AI Agent Workflow Collection

Use when providing educational legal structure guidance for entrepreneurs. Covers business entity selection, liability considerations, IP protection, and professional referral triggers. Educational only - not legal advice.

Use when a solo developer or aspiring entrepreneur needs a cognitive work-style assessment to personalize business coaching. Guides users through a 6-dimension self-assessment questionnaire and generates a structured profile.

Contract-specification reference for the DevForgeAI per-invocation work-contract handoff between the primary Claude session and the 5 development subagents (backend-architect, frontend-developer, refactoring-specialist, test-automator, integration-tester). Covers schema fields, lifecycle (primary writes → subagent reads + appends completion → gate verifies), file-path conventions (tmp/${STORYID}/contracts/), per-subagent phase-specific extensions, and the canonical template at assets/templates/contract-template.yaml. Preloaded into each of the 5 subagents via the skills: frontmatter array so the contract schema is available at subagent startup without on-demand reads.

Language- and framework-specific implementation templates for Python (FastAPI + SQLAlchemy), TypeScript/JavaScript (Node.js + Express/TypeORM), and C (.NET Core). Includes domain entities, application services, infrastructure repositories, API controllers, database transaction patterns, and input validation snippets. Preloaded into the backend-architect subagent so TDD Green phase implementation can emit framework-idiomatic code without on-demand reference loads.

Reference patterns for clean architecture, dependency injection, repository pattern, domain-driven design, error handling, security best practices (parameterized queries, no hardcoded secrets), and common backend anti-patterns. Preloaded into the backend-architect subagent so layer-placement, pattern-selection, and anti-pattern-avoidance decisions during TDD Green phase implementation happen without on-demand reference loads.

Guided team-building workflow covering first hire decisions, co-founder compatibility, and role…

Use when providing entrepreneurial coaching, business guidance, and confidence support to founders and solo entrepreneurs.

Framework-internal rot/silo audit. Detects wiring/reference rot in a DevForgeAI install — artifacts DEFINED but never wired in (orphaned agents/hooks/skills = silos) and references that point at a NON-EXISTENT artifact (dangling) — and orchestrates the existing dead-code-detector for function-level dead code, then synthesizes a GROUNDED inventory report. Read-only: it never mutates the repo and never asserts a false orphan (mentioned-but-uninvoked is INCONCLUSIVE, not orphan). Use when the user runs /audit-rot, asks to audit the framework for orphans / dead code / silos / rot, or asks "what is defined but never used here". Do NOT use for structural orphans like backups/duplicates/dual-path size-drift (use /audit-orphans) or for a reference-sweep migration (use /migrate-refs).

Convert selected AI-analysis recommendations from devforgeai/feedback/ai-analysis/${STORYID}/...ai-analysis.json files into GitHub issues in bankielewicz/DevForgeAI via gh issue create. Owns drafting, summary preview, drill-down approval flow, and posting. Consumes the embedded Github-incident-template.md as the issue-body schema and AI prompt. Use this skill whenever the user runs /create-incident-from-feedback, asks to convert aianalysis recommendations into GitHub issues, asks to "post issues from feedback", asks to "create incidents from framework-analyst recommendations", or wants to turn AI-analysis findings into actionable GitHub work-orders. The skill is the only place in the framework that calls gh issue create for aianalysis-derived work — slash commands and other skills MUST delegate here rather than calling gh directly.

Draft and post a single GitHub issue to bankielewicz/DevForgeAI from an inline spontaneous observation — a bug or enhancement discovered live during active work, with no upstream source document. Owns drafting, summary preview, drill-down approval flow, and posting. Consumes the embedded Github-incident-template.md as the issue-body schema and AI prompt. Use this skill whenever the user runs /create-incident, asks to "file a bug from something I just noticed", asks to "create an incident from this observation", wants to turn a spontaneous finding into a GitHub work-order, or an agent finds a framework defect live and needs to file it through the template pipeline. The skill is the only place in the framework that calls gh issue create for observation-derived work — slash commands and other skills MUST delegate here rather than calling gh directly.

Convert selected RCA recommendations into GitHub issues in bankielewicz/DevForgeAI via gh issue create. Owns drafting, summary preview, drill-down approval flow, and posting. Consumes the embedded Github-incident-template.md as the issue-body schema and AI prompt. Use this skill whenever the user runs /create-incident-from-rca, asks to convert RCA recommendations into GitHub issues, asks to "post issues from RCA", asks to "create incidents from RCA recommendations", or wants to turn analysis findings into actionable GitHub work-orders. The skill is the only place in the framework that calls gh issue create for RCA-derived work — slash commands and other skills MUST delegate here rather than calling gh directly.

Convert selected QA recommendations from devforgeai/qa/recommendations/STORY-NNN-qa-recommendations.md into GitHub issues in bankielewicz/DevForgeAI via gh issue create. Owns drafting, summary preview, drill-down approval flow, and posting. Consumes the embedded Github-incident-template.md as the issue-body schema and AI prompt. Use this skill whenever the user runs /create-incident-from-recommendations, asks to convert QA recommendations into GitHub issues, asks to "post issues from QA recs", asks to "create incidents from STORY-NNN findings", or wants to turn QA-validated findings into actionable GitHub work-orders. The skill is the only place in the framework that calls gh issue create for QA-recs-derived work — slash commands and other skills MUST delegate here rather than calling gh directly.

Guides entrepreneurs through financial planning including pricing strategy selection and financial…

Go-to-market strategy builder with channel selection matrix, budget allocation, and 30-day launch action plan. Use when users need to create marketing strategies or go-to-market plans.

Operations planning skill with progressive disclosure menu for launch readiness, tool selection, process design, and scaling…

Require a planning-only response before implementation when a request needs design, sequencing, risk analysis, user approval, or replaces Claude-Code-style EnterPlanMode/ExitPlanMode instructions in Codex skills. Use when updating or authoring Codex skills that mention plan mode, EnterPlanMode, ExitPlanMode, planning gates, or "plan before editing" workflows, and when Codex must avoid file edits unless the session was explicitly started with /plan.

Business planning skill with Lean Canvas, milestone planning, and business model analysis. Use when users need to create or refine business plans.

Guided market research workflow covering TAM/SAM/SOM market sizing, competitive landscape analysis, and customer interview…

Create DevForgeAI-aware Claude Code subagents with structural anti-skip enforcement (Execute-Verify-Record pattern) across all 6 phases.

Orchestrate session data mining operations through a 7-phase workflow with structural anti-skip enforcement.

Creates immutable context files and architecture documentation through spec-driven workflow with structural anti-skip enforcement. Replicates all 11 phases of the DevForgeAI architecture workflow using the Execute-Verify-Gate pattern at every step. Designed to prevent token optimization bias through lean orchestration, fresh-context subagent delegation, and artifact verification. Use when creating context files, making technology decisions, establishing project structure, or creating epics. Always use this skill when the user runs /create-context or /create-epic. Do NOT use when user wants spec-driven development (use spec-driven-dev) or QA validation (use spec-driven-qa).

Interactive question-driven discovery skill that transforms vague business problems into structured AI-consumable documents. Applies structural anti-skip enforcement (Execute-Verify-Gate pattern) to every step of the 7-phase discovery workflow (Phase 00 is inline initialization). Prevents token optimization bias through lean orchestration, per-phase reference loading, and artifact verification. Use when user says "brainstorm", wants to explore a vague business problem, needs stakeholder analysis, or runs /brainstorm. Do NOT use when user has structured requirements (use spec-driven-ideation) or wants a business plan directly (use planning-business).

Expert knowledge base for Claude Code Terminal — the CLI tool itself, not coding tasks. Implements 4 knowledge-retrieval phases with structural anti-skip enforcement using the Execute-Verify-Gate pattern at every step. Designed to prevent token optimization bias that causes reference file skipping by making every reference load mandatory and verifiable. MUST use this skill whenever the user asks about Claude Code features, configuration, setup, or troubleshooting. This includes: keyboard shortcuts not working (Option key, Alt+P, Shift+Enter, Ctrl+B), creating or configuring subagents/skills/commands/plugins, setting up hooks (PreToolUse, PostToolUse, HTTP hooks), installing or debugging MCP servers, GitHub Actions or GitLab CI/CD integration for PR reviews, switching models mid-conversation, undoing or rewinding Claude's changes, proxy/network configuration, permission modes, memory and CLAUDE.md setup, the /batch /simplify /debug bundled skills, git worktrees, agent teams, remote control, headless mode, or ANY question where the user is asking about how Claude Code works rather than asking Claude Code to do coding work. When in doubt about whether a question is about Claude Code itself vs. a coding task, prefer triggering this skill — it will not interfere with coding-focused responses.

Generate CI/CD pipeline workflows through spec-driven workflow generation with structural anti-skip enforcement. Implements 5 phases covering preflight validation, configuration loading, workflow template generation, cost optimization, and final validation using the Execute-Verify-Gate pattern at every step. Designed to prevent token optimization bias through lean orchestration and binary CLI gate enforcement. Currently supports GitHub Actions with cost-optimized Claude API integration (prompt caching, Haiku preference, max-turns limits). Use when setting up CI/CD automation for DevForgeAI projects. Always use this skill when the user runs /setup-github-actions. Also use when the user mentions GitHub Actions setup, CI/CD pipeline generation, headless DevForgeAI execution, or workflow automation for /dev and /qa commands.