bankielewicz
UserAI-powered spec-driven development framework with 26+ specialized subagents, mandatory TDD, immutable architectural constraints, and automated quality gates — enforcing zero technical debt from ideation to release.
Categories
Indexed Skills (43)
framework-rot-audit
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).
spec-driven-agents
Create DevForgeAI-aware Claude Code subagents with structural anti-skip enforcement (Execute-Verify-Record pattern) across all 6 phases. Prevents token optimization bias through lean orchestration, per-phase reference loading, checkpoint persistence, and artifact verification. Use when user runs /create-agent command, requests custom subagent creation with framework integration, or says "create a subagent" or "generate an agent". Supports guided, template, domain, and custom spec modes. Do NOT use for skill creation (use skill-creator) or command creation (use manual workflow).
spec-driven-analytics
Orchestrate session data mining operations through a 7-phase workflow with structural anti-skip enforcement. Analyzes Claude Code history.jsonl files and workflow artifacts to deliver formatted, actionable analytics for workflow patterns, errors, decisions, and command sequences. Prevents token optimization bias through per-phase reference loading, checkpoint persistence, Execute-Verify-Record enforcement, and artifact verification. Use when analyzing session data, extracting workflow patterns, investigating error trends, or reviewing development decisions. Always use this skill when the user runs /analytics or mentions session analytics, workflow patterns, error mining, decision archive, or command sequence analysis.
spec-driven-dev
Implements user stories through spec-driven TDD workflow (Red-Green-Refactor) with structural anti-skip enforcement. Replicates all 12 phases of the DevForgeAI development workflow using the Execute-Verify-Gate pattern at every step. Designed to prevent token optimization bias through lean orchestration, fresh-context subagent delegation, and binary CLI gate enforcement. Use when developing features from story specifications, building code that must comply with context files, or running TDD workflows.
spec-driven-development-architecture
Produces a per-feature Development Architecture Document through a spec-driven workflow with structural anti-skip enforcement. This skill is the micro/per-feature architect phase: it consumes the Solution Architecture Document and produces implementation-ready design — layer placement, design patterns, module structure, dependency wiring, test-strategy hooks, and story seeds for /create-story. Use when the user runs /create-development-architecture after the solution-architecture phase. This skill produces DESIGN ONLY — it does NOT write story files (use /create-story) and does NOT write production code (that is the backend-architect subagent inside /dev).
spec-driven-documentation
Automated documentation generation, auditing, and remediation with structural anti-skip enforcement. Supports 3 workflows: Generation (greenfield/brownfield), Audit (4-dimension DevEx scoring), and Fix (automated/interactive remediation). Uses Execute-Verify-Gate pattern at every step. Designed to prevent token optimization bias through lean orchestration, fresh-context subagent delegation, per-phase reference loading, and binary CLI gate enforcement. Use when generating project documentation, updating docs after story completion, or analyzing documentation coverage.
spec-driven-feedback
Retrospective feedback system with Execute-Verify-Gate structural anti-skip enforcement for DevForgeAI operations. Captures feedback after /dev, /qa, /release, sprint planning, or manual triggers. Handles 5 feedback types: conversation, summary, metrics, checklist, and ai_analysis. Prevents token optimization bias through lean orchestration, per-phase reference loading, checkpoint persistence, and binary CLI gate enforcement. Use when feedback needs to be captured, when the user mentions retrospectives, lessons learned, workflow improvements, process feedback, or wants to review what went well or poorly. Also handles AI architectural analysis, feedback search, export/import, and configuration management.
spec-driven-ideation
Transform business ideas into structured requirements through guided discovery with structural anti-skip enforcement (Execute-Verify-Gate pattern). Applies per-phase reference loading, checkpoint persistence, and artifact verification to every step of the 7-phase ideation process. Prevents token optimization bias through lean orchestration. Use when users say "I have a business idea", "help me define requirements", "let's explore what to build", or runs /ideate. Do NOT use when user wants to brainstorm a vague problem (use spec-driven-brainstorming) or wants a business plan directly (use planning-business).
spec-driven-lifecycle
Coordinates spec-driven development lifecycle from Epic -> Sprint -> Story -> Architecture -> Development -> QA -> Release with structural anti-skip enforcement. Manages story lifecycle across 11 workflow states, enforces 4 quality gates, and orchestrates skill invocation. Replaces spec-driven-lifecycle as the unified lifecycle coordinator. Use when starting sprints, managing story workflow progression, auditing deferrals, running sprint retrospectives, or coordinating multi-story releases. Always use this skill when /orchestrate, /create-sprint, or /audit-deferrals is invoked.
spec-driven-mcp-converter
Convert any MCP (Model Context Protocol) server into a standalone CLI utility and auto-generate companion skill documentation through an 8-phase workflow with structural anti-skip enforcement. Prevents token optimization bias through per-phase reference loading, checkpoint persistence, Execute-Verify-Record enforcement, and artifact verification. Use when you have an MCP server (Puppeteer, filesystem, weather, database, etc.) and need to: (1) Create a standalone CLI wrapper that Claude Code can execute, (2) Auto-generate a skill so Claude understands how to use the CLI, (3) Bridge MCP async patterns into sync CLI patterns, or (4) Rapidly prototype tool integration without MCP server overhead. Always use this skill when the user runs /convert-mcp. Make sure to use this skill whenever the user mentions converting MCP servers, bridging MCP to CLI, wrapping MCP tools as commands, or generating CLI utilities from MCP definitions — even if they don't explicitly say "convert-mcp".
spec-driven-qa-remediation
Process QA gap files and create remediation user stories with structural anti-skip enforcement (Execute-Verify-Gate pattern at every step). Applies per-phase reference loading, checkpoint persistence, and binary CLI gate enforcement to every step of the 7-phase QA remediation process. Prevents token optimization bias through lean orchestration, fresh-context subagent delegation, and artifact verification. Use when converting QA findings into actionable development work, processing imported QA reports, or systematically addressing accumulated technical debt from gap files. Always use this skill when the user runs /review-qa-reports or mentions QA gap remediation, gap-to-story conversion, or technical debt from QA reports.
spec-driven-rca
Unified root cause analysis with 4-layer anti-skip enforcement for both tactical (dev workflow diagnosis) and strategic (5 Whys RCA documents) modes. Tactical mode auto-triggers after 2-3 failed fix attempts during TDD, returning fix prescriptions. Strategic mode invoked via /rca command, producing self-contained RCA documents with 5 Whys analysis, evidence collection, and actionable recommendations. Uses Execute-Verify-Record pattern at every step to prevent token optimization bias. Use this skill whenever root cause analysis is needed — after repeated test failures, integration failures, QA violations, framework breakdowns, workflow violations, or when the user runs /rca. Also use when the diagnosis-before-fix rule triggers after 3+ consecutive fix attempts on the same error.
spec-driven-research
Capture, persist, and query research findings across sessions through a 7-phase workflow with structural anti-skip enforcement. Transforms web research, competitive analysis, technology evaluations, and market research into structured documents that survive session restarts. Prevents token optimization bias through per-phase reference loading, checkpoint persistence, Execute-Verify-Record enforcement, and artifact verification. Use when conducting competitive analysis, evaluating technologies, researching markets, planning integrations, or investigating architecture patterns. Always use this skill when the user runs /research or mentions research capture, knowledge persistence, or structured research documentation.
spec-driven-solution-architecture
Produces a per-epic Solution Architecture Document through a spec-driven workflow with structural anti-skip enforcement. This skill is the meso/per-epic architect phase: it consumes the System Architecture Document, decomposes an epic into components, interface contracts, a data model, and features with feasibility verdicts. Use when the user runs /create-solution-architecture after the system-architecture phase. Do NOT use for constitutional/system-wide decisions (use spec-driven-system-architecture) or per-feature implementation design (use spec-driven-development-architecture).
spec-driven-stories
Create user stories with acceptance criteria, technical specifications, and UI specifications through an 8-phase workflow with structural anti-skip enforcement. Prevents token optimization bias through per-phase reference loading, checkpoint persistence, Execute-Verify-Record enforcement, and artifact verification. Use when transforming feature descriptions into structured stories, generating stories from epic features, or creating follow-up stories for deferred work. Supports CRUD, authentication, workflow, and reporting story types with complete technical and UI specifications.
spec-driven-system-architecture
Produces the System Architecture Document and the constitutional context files for a project through a spec-driven workflow with structural anti-skip enforcement. This skill is the macro/constitutional architect phase: it consumes the Project Management plan, locks the technology stack, defines system boundaries and integration topology, and emits the immutable context files plus ADRs. Use when the user runs /create-system-architecture or after the PM (/ideate) phase completes. Do NOT use for per-epic technical design (use spec-driven-solution-architecture).
spec-driven-ui
Generate front-end UI specifications, code, and a framework-agnostic Design Source of Truth (design.md) for Web, GUI, or Terminal interfaces through a 9-phase workflow with structural anti-skip enforcement. Supports Web (React, Blazor, ASP.NET, HTML), Desktop GUI (WPF, Tkinter), and Terminal interfaces. Three modes: generated (interactive discovery), extracted (from existing mockup code via --extract), and hybrid. Produces design.md — a single document from which any AI can recreate the complete UI in any framework. Use when stories require UI components, when generating visual specifications from requirements, or when extracting a design source of truth from existing mockups. Always use this skill when the user runs /create-ui.
spec-driven-sprint
Drives an ad-hoc, resumable spec-driven sprint from a single GitHub issue with structural anti-skip enforcement. Given an issue, it researches the fix surface in plan mode, materializes a self-contained resumable HTML spec (work cards + embedded AI resumption prompt), creates an isolated worktree off the remote default branch, executes each work card (TDD Red-Green-Refactor where there is code), QA-validates against the spec's acceptance criteria in an iteration loop, and opens a PR — all through the Execute-Verify-Gate pattern at every step. No story file is required. Use when turning a GitHub issue into a hook-enforced, resumable sprint, or when the user runs /spec-sprint. Distinct from /create-sprint, which plans story sprints from an existing backlog; this skill is issue-driven and produces no story artifacts.
spec-driven-brainstorming
Interactive question-driven discovery skill that transforms vague business problems into a complete, self-contained HTML Business Analysis. Applies structural anti-skip enforcement (Execute-Verify-Gate pattern) to every step of the 11-phase Business Analysis 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).
spec-driven-cc-guide
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 A
spec-driven-ci
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.
spec-driven-collaboration
Generate self-contained collaboration documents for sharing issues with external AI systems (Gemini, ChatGPT, etc.) with structural anti-skip enforcement (Execute-Verify-Record pattern at every step). Interactively gathers context, reads actual code files, loads constitutional constraints, and produces a complete 10-section package ready to paste into the target LLM. Use when the user wants to collaborate with another AI, share an issue for joint problem-solving, get a fresh perspective from a peer LLM, or needs help from an external AI that doesn't have access to the codebase. Make sure to use this skill whenever the user mentions cross-AI collaboration, sharing issues with Gemini/ChatGPT/Copilot, peer review from another AI, or wants a second opinion from an external LLM.
spec-driven-coverage
Validate epic-to-story coverage with gap detection and batch story creation using structural anti-skip enforcement. Implements 6 phases of the DevForgeAI coverage workflow using the Execute-Verify-Gate pattern at every step. Designed to prevent token optimization bias through lean orchestration, fresh-context subagent delegation, and binary CLI gate enforcement. Detects coverage gaps between epics and stories, generates visual coverage reports, and orchestrates batch story creation with failure isolation. Use when validating epic coverage, detecting story gaps, or batch-creating stories for uncovered features. Always use this skill when the user runs /validate-epic-coverage or /create-missing-stories.
spec-driven-migration
Reference-sweep migration workflow for the DevForgeAI dual-path codebase. Replaces every occurrence of a `from_pattern` with a `to_pattern` across a defined corpus via 4-layer anti-skip enforcement: classify-first, dual-path identical edits, fresh-context cluster workers, and global verification. Encodes the playbook proven on PR #68 (source-tree.md → source-tree/, 324 files, 0 dual-path drift). Use when `/migrate-refs` is invoked, when a framework rename / retirement / library swap needs to land across many dual-path files, or when the user mentions a reference-sweep migration. Do NOT use for audit-finding-driven cleanup (use spec-driven-remediation) or general code refactoring without a defined from/to pattern.
spec-driven-qa
Validates code quality through spec-driven QA validation with structural anti-skip enforcement. Replicates all 6 phases of the DevForgeAI QA workflow using the Execute-Verify-Gate pattern at every step. Designed to prevent token optimization bias through lean orchestration, fresh-context subagent delegation, and binary CLI gate enforcement. Enforces test coverage (95%/85%/80% strict thresholds), detects anti-patterns, validates spec compliance, and analyzes code quality metrics. Use when validating implementations, ensuring quality standards, or preparing for release. Always use this skill when the user runs /qa or mentions QA validation, quality checks, or coverage analysis.
spec-driven-release
Orchestrates production releases through spec-driven deployment workflow with structural anti-skip enforcement. Implements 8 phases covering setup, build, validation, staging, production deployment, post-deployment validation, documentation, and monitoring using the Execute-Verify-Gate pattern at every step. Designed to prevent token optimization bias through lean orchestration, fresh-context subagent delegation, and binary CLI gate enforcement. Supports multiple deployment strategies (blue-green, canary, rolling, recreate) and environments (staging, production). Use when deploying QA-approved stories. Always use this skill when the user runs /release.
spec-driven-remediation
Apply automated and guided fixes to story, epic, and context files based on structured audit findings with 4-layer anti-skip enforcement. Classifies findings by fix complexity, applies safe automated fixes, guides interactive fixes with user confirmation, verifies all changes, and produces a fix report. Uses Execute-Verify-Record pattern at every step to prevent token optimization bias. Use when /fix-story is invoked, when audit findings need remediation, or when custody chain validation produces findings requiring correction. Make sure to use this skill whenever the user mentions fixing stories, remediating audit findings, applying fixes from /validate-stories output, or addressing custody chain violations.
backend-architect-contract-spec
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/${STORY_ID}/contracts/), per-subagent phase-specific extensions, and the canonical template at assets/templates/contract-template.yaml. Preloaded into each of the 5 subagents via the `skills:` frontmatter array so the contract schema is available at subagent startup without on-demand reads.
backend-architect-framework-patterns
Language- and framework-specific implementation templates for Python (FastAPI + SQLAlchemy), TypeScript/JavaScript (Node.js + Express/TypeORM), and C# (.NET Core). Includes domain entities, application services, infrastructure repositories, API controllers, database transaction patterns, and input validation snippets. Preloaded into the backend-architect subagent so TDD Green phase implementation can emit framework-idiomatic code without on-demand reference loads.
backend-architect-implementation-patterns
Reference patterns for clean architecture, dependency injection, repository pattern, domain-driven design, error handling, security best practices (parameterized queries, no hardcoded secrets), and common backend anti-patterns. Preloaded into the backend-architect subagent so layer-placement, pattern-selection, and anti-pattern-avoidance decisions during TDD Green phase implementation happen without on-demand reference loads.
building-team
Guided team-building workflow covering first hire decisions, co-founder compatibility, and role planning
github-incident-from-feedback
Convert selected AI-analysis recommendations from `devforgeai/feedback/ai-analysis/${STORY_ID}/...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 ai_analysis 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 ai_analysis-derived work — slash commands and other skills MUST delegate here rather than calling gh directly.
github-incident-from-rca
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.
github-incident-from-recommendations
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.
managing-finances
Guides entrepreneurs through financial planning including pricing strategy selection and financial modeling
operating-business
Operations planning skill with progressive disclosure menu for launch readiness, tool selection, process design, and scaling assessment
researching-market
Guided market research workflow covering TAM/SAM/SOM market sizing, competitive landscape analysis, and customer interview preparation
advising-legal
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.
assessing-entrepreneur
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.
coaching-entrepreneur
Use when providing entrepreneurial coaching, business guidance, and confidence support to founders and solo entrepreneurs.
marketing-business
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.
planning-business
Business planning skill with Lean Canvas, milestone planning, and business model analysis. Use when users need to create or refine business plans.
web-scraper-seo
Scrape and clone websites into a navigable local mirror with rewritten links and inline CSS, then analyze them for SEO, WCAG 2.1 accessibility, and design tokens (colors, typography, spacing). Use when the user provides a URL and wants to capture, clone, reverse-engineer, or audit a site — including JavaScript-rendered SPAs (React, Next.js, Vue, Angular) — or wants design inspiration, design-token extraction, broken-link detection, or keyword-density analysis from live pages.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.