensions, unresolved assumptions, and sales/investor objections. Run after developing-gtm-strategy (Phase 4).

Analyzes C++ desktop codebase architecture, dependency graphs, framework detection, and migration assessment. Use when exploring an unfamiliar C++ project or assessing upgrade paths.

Assess a source project's technical capabilities. Reads config/sources.md and produces a structured capability profile. Use to start the GTM pipeline or evaluate technical differentiators (Phase 0).

Audit code against OWASP Top 10 vulnerabilities with structured findings. Use when reviewing code for security issues or conducting security audits.

Runs KiCad DRC/ERC checks, exports gerbers and BOM, and generates a structured findings report. Use when reviewing PCB designs, running design rule checks, or preparing manufacturing outputs.

Audit README.md files against best practices for repos, accounts, or orgs. Detects missing sections, stale links, inconsistent formatting, and convention violations. Use when reviewing README quality across one or many repos.

Audits website accessibility for WCAG 2.1 AA compliance, generating findings and code fixes. Use when reviewing accessibility, keyboard navigation, screen reader compatibility, or inclusive design.

Audits a site's SEO and AI-search (GEO) readiness — meta tags, Open Graph/Twitter, JSON-LD, robots/llms conventions — and generates fixes. Use when reviewing search visibility, social previews, structured data, or LLM/AI-crawler discoverability.

Audits website usability for UX optimization, covering forms, navigation, validation, and microcopy. Use when reviewing user experience, task completion flows, or interface friction points.

Generates compliance requirements from CE/FCC/UL standards for a device description. Use when starting a new embedded product, checking regulatory compliance, or generating initial SYS-REQ entries from applicable directives.

Generate commit message for staged changes, pause for approval, then commit. Stage files first with git add, then run this skill.

Compacts verbose context into structured summary. Use after pollution sources (searches, logs, JSON) or at phase milestones.

Creates GitHub Actions for the Marketplace. Use when scaffolding a new action, implementing composite steps, writing BATS tests, or preparing a Marketplace release.

Scaffold or review Makefiles following org conventions. Use when creating a new Makefile, auditing an existing one, or adding recipes to a project. Auto-detects project type from the working directory.

Create a pull request from the current branch. Analyzes commits, generates title+body from PR template, pauses for approval, then pushes and creates PR. Use after committing changes.

Designs concise, streamlined backend systems matching exact task requirements. Use when planning APIs, data models, system architecture, or when the user requests backend design work.

Detect hardcoded secrets, API keys, tokens, and credentials in code and git history. Use when auditing for leaked secrets or before publishing code.

Develop customer segmentation, channel selection, and a 90-day launch plan from Phase 2 PMF assessment. Run after validating-product-market-fit (Phase 3).

Extracts decisions, rejected alternatives, and patterns from recent plans into a persistent learnings document. Use after completing a plan or sprint.

Audit documentation against its declared hierarchy — broken links, duplicates, misplaced content, stale references, single-source-of-truth enforcement. Use for doc health reviews.

Build UserStory.md interactively via Q&A. Use when the user wants to create a user story document or start the assisted workflow.

Generates prd.json task tracking file from PRD.md requirements document. Use when initializing Ralph loop or when the user asks to convert PRD to JSON format for autonomous execution.

Converts UserStory.md into a structured PRD.md document. Use after generating UserStory.md and before initializing the Ralph loop.

Generates structured reports including status updates, assessments, post-mortems, and executive summaries. Use when writing a report, creating a project status update, or documenting an incident post-mortem.